diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 1631e2d..9b97477 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -1613,6 +1613,9 @@ public void setSparkConfigUpdated(boolean isSparkConfigUpdated) { HIVE_LOG_EXPLAIN_OUTPUT("hive.log.explain.output", false, "Whether to log explain output for every query.\n" + "When enabled, will log EXPLAIN EXTENDED output for the query at INFO log4j log level."), + HIVE_EXPLAIN_USER("hive.explain.user", false, + "Whether to show explain result at user level.\n" + + "When enabled, will log EXPLAIN output for the query at user level."), // prefix used to auto generated column aliases (this should be started with '_') HIVE_AUTOGEN_COLUMNALIAS_PREFIX_LABEL("hive.autogen.columnalias.prefix.label", "_c", diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties index 288270e..676a093 100644 --- a/itests/src/test/resources/testconfiguration.properties +++ b/itests/src/test/resources/testconfiguration.properties @@ -287,6 +287,9 @@ minitez.query.files=bucket_map_join_tez1.q,\ bucket_map_join_tez2.q,\ dynamic_partition_pruning.q,\ dynamic_partition_pruning_2.q,\ + explainuser_1.q,\ + explainuser_2.q,\ + explainuser_3.q,\ hybridhashjoin.q,\ mapjoin_decimal.q,\ lvj_mapjoin.q, \ diff --git a/ql/src/java/org/apache/hadoop/hive/ql/Context.java b/ql/src/java/org/apache/hadoop/hive/ql/Context.java index 0f7da53..c76fdc2 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/Context.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/Context.java @@ -23,6 +23,7 @@ import java.io.IOException; import java.net.URI; import java.text.SimpleDateFormat; +import java.util.ArrayList; import java.util.Date; import java.util.HashMap; import java.util.List; @@ -84,6 +85,7 @@ private final Configuration conf; protected int pathid = 10000; protected boolean explain = false; + protected List cboInfo = new ArrayList<>(); protected boolean explainLogical = false; protected String cmd = ""; // number of previous attempts @@ -695,4 +697,12 @@ public void setAcidOperation(AcidUtils.Operation op) { public AcidUtils.Operation getAcidOperation() { return acidOperation; } + + public List getCboInfo() { + return cboInfo; + } + + public void setCboInfo(List cboInfo) { + this.cboInfo = cboInfo; + } } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/ExplainTask.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/ExplainTask.java index 149f911..af280bd 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/ExplainTask.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/ExplainTask.java @@ -40,14 +40,18 @@ import java.util.TreeMap; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.conf.HiveConf; import org.apache.hadoop.hive.metastore.api.FieldSchema; import org.apache.hadoop.hive.ql.Driver; import org.apache.hadoop.hive.ql.DriverContext; +import org.apache.hadoop.hive.ql.exec.tez.explain.TezJsonParser; import org.apache.hadoop.hive.ql.hooks.ReadEntity; import org.apache.hadoop.hive.ql.metadata.Table; import org.apache.hadoop.hive.ql.optimizer.physical.StageIDsRearranger; import org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer; +import org.apache.hadoop.hive.ql.parse.SemanticException; import org.apache.hadoop.hive.ql.plan.Explain; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.hive.ql.plan.ExplainWork; import org.apache.hadoop.hive.ql.plan.HiveOperation; import org.apache.hadoop.hive.ql.plan.OperatorDesc; @@ -288,9 +292,27 @@ public int execute(DriverContext driverContext) { JSONObject jsonDependencies = getJSONDependencies(work); out.print(jsonDependencies); } else { - JSONObject jsonPlan = getJSONPlan(out, work); - if (work.isFormatted()) { - out.print(jsonPlan); + if (work.isTezUserLevelExplain()) { + if (conf.getVar(HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) { + work.setFormatted(true); + JSONObject jsonPlan = getJSONPlan(out, work); + if (work.getCboInfo() != null && !work.getCboInfo().isEmpty()) { + StringBuffer sb = new StringBuffer(); + for (String info : work.getCboInfo()) { + sb.append(info + "\n"); + } + jsonPlan.put("cboInfo", sb.toString()); + } + TezJsonParser parser = new TezJsonParser(jsonPlan, out); + parser.print(); + } else { + throw new SemanticException("Hive tezUserLevelExplain only supports tez engine."); + } + } else { + JSONObject jsonPlan = getJSONPlan(out, work); + if (work.isFormatted()) { + out.print(jsonPlan); + } } } } @@ -566,7 +588,17 @@ private JSONObject outputPlan(Object work, PrintStream out, if (note instanceof Explain) { Explain xpl_note = (Explain) note; - if (extended || xpl_note.normalExplain()) { + boolean invokeFlag = false; + if (this.work.isTezUserLevelExplain()) { + invokeFlag = Level.USER.in(xpl_note.explainLevels()); + } else { + if (extended) { + invokeFlag = Level.EXTENDED.in(xpl_note.explainLevels()); + } else { + invokeFlag = Level.DEFAULT.in(xpl_note.explainLevels()); + } + } + if (invokeFlag) { keyJSONObject = xpl_note.displayName(); if (out != null) { out.print(indentString(indent)); @@ -589,6 +621,12 @@ private JSONObject outputPlan(Object work, PrintStream out, String appender = isLogical ? " (" + operator.getOperatorId() + ")" : ""; JSONObject jsonOut = outputPlan(operator.getConf(), out, extended, jsonOutput, jsonOutput ? 0 : indent, appender); + if (this.work.isTezUserLevelExplain()) { + if (jsonOut != null && jsonOut.length() > 0) { + ((JSONObject) jsonOut.get(JSONObject.getNames(jsonOut)[0])).put("OperatorId:", + operator.getOperatorId()); + } + } if (jsonOutput) { json = jsonOut; } @@ -623,8 +661,17 @@ private JSONObject outputPlan(Object work, PrintStream out, if (note instanceof Explain) { Explain xpl_note = (Explain) note; - - if (extended || xpl_note.normalExplain()) { + boolean invokeFlag = false; + if (this.work.isTezUserLevelExplain()) { + invokeFlag = Level.USER.in(xpl_note.explainLevels()); + } else { + if (extended) { + invokeFlag = Level.EXTENDED.in(xpl_note.explainLevels()); + } else { + invokeFlag = Level.DEFAULT.in(xpl_note.explainLevels()); + } + } + if (invokeFlag) { Object val = null; try { diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Attr.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Attr.java new file mode 100644 index 0000000..b2578a4 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Attr.java @@ -0,0 +1,39 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.tez.explain; + +public class Attr implements Comparable { + String name; + String value; + + public Attr(String name, String value) { + super(); + this.name = name; + this.value = value; + } + + @Override + public int compareTo(Attr o) { + return this.name.compareToIgnoreCase(o.name); + } + + public String toString() { + return this.name + this.value; + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Connection.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Connection.java new file mode 100644 index 0000000..90fd183 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Connection.java @@ -0,0 +1,30 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.tez.explain; + +public class Connection { + public String type; + public Vertex from; + + public Connection(String type, Vertex from) { + super(); + this.type = type; + this.from = from; + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Op.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Op.java new file mode 100644 index 0000000..909374e --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Op.java @@ -0,0 +1,216 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.tez.explain; + +import java.io.PrintStream; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; + +import org.apache.hadoop.hive.ql.parse.SemanticException; +import org.json.JSONException; +import org.json.JSONObject; + +public class Op { + String name; + String id; + Op parent; + List children; + List attrs; + JSONObject object; + List mapJoinConnections; + // the vertex that this op belongs to + Vertex vertex; + private boolean visited; + // the vertex that this op output to if this op is a ReduceOutputOperator + String outputVertexName; + + public Op(String name, String id, String outputVertexName, List children, List attrs, JSONObject object, Vertex vertex) + throws JSONException { + super(); + this.name = name; + this.id = id; + this.outputVertexName = outputVertexName; + this.children = children; + this.attrs = attrs; + this.object = object; + this.mapJoinConnections = new ArrayList<>(); + this.vertex = vertex; + this.visited = false; + } + + private void inlineMapJoinOp() throws JSONException { + // inline map join operator + if (this.name.equals("Map Join Operator")) { + JSONObject obj = object.getJSONObject("Map Join Operator"); + // get the map for posToVertex + JSONObject json = obj.getJSONObject("input vertices:"); + Map posToVertex = new HashMap<>(); + for (String pos : JSONObject.getNames(json)) { + String vertexName = json.getString(pos); + posToVertex.put(pos, vertexName); + // update the connection + Connection c = null; + for (Connection connection : vertex.parents) { + if (connection.from.name.equals(vertexName)) { + c = connection; + break; + } + } + if (c != null) { + c.from.setInlined(true); + this.addConnection(c); + vertex.parents.remove(c); + } + } + // update the attrs + removeAttr("input vertices:"); + // update the keys to use vertex name + JSONObject keys = obj.getJSONObject("keys:"); + if (keys.length() != 0) { + JSONObject newKeys = new JSONObject(); + for (String key : JSONObject.getNames(keys)) { + String vertexName = posToVertex.get(key); + if (vertexName != null) { + newKeys.put(vertexName, keys.get(key)); + } else { + newKeys.put(this.vertex.name, keys.get(key)); + } + } + // update the attrs + removeAttr("keys:"); + this.attrs.add(new Attr("keys:", newKeys.toString())); + } + } + } + + private void inlineMergeJoinOp() throws JSONException { + // inline map join operator + if (this.name.equals("Merge Join Operator")) { + if (this.vertex != null) { + for (Vertex v : this.vertex.mergeJoinDummyVertexs) { + this.addConnection(new Connection(null, v)); + v.setInlined(true); + } + this.vertex.mergeJoinDummyVertexs.clear(); + } + } + } + + private String getNameWithOpId() { + if (id != null) { + return this.name + " [" + id + "]"; + } else { + return this.name; + } + } + + public void print(PrintStream out, List indentFlag, boolean fromJoinOp) throws JSONException, SemanticException { + // print name + if (visited) { + out.println(TezJsonParser.prefixString(indentFlag) + " Please refer to the previous " + + this.getNameWithOpId()); + return; + } + visited = true; + if (!fromJoinOp) { + out.println(TezJsonParser.prefixString(indentFlag) + this.getNameWithOpId()); + } else { + out.println(TezJsonParser.prefixString(indentFlag, "|<-") + this.getNameWithOpId()); + } + fromJoinOp = false; + if (this.name.contains("Join")) { + inlineMapJoinOp(); + inlineMergeJoinOp(); + fromJoinOp = true; + } + + // print attr + List attFlag = new ArrayList<>(); + attFlag.addAll(indentFlag); + // should have | if (1) it is fromJoinOp or (2) last op but has vertex + // followed + if (fromJoinOp || (this.parent == null && this.vertex != null && !this.vertex.parents.isEmpty())) { + attFlag.add(true); + } else { + attFlag.add(false); + } + Collections.sort(attrs); + for (Attr attr : attrs) { + out.println(TezJsonParser.prefixString(attFlag) + attr.toString()); + } + + // print inline vertex + for (int index = 0; index < mapJoinConnections.size(); index++) { + Connection c = mapJoinConnections.get(index); + List vertexFlag = new ArrayList<>(); + vertexFlag.addAll(indentFlag); + // should have | if it is not the last connection or parent is not null + if (index != mapJoinConnections.size() - 1 || this.parent != null) { + vertexFlag.add(true); + c.from.print(out, vertexFlag, c.type, this.vertex); + } else { + vertexFlag.add(false); + c.from.print(out, vertexFlag, c.type, this.vertex); + } + } + // print parent op, i.e., where data comes from + if (this.parent != null) { + List parentFlag = new ArrayList<>(); + parentFlag.addAll(indentFlag); + parentFlag.add(false); + this.parent.print(out, parentFlag, fromJoinOp); + } + // print next vertex + else { + if (this.vertex != null) { + for (int index = 0; index < this.vertex.parents.size(); index++) { + Connection connection = this.vertex.parents.get(index); + List vertexFlag = new ArrayList<>(); + vertexFlag.addAll(indentFlag); + if (index != this.vertex.parents.size() - 1) { + vertexFlag.add(true); + } else { + vertexFlag.add(false); + } + connection.from.print(out, vertexFlag, connection.type, this.vertex); + } + } + } + } + + public void removeAttr(String name) { + int removeIndex = -1; + for (int index = 0; index < attrs.size(); index++) { + if (attrs.get(index).name.equals(name)) { + removeIndex = index; + break; + } + } + if (removeIndex != -1) { + attrs.remove(removeIndex); + } + } + + public void addConnection(Connection c) { + this.mapJoinConnections.add(c); + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Stage.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Stage.java new file mode 100644 index 0000000..7e58177 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Stage.java @@ -0,0 +1,249 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.tez.explain; + +import java.io.IOException; +import java.io.PrintStream; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; + +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.parse.SemanticException; +import org.apache.hadoop.hive.ql.plan.TezEdgeProperty; +import org.codehaus.jackson.JsonParseException; +import org.codehaus.jackson.map.JsonMappingException; +import org.json.JSONArray; +import org.json.JSONException; +import org.json.JSONObject; + +public class Stage { + String name; + // upstream stages, e.g., root stage + List parentStages; + // downstream stages. + List childStages; + Map vertexs; + List attrs; + Op op; + LinkedHashMap> tezStageDependency; + boolean visited; + + public Stage(String name) { + super(); + this.name = name; + parentStages = new ArrayList<>(); + childStages = new ArrayList<>(); + attrs = new ArrayList<>(); + vertexs = new LinkedHashMap<>(); + this.visited = false; + } + + public void addDependency(JSONObject object, Map stages) throws JSONException { + if (!object.has("ROOT STAGE")) { + String names = object.getString("DEPENDENT STAGES"); + for (String name : names.split(",")) { + Stage parent = stages.get(name.trim()); + this.parentStages.add(parent); + parent.childStages.add(this); + } + } + } + + public void extractVertex(JSONObject object) throws JSONException, JsonParseException, + JsonMappingException, IOException, SemanticException { + if (object.has("Tez")) { + this.tezStageDependency = new LinkedHashMap<>(); + JSONObject tez = (JSONObject) object.get("Tez"); + JSONObject vertices = tez.getJSONObject("Vertices:"); + if (tez.has("Edges:")) { + JSONObject edges = tez.getJSONObject("Edges:"); + // iterate for the first time to get all the vertices + for (String to : JSONObject.getNames(edges)) { + vertexs.put(to, new Vertex(to, vertices.getJSONObject(to))); + } + // iterate for the second time to get all the vertex dependency + for (String to : JSONObject.getNames(edges)) { + Object o = edges.get(to); + Vertex v = vertexs.get(to); + // 1 to 1 mapping + if (o instanceof JSONObject) { + JSONObject obj = (JSONObject) o; + String parent = obj.getString("parent"); + Vertex parentVertex = vertexs.get(parent); + if (parentVertex == null) { + parentVertex = new Vertex(parent, vertices.getJSONObject(parent)); + vertexs.put(parent, parentVertex); + } + String type = obj.getString("type"); + // for union vertex, we reverse the dependency relationship + if (!TezEdgeProperty.EdgeType.CONTAINS.name().equals(type)) { + v.addDependency(new Connection(type, parentVertex)); + parentVertex.children.add(v); + } else { + parentVertex.addDependency(new Connection(type, v)); + v.children.add(parentVertex); + } + this.tezStageDependency.put(v, Arrays.asList(new Connection(type,parentVertex))); + } else { + // 1 to many mapping + JSONArray from = (JSONArray) o; + List list = new ArrayList<>(); + for (int index = 0; index < from.length(); index++) { + JSONObject obj = from.getJSONObject(index); + String parent = obj.getString("parent"); + Vertex parentVertex = vertexs.get(parent); + if (parentVertex == null) { + parentVertex = new Vertex(parent, vertices.getJSONObject(parent)); + vertexs.put(parent, parentVertex); + } + String type = obj.getString("type"); + if (!TezEdgeProperty.EdgeType.CONTAINS.name().equals(type)) { + v.addDependency(new Connection(type, parentVertex)); + parentVertex.children.add(v); + } else { + parentVertex.addDependency(new Connection(type, v)); + v.children.add(parentVertex); + } + list.add(new Connection(type, parentVertex)); + } + this.tezStageDependency.put(v, list); + } + } + } else { + for (String vertexName : JSONObject.getNames(vertices)) { + vertexs.put(vertexName, new Vertex(vertexName, vertices.getJSONObject(vertexName))); + } + } + // The opTree in vertex is extracted + for (Vertex v : vertexs.values()) { + if (!v.union) { + v.extractOpTree(); + v.processMultiReduceOperator(); + } + } + } else { + String[] names = JSONObject.getNames(object); + for (String name : names) { + if (name.contains("Operator")) { + this.op = extractOp(name, object.getJSONObject(name)); + } else { + attrs.add(new Attr(name, object.get(name).toString())); + } + } + } + } + + /** + * @param opName + * @param opObj + * @return + * @throws JSONException + * @throws JsonParseException + * @throws JsonMappingException + * @throws IOException + * @throws SemanticException + * This method address the create table operator, fetch operator, + * etc + */ + Op extractOp(String opName, JSONObject opObj) throws JSONException, JsonParseException, + JsonMappingException, IOException, SemanticException { + List attrs = new ArrayList<>(); + Vertex v = null; + if (opObj.length() > 0) { + String[] names = JSONObject.getNames(opObj); + for (String name : names) { + Object o = opObj.get(name); + if (isPrintable(o)) { + attrs.add(new Attr(name, o.toString())); + } else if (o instanceof JSONObject) { + JSONObject attrObj = (JSONObject) o; + if (attrObj.length() > 0) { + if (name.equals("Processor Tree:")) { + JSONObject object = new JSONObject(); + object.put(name, attrObj); + v = new Vertex(null, object); + v.extractOpTree(); + } else { + for (String attrName : JSONObject.getNames(attrObj)) { + attrs.add(new Attr(attrName, attrObj.get(attrName).toString())); + } + } + } + } else { + throw new SemanticException("Unsupported object in " + this.name); + } + } + } + Op op = new Op(opName, null, null, null, attrs, null, v); + if (v != null) { + op.addConnection(new Connection(null, v)); + } + return op; + } + + private boolean isPrintable(Object val) { + if (val instanceof Boolean || val instanceof String || val instanceof Integer + || val instanceof Long || val instanceof Byte || val instanceof Float + || val instanceof Double || val instanceof Path) { + return true; + } + if (val != null && val.getClass().isPrimitive()) { + return true; + } + return false; + } + + public void print(PrintStream out, List indentFlag) throws JSONException, SemanticException { + // print stagename + if (visited) { + out.println(TezJsonParser.prefixString(indentFlag) + " Please refer to the previous " + + this.name); + return; + } + visited = true; + out.println(TezJsonParser.prefixString(indentFlag) + this.name); + // print vertexes + List nextIndentFlag = new ArrayList<>(); + nextIndentFlag.addAll(indentFlag); + nextIndentFlag.add(false); + for (Vertex candidate : this.vertexs.values()) { + if (!candidate.isInlined() && candidate.children.isEmpty()) { + candidate.print(out, nextIndentFlag, null, null); + } + } + if (!attrs.isEmpty()) { + Collections.sort(attrs); + for (Attr attr : attrs) { + out.println(TezJsonParser.prefixString(nextIndentFlag) + attr.toString()); + } + } + if (op != null) { + op.print(out, nextIndentFlag, false); + } + nextIndentFlag.add(false); + // print dependent stages + for (Stage stage : this.parentStages) { + stage.print(out, nextIndentFlag); + } + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/TezJsonParser.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/TezJsonParser.java new file mode 100644 index 0000000..2a3d710 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/TezJsonParser.java @@ -0,0 +1,139 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.tez.explain; + +import java.io.IOException; +import java.io.PrintStream; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Map.Entry; + +import org.apache.hadoop.hive.ql.parse.SemanticException; +import org.codehaus.jackson.JsonParseException; +import org.codehaus.jackson.map.JsonMappingException; +import org.json.JSONException; +import org.json.JSONObject; + +public class TezJsonParser { + JSONObject inputObject; + JSONObject stagePlans; + Map stages; + PrintStream outputStream; + + public TezJsonParser(JSONObject inputObject, PrintStream outputStream) throws JSONException, + JsonParseException, JsonMappingException, IOException { + super(); + this.inputObject = inputObject; + this.outputStream = outputStream; + } + + public void print() throws JSONException, JsonParseException, JsonMappingException, IOException, + SemanticException { + extractStages(); + extractStagePlans(); + // print out the cbo info + if (inputObject.has("cboInfo")) { + outputStream.println(inputObject.getString("cboInfo")); + } + // print out the vertex dependency in root stage + for (Stage candidate : this.stages.values()) { + if (candidate.tezStageDependency != null && candidate.tezStageDependency.size() > 0) { + outputStream.println("Vertex dependency in root stage"); + for (Entry> entry : candidate.tezStageDependency.entrySet()) { + StringBuffer sb = new StringBuffer(); + sb.append(entry.getKey().name); + sb.append(" <- "); + boolean printcomma = false; + for (Connection connection : entry.getValue()) { + if (printcomma) { + sb.append(", "); + } else { + printcomma = true; + } + sb.append(connection.from.name + " (" + connection.type + ")"); + } + outputStream.println(sb.toString()); + } + outputStream.println(); + } + } + List indentFlag = new ArrayList<>(); + for (Stage candidate : this.stages.values()) { + if (candidate.childStages.isEmpty()) { + candidate.print(outputStream, indentFlag); + } + } + } + + public void extractStages() throws JSONException { + this.stages = new HashMap(); + JSONObject dependency = inputObject.getJSONObject("STAGE DEPENDENCIES"); + if (dependency.length() > 0) { + // iterate for the first time to get all the names of stages. + for (String stageName : JSONObject.getNames(dependency)) { + this.stages.put(stageName, new Stage(stageName)); + } + // iterate for the second time to get all the dependency. + for (String stageName : JSONObject.getNames(dependency)) { + JSONObject dependentStageNames = dependency.getJSONObject(stageName); + this.stages.get(stageName).addDependency(dependentStageNames, this.stages); + } + } + } + + public void extractStagePlans() throws JSONException, JsonParseException, JsonMappingException, + IOException, SemanticException { + stagePlans = inputObject.getJSONObject("STAGE PLANS"); + if (stagePlans.length() > 0) { + for (String stageName : JSONObject.getNames(stagePlans)) { + JSONObject stagePlan = stagePlans.getJSONObject(stageName); + this.stages.get(stageName).extractVertex(stagePlan); + } + } + } + + /** + * @param indentFlag + * @return help to generate correct indent + */ + public static String prefixString(List indentFlag) { + StringBuilder sb = new StringBuilder(); + for (int index = 0; index < indentFlag.size(); index++) { + if (indentFlag.get(index)) + sb.append("| "); + else + sb.append(" "); + } + return sb.toString(); + } + + public static String prefixString(List indentFlag, String tail) { + StringBuilder sb = new StringBuilder(); + for (int index = 0; index < indentFlag.size(); index++) { + if (indentFlag.get(index)) + sb.append("| "); + else + sb.append(" "); + } + int len = sb.length(); + return sb.replace(len - tail.length(), len, tail).toString(); + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Vertex.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Vertex.java new file mode 100644 index 0000000..6b1ea84 --- /dev/null +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/explain/Vertex.java @@ -0,0 +1,266 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.hive.ql.exec.tez.explain; + +import java.io.IOException; +import java.io.PrintStream; +import java.util.ArrayList; +import java.util.List; + +import org.apache.hadoop.hive.ql.parse.SemanticException; +import org.codehaus.jackson.JsonParseException; +import org.codehaus.jackson.map.JsonMappingException; +import org.json.JSONArray; +import org.json.JSONException; +import org.json.JSONObject; + +public class Vertex { + public String name; + public List parents; + public List children; + public JSONObject object; + public boolean union; + public List rootOps; + boolean inlined; + boolean dummy; + public List mergeJoinDummyVertexs; + boolean hasMultiReduceOp; + boolean visited; + + public Vertex(String name, JSONObject object) { + super(); + this.name = name; + if (this.name != null && this.name.contains("Union")) { + this.union = true; + } else { + this.union = false; + } + this.object = object; + this.parents = new ArrayList<>(); + this.children = new ArrayList<>(); + this.rootOps = new ArrayList<>(); + this.inlined = false; + this.dummy = false; + this.mergeJoinDummyVertexs = new ArrayList<>(); + this.hasMultiReduceOp = false; + this.visited = false; + } + + public void addDependency(Connection connection) throws JSONException { + this.parents.add(connection); + } + + /** + * @throws JSONException + * @throws JsonParseException + * @throws JsonMappingException + * @throws IOException + * @throws SemanticException + * We assume that there is a single top-level Map Operator Tree or a + * Reduce Operator Tree in a vertex + */ + public void extractOpTree() throws JSONException, JsonParseException, JsonMappingException, + IOException, SemanticException { + if (object.length() != 0) { + for (String key : JSONObject.getNames(object)) { + if (key.equals("Map Operator Tree:")) { + extractOp(object.getJSONArray(key).getJSONObject(0)); + } else if (key.equals("Reduce Operator Tree:") || key.equals("Processor Tree:")) { + extractOp(object.getJSONObject(key)); + } + // this is the case when we have a map-side SMB join + // one input of the join is treated as a dummy vertex + else if (key.equals("Join:")) { + JSONArray array = object.getJSONArray(key); + for (int index = 0; index < array.length(); index++) { + JSONObject mpOpTree = array.getJSONObject(index); + Vertex v = new Vertex("", mpOpTree); + v.extractOpTree(); + v.setDummy(true); + mergeJoinDummyVertexs.add(v); + } + } else { + throw new SemanticException("unsupported operator tree in vertex " + this.name); + } + } + } + } + + /** + * @param operator + * @param parent + * @return + * @throws JSONException + * @throws JsonParseException + * @throws JsonMappingException + * @throws IOException + * @throws SemanticException + * assumption: each operator only has one parent but may have many + * children + */ + Op extractOp(JSONObject operator) throws JSONException, JsonParseException, JsonMappingException, + IOException, SemanticException { + String[] names = JSONObject.getNames(operator); + if (names.length != 1) { + throw new SemanticException("Expect only one operator in " + operator.toString()); + } else { + String opName = names[0]; + JSONObject attrObj = (JSONObject) operator.get(opName); + List attrs = new ArrayList<>(); + List children = new ArrayList<>(); + String id = null; + String outputVertexName = null; + for (String attrName : JSONObject.getNames(attrObj)) { + if (attrName.equals("children")) { + Object childrenObj = attrObj.get(attrName); + if (childrenObj instanceof JSONObject) { + if (((JSONObject) childrenObj).length() != 0) { + children.add(extractOp((JSONObject) childrenObj)); + } + } else if (childrenObj instanceof JSONArray) { + if (((JSONArray) childrenObj).length() != 0) { + JSONArray array = ((JSONArray) childrenObj); + for (int index = 0; index < array.length(); index++) { + children.add(extractOp(array.getJSONObject(index))); + } + } + } else { + throw new SemanticException("Unsupported operator " + this.name + + "'s children operator is neither a jsonobject nor a jsonarray"); + } + } else { + if (attrName.equals("OperatorId:")) { + id = attrObj.get(attrName).toString(); + } else if (attrName.equals("outputname:")) { + outputVertexName = attrObj.get(attrName).toString(); + } else { + attrs.add(new Attr(attrName, attrObj.get(attrName).toString())); + } + } + } + Op op = new Op(opName, id, outputVertexName, children, attrs, operator, this); + if (!children.isEmpty()) { + for (Op child : children) { + child.parent = op; + } + } else { + this.rootOps.add(op); + } + return op; + } + } + + public void print(PrintStream out, List indentFlag, String type, Vertex callingVertex) + throws JSONException, SemanticException { + // print vertexname + if (visited && !hasMultiReduceOp) { + if (type != null) { + out.println(TezJsonParser.prefixString(indentFlag, "|<-") + + " Please refer to the previous " + this.name + " [" + type + "]"); + } else { + out.println(TezJsonParser.prefixString(indentFlag, "|<-") + + " Please refer to the previous " + this.name); + } + return; + } + visited = true; + if (type != null) { + out.println(TezJsonParser.prefixString(indentFlag, "|<-") + this.name + " [" + type + "]"); + } else if (this.name != null) { + out.println(TezJsonParser.prefixString(indentFlag) + this.name); + } + // print operators + if (hasMultiReduceOp) { + // find the right op + Op choose = null; + for (Op op : this.rootOps) { + if (op.outputVertexName.equals(callingVertex.name)) { + choose = op; + } + } + if (choose != null) { + choose.print(out, indentFlag, false); + } else { + throw new SemanticException("Can not find the right reduce output operator for vertex " + + this.name); + } + } else { + for (Op op : this.rootOps) { + if (!this.isDummy()) { + op.print(out, indentFlag, false); + } + // dummy operator is treated the same as from join op + else { + op.print(out, indentFlag, true); + } + } + } + if (this.union) { + // print dependent vertexs + for (int index = 0; index < this.parents.size(); index++) { + Connection connection = this.parents.get(index); + List unionFlag = new ArrayList<>(); + unionFlag.addAll(indentFlag); + if (index != this.parents.size() - 1) { + unionFlag.add(true); + } else { + unionFlag.add(false); + } + connection.from.print(out, unionFlag, connection.type, this); + } + } + } + + public boolean isDummy() { + return dummy; + } + + public void setDummy(boolean dummy) { + this.dummy = dummy; + } + + public boolean isInlined() { + return inlined; + } + + public void setInlined(boolean inlined) { + this.inlined = inlined; + } + + public boolean isUnion() { + return union; + } + + public void setUnion(boolean union) { + this.union = union; + } + + public void processMultiReduceOperator() { + // check if it is a reduce vertex and its children is more than 1; + if (!this.name.contains("Reduce") || this.rootOps.size() < 2) { + return; + } + // check if all the child ops are a reduce output operator + for (Op op : this.rootOps) { + if (!op.name.contains("Reduce")) + return; + } + this.hasMultiReduceOp = true; + } +} diff --git a/ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java b/ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java index e572338..fbc87e8 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/io/merge/MergeFileWork.java @@ -35,6 +35,7 @@ import org.apache.hadoop.hive.ql.plan.MapWork; import org.apache.hadoop.hive.ql.plan.PartitionDesc; import org.apache.hadoop.hive.ql.plan.TableDesc; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.mapred.InputFormat; import java.io.IOException; @@ -42,7 +43,7 @@ import java.util.LinkedHashMap; import java.util.List; -@Explain(displayName = "Merge File Operator") +@Explain(displayName = "Merge File Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class MergeFileWork extends MapWork { private static final Log LOG = LogFactory.getLog(MergeFileWork.class); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/stats/PartialScanWork.java b/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/stats/PartialScanWork.java index 095afd4..c0a8ae7 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/stats/PartialScanWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/stats/PartialScanWork.java @@ -28,6 +28,7 @@ import org.apache.hadoop.hive.ql.plan.Explain; import org.apache.hadoop.hive.ql.plan.MapWork; import org.apache.hadoop.hive.ql.plan.PartitionDesc; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.mapred.Mapper; /** @@ -88,7 +89,7 @@ public boolean isGatheringStats() { /** * @return the aggKey */ - @Explain(displayName = "Stats Aggregation Key Prefix", normalExplain = false) + @Explain(displayName = "Stats Aggregation Key Prefix", explainLevels = { Level.EXTENDED }) public String getAggKey() { return aggKey; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/truncate/ColumnTruncateWork.java b/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/truncate/ColumnTruncateWork.java index 092f627..d63aa29 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/truncate/ColumnTruncateWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/io/rcfile/truncate/ColumnTruncateWork.java @@ -30,9 +30,10 @@ import org.apache.hadoop.hive.ql.plan.ListBucketingCtx; import org.apache.hadoop.hive.ql.plan.MapWork; import org.apache.hadoop.hive.ql.plan.PartitionDesc; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.mapred.Mapper; -@Explain(displayName = "Column Truncate") +@Explain(displayName = "Column Truncate", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ColumnTruncateWork extends MapWork implements Serializable { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/AlterTablePartMergeFilesDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/AlterTablePartMergeFilesDesc.java index eaf3dc4..bdb872a 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/AlterTablePartMergeFilesDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/AlterTablePartMergeFilesDesc.java @@ -26,8 +26,10 @@ import org.apache.hadoop.hive.ql.plan.Explain; import org.apache.hadoop.hive.ql.plan.ListBucketingCtx; import org.apache.hadoop.mapred.InputFormat; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Alter Table Partition Merge Files") + +@Explain(displayName = "Alter Table Partition Merge Files", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class AlterTablePartMergeFilesDesc { private String tableName; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index 9596269..97e524d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -182,6 +182,7 @@ public CalcitePlanner(HiveConf conf) throws SemanticException { super(conf); if (!HiveConf.getBoolVar(conf, HiveConf.ConfVars.HIVE_CBO_ENABLED)) { runCBO = false; + this.ctx.getCboInfo().add("CBO is disabled in HiveConf."); } } @@ -238,6 +239,7 @@ Operator genOPTree(ASTNode ast, PlannerContext plannerCtx) throws SemanticExcept } Phase1Ctx ctx_1 = initPhase1Ctx(); if (!doPhase1(newAST, getQB(), ctx_1, null)) { + this.ctx.getCboInfo().add("CBO failed, couldn't do phase1 on CBO optimized query plan"); throw new RuntimeException("Couldn't do phase1 on CBO optimized query plan"); } // unfortunately making prunedPartitions immutable is not possible @@ -248,13 +250,16 @@ Operator genOPTree(ASTNode ast, PlannerContext plannerCtx) throws SemanticExcept disableJoinMerge = false; sinkOp = genPlan(getQB()); LOG.info("CBO Succeeded; optimized logical plan."); + this.ctx.getCboInfo().add("CBO Succeeded"); LOG.debug(newAST.dump()); } catch (Exception e) { boolean isMissingStats = noColsMissingStats.get() > 0; if (isMissingStats) { LOG.error("CBO failed due to missing column stats (see previous errors), skipping CBO"); + this.ctx.getCboInfo().add("CBO failed due to missing column stats (see previous errors), skipping CBO"); } else { LOG.error("CBO failed, skipping CBO. ", e); + this.ctx.getCboInfo().add("CBO failed, skipping CBO. " + e.toString()); } if (!conf.getBoolVar(ConfVars.HIVE_IN_TEST) || isMissingStats || e instanceof CalciteSemanticException) { @@ -317,24 +322,28 @@ boolean canHandleAstForCbo(ASTNode ast, QB qb, PreCboCtx cboCtx) { && noBadTokens; if (!result) { - if (needToLogMessage) { - String msg = ""; - if (!isSupportedRoot) { - msg += "doesn't have QUERY or EXPLAIN as root and not a CTAS; "; - } - if (!isSupportedType) { - msg += "is not a query, CTAS, or insert; "; - } - if (getCreateViewDesc() != null) { - msg += "has create view; "; - } - if (!noBadTokens) { - msg += "has unsupported tokens; "; - } + String msg = ""; + if (!isSupportedRoot) { + msg += "doesn't have QUERY or EXPLAIN as root and not a CTAS; "; + } + if (!isSupportedType) { + msg += "is not a query, CTAS, or insert; "; + } + if (getCreateViewDesc() != null) { + msg += "has create view; "; + } + if (!noBadTokens) { + msg += "has unsupported tokens; "; + } - if (msg.isEmpty()) { - msg += "has some unspecified limitations; "; - } + if (msg.isEmpty()) { + msg += "has some unspecified limitations; "; + } + if (msg.length() > 0) { + this.ctx.getCboInfo().add( + "Not invoking CBO because the statement " + msg.substring(0, msg.length() - 2)); + } + if (needToLogMessage) { STATIC_LOG.info("Not invoking CBO because the statement " + msg.substring(0, msg.length() - 2)); } @@ -346,6 +355,8 @@ boolean canHandleAstForCbo(ASTNode ast, QB qb, PreCboCtx cboCtx) { if (msg == null) { return true; } + this.ctx.getCboInfo().add( + "Not invoking CBO because the statement " + msg.substring(0, msg.length() - 2)); if (needToLogMessage) { STATIC_LOG.info("Not invoking CBO because the statement " + msg.substring(0, msg.length() - 2)); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ExplainSemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ExplainSemanticAnalyzer.java index 38b6d96..97fb2c5 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ExplainSemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ExplainSemanticAnalyzer.java @@ -91,6 +91,9 @@ public void analyzeInternal(ASTNode ast) throws SemanticException { pCtx = ((SemanticAnalyzer)sem).getParseContext(); } + boolean tezUserLevelExplain = !extended && !formatted + && HiveConf.getBoolVar(ctx.getConf(), HiveConf.ConfVars.HIVE_EXPLAIN_USER); + ExplainWork work = new ExplainWork(ctx.getResFile(), pCtx, tasks, @@ -101,7 +104,9 @@ public void analyzeInternal(ASTNode ast) throws SemanticException { formatted, dependency, logical, - authorize); + authorize, + tezUserLevelExplain, + ctx.getCboInfo()); work.setAppendTaskType( HiveConf.getBoolVar(conf, HiveConf.ConfVars.HIVEEXPLAINDEPENDENCYAPPENDTASKTYPES)); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/AbstractOperatorDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/AbstractOperatorDesc.java index 476dfd1..9ab576b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/AbstractOperatorDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/AbstractOperatorDesc.java @@ -22,6 +22,7 @@ import java.util.Map; import org.apache.hadoop.hive.ql.exec.PTFUtils; +import org.apache.hadoop.hive.ql.plan.Explain.Level; public class AbstractOperatorDesc implements OperatorDesc { @@ -35,7 +36,7 @@ } @Override - @Explain(skipHeader = true, displayName = "Statistics") + @Explain(skipHeader = true, displayName = "Statistics", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Statistics getStatistics() { return statistics; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterDatabaseDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterDatabaseDesc.java index e45bc26..5e218c4 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterDatabaseDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterDatabaseDesc.java @@ -21,11 +21,13 @@ import java.io.Serializable; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * AlterDatabaseDesc. * */ -@Explain(displayName = "Create Database") +@Explain(displayName = "Create Database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class AlterDatabaseDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -68,7 +70,7 @@ public void setDatabaseProperties(Map dbProps) { this.dbProperties = dbProps; } - @Explain(displayName="name") + @Explain(displayName="name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDatabaseName() { return databaseName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterIndexDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterIndexDesc.java index db2cf7f..019210b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterIndexDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterIndexDesc.java @@ -21,11 +21,13 @@ import java.io.Serializable; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * AlterIndexDesc. * */ -@Explain(displayName = "Alter Index") +@Explain(displayName = "Alter Index", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class AlterIndexDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; private String indexName; @@ -53,7 +55,7 @@ public AlterIndexDesc(AlterIndexTypes type) { /** * @return the name of the index */ - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getIndexName() { return indexName; } @@ -69,7 +71,7 @@ public void setIndexName(String indexName) { /** * @return the baseTable */ - @Explain(displayName = "new name") + @Explain(displayName = "new name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getBaseTableName() { return baseTable; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterTableDesc.java index 24cf1da..9e1ac80 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/AlterTableDesc.java @@ -32,12 +32,13 @@ import org.apache.hadoop.hive.ql.metadata.Table; import org.apache.hadoop.hive.ql.parse.ParseUtils; import org.apache.hadoop.hive.ql.parse.SemanticException; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * AlterTableDesc. * */ -@Explain(displayName = "Alter Table") +@Explain(displayName = "Alter Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class AlterTableDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -261,12 +262,12 @@ public AlterTableDesc(String tableName, HashMap partSpec, int nu this.numberBuckets = numBuckets; } - @Explain(displayName = "new columns") + @Explain(displayName = "new columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getNewColsString() { return Utilities.getFieldSchemaString(getNewCols()); } - @Explain(displayName = "type") + @Explain(displayName = "type", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getAlterTableTypeString() { return op.getName(); } @@ -274,7 +275,7 @@ public String getAlterTableTypeString() { /** * @return the old name of the table */ - @Explain(displayName = "old name") + @Explain(displayName = "old name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOldName() { return oldName; } @@ -290,7 +291,7 @@ public void setOldName(String oldName) { /** * @return the newName */ - @Explain(displayName = "new name") + @Explain(displayName = "new name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getNewName() { return newName; } @@ -368,7 +369,7 @@ public void setProps(HashMap props) { /** * @return the input format */ - @Explain(displayName = "input format") + @Explain(displayName = "input format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getInputFormat() { return inputFormat; } @@ -384,7 +385,7 @@ public void setInputFormat(String inputFormat) { /** * @return the output format */ - @Explain(displayName = "output format") + @Explain(displayName = "output format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOutputFormat() { return outputFormat; } @@ -400,7 +401,7 @@ public void setOutputFormat(String outputFormat) { /** * @return the storage handler */ - @Explain(displayName = "storage handler") + @Explain(displayName = "storage handler", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getStorageHandler() { return storageHandler; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ArchiveWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ArchiveWork.java index 9fb5c8b..468d1bf 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ArchiveWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ArchiveWork.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ArchiveWork. * */ -@Explain(displayName = "Map Reduce") +@Explain(displayName = "Map Reduce", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ArchiveWork implements Serializable { private static final long serialVersionUID = 1L; private ArchiveActionType type; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/BaseWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/BaseWork.java index 1737a34..59e9d5f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/BaseWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/BaseWork.java @@ -29,6 +29,8 @@ import org.apache.hadoop.hive.ql.exec.HashTableDummyOperator; import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * BaseWork. Base class for any "work" that's being done on the cluster. Items like stats @@ -162,7 +164,7 @@ public void setAllColumnVectorMaps(Map> allColumnVe /** * @return the mapredLocalWork */ - @Explain(displayName = "Local Work") + @Explain(displayName = "Local Work", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public MapredLocalWork getMapRedLocalWork() { return mrLocalWork; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/BucketMapJoinContext.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/BucketMapJoinContext.java index f436bc0..4587c32 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/BucketMapJoinContext.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/BucketMapJoinContext.java @@ -30,6 +30,7 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.common.FileUtils; import org.apache.hadoop.hive.ql.exec.BucketMatcher; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * was inner class of MapreLocalWork. context for bucket mapjoin (or smb join) @@ -130,7 +131,7 @@ public void setBucketMatcherClass( this.bucketMatcherClass = bucketMatcherClass; } - @Explain(displayName = "Alias Bucket File Name Mapping", normalExplain = false) + @Explain(displayName = "Alias Bucket File Name Mapping", explainLevels = { Level.EXTENDED }) public Map>> getAliasBucketFileNameMapping() { return aliasBucketFileNameMapping; } @@ -149,7 +150,7 @@ public String toString() { } } - @Explain(displayName = "Alias Bucket Base File Name Mapping", normalExplain = false) + @Explain(displayName = "Alias Bucket Base File Name Mapping", explainLevels = { Level.EXTENDED }) public Map>> getAliasBucketBaseFileNameMapping() { return aliasBucketBaseFileNameMapping; } @@ -159,7 +160,7 @@ public void setAliasBucketBaseFileNameMapping( this.aliasBucketBaseFileNameMapping = aliasBucketBaseFileNameMapping; } - @Explain(displayName = "Alias Bucket Output File Name Mapping", normalExplain = false) + @Explain(displayName = "Alias Bucket Output File Name Mapping", explainLevels = { Level.EXTENDED }) public Map getBucketFileNameMapping() { return bucketFileNameMapping; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CollectDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CollectDesc.java index 588e14d..46f3aaf 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CollectDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CollectDesc.java @@ -17,13 +17,15 @@ */ package org.apache.hadoop.hive.ql.plan; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * CollectDesc. * */ -@Explain(displayName = "Collect") +@Explain(displayName = "Collect", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CollectDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; Integer bufferSize; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsDesc.java index a44c8e8..c000db2 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsDesc.java @@ -20,6 +20,8 @@ import java.io.Serializable; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Contains the information needed to persist column level statistics */ @@ -51,7 +53,7 @@ public void setTableName(String tableName) { this.tableName = tableName; } - @Explain(displayName = "Is Table Level Stats", normalExplain=false) + @Explain(displayName = "Is Table Level Stats", explainLevels = { Level.EXTENDED }) public boolean isTblLevel() { return isTblLevel; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsUpdateWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsUpdateWork.java index d644155..8db2889 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsUpdateWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsUpdateWork.java @@ -21,6 +21,8 @@ import java.io.Serializable; import java.util.List; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ColumnStatsUpdateWork implementation. ColumnStatsUpdateWork will persist the @@ -30,7 +32,7 @@ * PARTITION(partitionId=100) UPDATE STATISTICS for column value SET * ('maxColLen'='4444','avgColLen'='44.4'); */ -@Explain(displayName = "Column Stats Update Work") +@Explain(displayName = "Column Stats Update Work", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ColumnStatsUpdateWork implements Serializable { private static final long serialVersionUID = 1L; private ColumnStatsDesc colStats; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsWork.java index 3cae727..1d2c24d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ColumnStatsWork.java @@ -21,12 +21,14 @@ import java.io.Serializable; import org.apache.hadoop.hive.ql.exec.ListSinkOperator; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ColumnStats Work. * */ -@Explain(displayName = "Column Stats Work") +@Explain(displayName = "Column Stats Work", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ColumnStatsWork implements Serializable { private static final long serialVersionUID = 1L; private FetchWork fWork; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CommonMergeJoinDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CommonMergeJoinDesc.java index 2354139..f9c34cb 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CommonMergeJoinDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CommonMergeJoinDesc.java @@ -19,8 +19,10 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Merge Join Operator") + +@Explain(displayName = "Merge Join Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CommonMergeJoinDesc extends MapJoinDesc implements Serializable { private static final long serialVersionUID = 1L; private int numBuckets; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CopyWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CopyWork.java index 3353384..9a4e782 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CopyWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CopyWork.java @@ -21,12 +21,13 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * CopyWork. * */ -@Explain(displayName = "Copy") +@Explain(displayName = "Copy", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CopyWork implements Serializable { private static final long serialVersionUID = 1L; private Path fromPath; @@ -46,12 +47,12 @@ public CopyWork(final Path fromPath, final Path toPath, boolean errorOnSrcEmpty) this.setErrorOnSrcEmpty(errorOnSrcEmpty); } - @Explain(displayName = "source") + @Explain(displayName = "source", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Path getFromPath() { return fromPath; } - @Explain(displayName = "destination") + @Explain(displayName = "destination", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Path getToPath() { return toPath; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateDatabaseDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateDatabaseDesc.java index a6b52aa..1047b9e 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateDatabaseDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateDatabaseDesc.java @@ -21,11 +21,13 @@ import java.io.Serializable; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * CreateDatabaseDesc. * */ -@Explain(displayName = "Create Database") +@Explain(displayName = "Create Database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CreateDatabaseDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -75,7 +77,7 @@ public void setDatabaseProperties(Map dbProps) { this.dbProperties = dbProps; } - @Explain(displayName="name") + @Explain(displayName="name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getName() { return databaseName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateFunctionDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateFunctionDesc.java index dce5ece..46b0fd6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateFunctionDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateFunctionDesc.java @@ -22,12 +22,13 @@ import java.util.List; import org.apache.hadoop.hive.metastore.api.ResourceUri; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * CreateFunctionDesc. * */ -@Explain(displayName = "Create Function") +@Explain(displayName = "Create Function", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CreateFunctionDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -50,7 +51,7 @@ public CreateFunctionDesc(String functionName, boolean isTemp, String className, this.resources = resources; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getFunctionName() { return functionName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateMacroDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateMacroDesc.java index 3c5a723..443614c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateMacroDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateMacroDesc.java @@ -21,13 +21,14 @@ import java.io.Serializable; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; /** * CreateMacroDesc. * */ -@Explain(displayName = "Create Macro") +@Explain(displayName = "Create Macro", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CreateMacroDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -52,7 +53,7 @@ public CreateMacroDesc(String macroName, this.body = body; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getMacroName() { return macroName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableDesc.java index 8cadb96..124f06f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableDesc.java @@ -40,12 +40,14 @@ import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; import org.apache.hadoop.mapred.OutputFormat; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * CreateTableDesc. * */ -@Explain(displayName = "Create Table") +@Explain(displayName = "Create Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CreateTableDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; private static Log LOG = LogFactory.getLog(CreateTableDesc.class); @@ -140,12 +142,12 @@ public CreateTableDesc(String tableName, boolean isExternal, boolean isTemporary return copy == null ? null : new ArrayList(copy); } - @Explain(displayName = "columns") + @Explain(displayName = "columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getColsString() { return Utilities.getFieldSchemaString(getCols()); } - @Explain(displayName = "partition columns") + @Explain(displayName = "partition columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getPartColsString() { return Utilities.getFieldSchemaString(getPartCols()); } @@ -159,7 +161,7 @@ public void setIfNotExists(boolean ifNotExists) { this.ifNotExists = ifNotExists; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } @@ -188,7 +190,7 @@ public void setPartCols(ArrayList partCols) { this.partCols = partCols; } - @Explain(displayName = "bucket columns") + @Explain(displayName = "bucket columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getBucketCols() { return bucketCols; } @@ -197,7 +199,7 @@ public void setBucketCols(ArrayList bucketCols) { this.bucketCols = bucketCols; } - @Explain(displayName = "# buckets") + @Explain(displayName = "# buckets", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Integer getNumBucketsExplain() { if (numBuckets == -1) { return null; @@ -268,7 +270,7 @@ public void setComment(String comment) { this.comment = comment; } - @Explain(displayName = "input format") + @Explain(displayName = "input format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getInputFormat() { return inputFormat; } @@ -277,7 +279,7 @@ public void setInputFormat(String inputFormat) { this.inputFormat = inputFormat; } - @Explain(displayName = "output format") + @Explain(displayName = "output format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOutputFormat() { return outputFormat; } @@ -286,7 +288,7 @@ public void setOutputFormat(String outputFormat) { this.outputFormat = outputFormat; } - @Explain(displayName = "storage handler") + @Explain(displayName = "storage handler", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getStorageHandler() { return storageHandler; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableLikeDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableLikeDesc.java index 3dad4ab..f051712 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableLikeDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateTableLikeDesc.java @@ -21,11 +21,13 @@ import java.io.Serializable; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * CreateTableLikeDesc. * */ -@Explain(displayName = "Create Table") +@Explain(displayName = "Create Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CreateTableLikeDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String tableName; @@ -71,7 +73,7 @@ public void setIfNotExists(boolean ifNotExists) { this.ifNotExists = ifNotExists; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } @@ -80,7 +82,7 @@ public void setTableName(String tableName) { this.tableName = tableName; } - @Explain(displayName = "default input format") + @Explain(displayName = "default input format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDefaultInputFormat() { return defaultInputFormat; } @@ -89,7 +91,7 @@ public void setInputFormat(String inputFormat) { this.defaultInputFormat = inputFormat; } - @Explain(displayName = "default output format") + @Explain(displayName = "default output format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDefaultOutputFormat() { return defaultOutputFormat; } @@ -148,7 +150,7 @@ public void setDefaultSerdeProps(Map serdeProps) { this.defaultSerdeProps = serdeProps; } - @Explain(displayName = "like") + @Explain(displayName = "like", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getLikeTableName() { return likeTableName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java index dd76a82..a5cf076 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java @@ -24,12 +24,14 @@ import org.apache.hadoop.hive.metastore.api.FieldSchema; import org.apache.hadoop.hive.ql.exec.Utilities; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * CreateViewDesc. * */ -@Explain(displayName = "Create View") +@Explain(displayName = "Create View", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class CreateViewDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -65,7 +67,7 @@ public CreateViewDesc(String viewName, List schema, this.isAlterViewAs = isAlterViewAs; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getViewName() { return viewName; } @@ -74,7 +76,7 @@ public void setViewName(String viewName) { this.viewName = viewName; } - @Explain(displayName = "original text") + @Explain(displayName = "original text", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getViewOriginalText() { return originalText; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java index 79d9d16..8dbb3c1 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java @@ -23,6 +23,7 @@ import org.apache.hadoop.hive.ql.hooks.ReadEntity; import org.apache.hadoop.hive.ql.hooks.WriteEntity; import org.apache.hadoop.hive.ql.parse.AlterTablePartMergeFilesDesc; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * DDLWork. @@ -562,7 +563,7 @@ public void setUnlockDatabaseDesc(UnlockDatabaseDesc unlockDatabaseDesc) { /** * @return the createTblDesc */ - @Explain(displayName = "Create Table Operator") + @Explain(displayName = "Create Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public CreateTableDesc getCreateTblDesc() { return createTblDesc; } @@ -608,7 +609,7 @@ public void setAlterIndexDesc(AlterIndexDesc alterIndexDesc) { /** * @return the createTblDesc */ - @Explain(displayName = "Create Table Operator") + @Explain(displayName = "Create Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public CreateTableLikeDesc getCreateTblLikeDesc() { return createTblLikeDesc; } @@ -624,7 +625,7 @@ public void setCreateTblLikeDesc(CreateTableLikeDesc createTblLikeDesc) { /** * @return the createTblDesc */ - @Explain(displayName = "Create View Operator") + @Explain(displayName = "Create View Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public CreateViewDesc getCreateViewDesc() { return createVwDesc; } @@ -640,7 +641,7 @@ public void setCreateViewDesc(CreateViewDesc createVwDesc) { /** * @return the dropTblDesc */ - @Explain(displayName = "Drop Table Operator") + @Explain(displayName = "Drop Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public DropTableDesc getDropTblDesc() { return dropTblDesc; } @@ -656,7 +657,7 @@ public void setDropTblDesc(DropTableDesc dropTblDesc) { /** * @return the alterTblDesc */ - @Explain(displayName = "Alter Table Operator") + @Explain(displayName = "Alter Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public AlterTableDesc getAlterTblDesc() { return alterTblDesc; } @@ -672,7 +673,7 @@ public void setAlterTblDesc(AlterTableDesc alterTblDesc) { /** * @return the showDatabasesDesc */ - @Explain(displayName = "Show Databases Operator") + @Explain(displayName = "Show Databases Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowDatabasesDesc getShowDatabasesDesc() { return showDatabasesDesc; } @@ -688,7 +689,7 @@ public void setShowDatabasesDesc(ShowDatabasesDesc showDatabasesDesc) { /** * @return the showTblsDesc */ - @Explain(displayName = "Show Table Operator") + @Explain(displayName = "Show Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowTablesDesc getShowTblsDesc() { return showTblsDesc; } @@ -704,7 +705,7 @@ public void setShowTblsDesc(ShowTablesDesc showTblsDesc) { /** * @return the showColumnsDesc */ - @Explain(displayName = "Show Columns Operator") + @Explain(displayName = "Show Columns Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowColumnsDesc getShowColumnsDesc() { return showColumnsDesc; } @@ -720,7 +721,7 @@ public void setShowColumnsDesc(ShowColumnsDesc showColumnsDesc) { /** * @return the showFuncsDesc */ - @Explain(displayName = "Show Function Operator") + @Explain(displayName = "Show Function Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowFunctionsDesc getShowFuncsDesc() { return showFuncsDesc; } @@ -728,17 +729,17 @@ public ShowFunctionsDesc getShowFuncsDesc() { /** * @return the showLocksDesc */ - @Explain(displayName = "Show Lock Operator") + @Explain(displayName = "Show Lock Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowLocksDesc getShowLocksDesc() { return showLocksDesc; } - @Explain(displayName = "Show Compactions Operator") + @Explain(displayName = "Show Compactions Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowCompactionsDesc getShowCompactionsDesc() { return showCompactionsDesc; } - @Explain(displayName = "Show Transactions Operator") + @Explain(displayName = "Show Transactions Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowTxnsDesc getShowTxnsDesc() { return showTxnsDesc; } @@ -746,7 +747,7 @@ public ShowTxnsDesc getShowTxnsDesc() { /** * @return the lockTblDesc */ - @Explain(displayName = "Lock Table Operator") + @Explain(displayName = "Lock Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public LockTableDesc getLockTblDesc() { return lockTblDesc; } @@ -754,7 +755,7 @@ public LockTableDesc getLockTblDesc() { /** * @return the unlockTblDesc */ - @Explain(displayName = "Unlock Table Operator") + @Explain(displayName = "Unlock Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public UnlockTableDesc getUnlockTblDesc() { return unlockTblDesc; } @@ -762,7 +763,7 @@ public UnlockTableDesc getUnlockTblDesc() { /** * @return the descFuncDesc */ - @Explain(displayName = "Show Function Operator") + @Explain(displayName = "Show Function Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public DescFunctionDesc getDescFunctionDesc() { return descFunctionDesc; } @@ -818,7 +819,7 @@ public void setDescFuncDesc(DescFunctionDesc descFuncDesc) { /** * @return the showPartsDesc */ - @Explain(displayName = "Show Partitions Operator") + @Explain(displayName = "Show Partitions Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowPartitionsDesc getShowPartsDesc() { return showPartsDesc; } @@ -834,7 +835,7 @@ public void setShowPartsDesc(ShowPartitionsDesc showPartsDesc) { /** * @return the showCreateTblDesc */ - @Explain(displayName = "Show Create Table Operator") + @Explain(displayName = "Show Create Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowCreateTableDesc getShowCreateTblDesc() { return showCreateTblDesc; } @@ -850,7 +851,7 @@ public void setShowCreateTblDesc(ShowCreateTableDesc showCreateTblDesc) { /** * @return the showIndexesDesc */ - @Explain(displayName = "Show Index Operator") + @Explain(displayName = "Show Index Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ShowIndexesDesc getShowIndexesDesc() { return showIndexesDesc; } @@ -862,7 +863,7 @@ public void setShowIndexesDesc(ShowIndexesDesc showIndexesDesc) { /** * @return the descTblDesc */ - @Explain(displayName = "Describe Table Operator") + @Explain(displayName = "Describe Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public DescTableDesc getDescTblDesc() { return descTblDesc; } @@ -878,7 +879,7 @@ public void setDescTblDesc(DescTableDesc descTblDesc) { /** * @return information about the partitions we want to add. */ - @Explain(displayName = "Add Partition Operator") + @Explain(displayName = "Add Partition Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public AddPartitionDesc getAddPartitionDesc() { return addPartitionDesc; } @@ -1101,7 +1102,7 @@ public void setAlterTableAlterPartDesc(AlterTableAlterPartDesc alterPartitionDes this.alterTableAlterPartDesc = alterPartitionDesc; } - @Explain(displayName = "Truncate Table Operator") + @Explain(displayName = "Truncate Table Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public TruncateTableDesc getTruncateTblDesc() { return truncateTblDesc; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DemuxDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DemuxDesc.java index 62de2e4..ff6147d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DemuxDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DemuxDesc.java @@ -20,13 +20,15 @@ import java.util.List; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Demux operator descriptor implementation. * */ -@Explain(displayName = "Demux Operator") +@Explain(displayName = "Demux Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DemuxDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DependencyCollectionWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DependencyCollectionWork.java index 35180cd..6ca80df 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DependencyCollectionWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DependencyCollectionWork.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * DependencyCollectionWork * */ -@Explain(displayName = "Dependency Collection") +@Explain(displayName = "Dependency Collection", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DependencyCollectionWork implements Serializable { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DescDatabaseDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DescDatabaseDesc.java index 3c0ed2a..af49d92 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DescDatabaseDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DescDatabaseDesc.java @@ -21,12 +21,13 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * DescDatabaseDesc. * */ -@Explain(displayName = "Describe Database") +@Explain(displayName = "Describe Database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DescDatabaseDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -76,7 +77,7 @@ public void setExt(boolean isExt) { /** * @return the tableName */ - @Explain(displayName = "database") + @Explain(displayName = "database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDatabaseName() { return dbName; } @@ -92,7 +93,7 @@ public void setDatabaseName(String db) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DescFunctionDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DescFunctionDesc.java index 814ad73..fea5c1c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DescFunctionDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DescFunctionDesc.java @@ -21,12 +21,13 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * DescFunctionDesc. * */ -@Explain(displayName = "Describe Function") +@Explain(displayName = "Describe Function", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DescFunctionDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String name; @@ -82,7 +83,7 @@ public DescFunctionDesc(Path resFile, String name, boolean isExtended) { /** * @return the name */ - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getName() { return name; } @@ -98,7 +99,7 @@ public void setName(String name) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DescTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DescTableDesc.java index eefd4d4..d7a9888 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DescTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DescTableDesc.java @@ -22,12 +22,14 @@ import java.util.Map; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * DescTableDesc. * */ -@Explain(displayName = "Describe Table") +@Explain(displayName = "Describe Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DescTableDesc extends DDLDesc implements Serializable { public void setPartSpec(Map partSpec) { this.partSpec = partSpec; @@ -131,7 +133,7 @@ public void setPretty(boolean isPretty) { /** * @return the tableName */ - @Explain(displayName = "table") + @Explain(displayName = "table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } @@ -162,7 +164,7 @@ public String getColumnPath() { /** * @return the partSpec */ - @Explain(displayName = "partition") + @Explain(displayName = "partition", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getPartSpec() { return partSpec; } @@ -178,7 +180,7 @@ public void setPartSpecs(Map partSpec) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropDatabaseDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropDatabaseDesc.java index 66d8768..5633c52 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropDatabaseDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropDatabaseDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * DropDatabaseDesc. * */ -@Explain(displayName = "Drop Database") +@Explain(displayName = "Drop Database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DropDatabaseDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -43,7 +45,7 @@ public DropDatabaseDesc(String databaseName, boolean ifExists, boolean cascade) this.cascade = cascade; } - @Explain(displayName = "database") + @Explain(displayName = "database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDatabaseName() { return databaseName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropFunctionDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropFunctionDesc.java index e1f93a1..54dd374 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropFunctionDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropFunctionDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * DropFunctionDesc. * */ -@Explain(displayName = "Drop Function") +@Explain(displayName = "Drop Function", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DropFunctionDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -42,7 +44,7 @@ public DropFunctionDesc(String functionName, boolean isTemp) { this.isTemp = isTemp; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getFunctionName() { return functionName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropMacroDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropMacroDesc.java index 3e2aefc..9de1353 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropMacroDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropMacroDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * DropMacroDesc. * */ -@Explain(displayName = "Drop Macro") +@Explain(displayName = "Drop Macro", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DropMacroDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -40,7 +42,7 @@ public DropMacroDesc(String macroName) { this.macroName = macroName; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getMacroName() { return macroName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropTableDesc.java index c79710d..42fae24 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/DropTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/DropTableDesc.java @@ -22,12 +22,14 @@ import java.util.ArrayList; import java.util.List; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * DropTableDesc. * TODO: this is currently used for both drop table and drop partitions. */ -@Explain(displayName = "Drop Table") +@Explain(displayName = "Drop Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class DropTableDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -89,7 +91,7 @@ public DropTableDesc(String tableName, Map cboInfo; private transient BaseSemanticAnalyzer analyzer; @@ -67,7 +71,9 @@ public ExplainWork(Path resFile, boolean formatted, boolean dependency, boolean logical, - boolean authorize) { + boolean authorize, + boolean tezUserLevelExplain, + List cboInfo) { this.resFile = resFile; this.rootTasks = new ArrayList>(rootTasks); this.fetchTask = fetchTask; @@ -80,6 +86,8 @@ public ExplainWork(Path resFile, this.logical = logical; this.pCtx = pCtx; this.authorize = authorize; + this.tezUserLevelExplain = tezUserLevelExplain; + this.cboInfo = cboInfo; } public Path getResFile() { @@ -181,4 +189,20 @@ public void setAuthorize(boolean authorize) { public BaseSemanticAnalyzer getAnalyzer() { return analyzer; } + + public boolean isTezUserLevelExplain() { + return tezUserLevelExplain; + } + + public void setTezUserLevelExplain(boolean tezUserLevelExplain) { + this.tezUserLevelExplain = tezUserLevelExplain; + } + + public List getCboInfo() { + return cboInfo; + } + + public void setCboInfo(List cboInfo) { + this.cboInfo = cboInfo; + } } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ExplosionDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ExplosionDesc.java index dc56ccd..e628311 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ExplosionDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ExplosionDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ExplosionDesc. * */ -@Explain(displayName = "Explosion") +@Explain(displayName = "Explosion", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ExplosionDesc implements Serializable { private static final long serialVersionUID = 1L; private String fieldName; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/FetchWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/FetchWork.java index ef5a655..edd9cac 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/FetchWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/FetchWork.java @@ -29,13 +29,14 @@ import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.hive.ql.exec.OperatorFactory; import org.apache.hadoop.hive.ql.parse.SplitSample; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector; /** * FetchWork. * */ -@Explain(displayName = "Fetch Operator") +@Explain(displayName = "Fetch Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class FetchWork implements Serializable { private static final long serialVersionUID = 1L; @@ -185,7 +186,7 @@ public void setPartDir(ArrayList partDir) { * * @return the partDesc array list */ - @Explain(displayName = "Partition Description", normalExplain = false) + @Explain(displayName = "Partition Description", explainLevels = { Level.EXTENDED }) public ArrayList getPartDescOrderedByPartDir() { ArrayList partDescOrdered = partDesc; @@ -232,7 +233,7 @@ public void setPartDesc(ArrayList partDesc) { /** * @return the limit */ - @Explain(displayName = "limit") + @Explain(displayName = "limit", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public int getLimit() { return limit; } @@ -253,7 +254,7 @@ public void setLeastNumRows(int leastNumRows) { this.leastNumRows = leastNumRows; } - @Explain(displayName = "Processor Tree") + @Explain(displayName = "Processor Tree", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Operator getSource() { return source; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/FileSinkDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/FileSinkDesc.java index 83ebfa3..bb6cee5 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/FileSinkDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/FileSinkDesc.java @@ -24,12 +24,14 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.ql.io.AcidUtils; import org.apache.hadoop.hive.ql.metadata.Table; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * FileSinkDesc. * */ -@Explain(displayName = "File Output Operator") +@Explain(displayName = "File Output Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class FileSinkDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; @@ -151,7 +153,7 @@ public Object clone() throws CloneNotSupportedException { return (Object) ret; } - @Explain(displayName = "directory", normalExplain = false) + @Explain(displayName = "directory", explainLevels = { Level.EXTENDED }) public Path getDirName() { return dirName; } @@ -164,7 +166,7 @@ public Path getFinalDirName() { return linkedFileSink ? parentDir : dirName; } - @Explain(displayName = "table") + @Explain(displayName = "table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public TableDesc getTableInfo() { return tableInfo; } @@ -173,7 +175,7 @@ public void setTableInfo(final TableDesc tableInfo) { this.tableInfo = tableInfo; } - @Explain(displayName = "compressed") + @Explain(displayName = "compressed", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public boolean getCompressed() { return compressed; } @@ -182,7 +184,7 @@ public void setCompressed(boolean compressed) { this.compressed = compressed; } - @Explain(displayName = "GlobalTableId", normalExplain = false) + @Explain(displayName = "GlobalTableId", explainLevels = { Level.EXTENDED }) public int getDestTableId() { return destTableId; } @@ -210,7 +212,7 @@ public void setCompressType(String intermediateCompressType) { /** * @return the multiFileSpray */ - @Explain(displayName = "MultiFileSpray", normalExplain = false) + @Explain(displayName = "MultiFileSpray", explainLevels = { Level.EXTENDED }) public boolean isMultiFileSpray() { return multiFileSpray; } @@ -248,7 +250,7 @@ public void setCanBeMerged(boolean canBeMerged) { /** * @return the totalFiles */ - @Explain(displayName = "TotalFiles", normalExplain = false) + @Explain(displayName = "TotalFiles", explainLevels = { Level.EXTENDED }) public int getTotalFiles() { return totalFiles; } @@ -277,7 +279,7 @@ public void setPartitionCols(ArrayList partitionCols) { /** * @return the numFiles */ - @Explain(displayName = "NumFilesPerFileSink", normalExplain = false) + @Explain(displayName = "NumFilesPerFileSink", explainLevels = { Level.EXTENDED }) public int getNumFiles() { return numFiles; } @@ -301,7 +303,7 @@ public void setStaticSpec(String staticSpec) { this.staticSpec = staticSpec; } - @Explain(displayName = "Static Partition Specification", normalExplain = false) + @Explain(displayName = "Static Partition Specification", explainLevels = { Level.EXTENDED }) public String getStaticSpec() { return staticSpec; } @@ -310,7 +312,7 @@ public void setGatherStats(boolean gatherStats) { this.gatherStats = gatherStats; } - @Explain(displayName = "GatherStats", normalExplain = false) + @Explain(displayName = "GatherStats", explainLevels = { Level.EXTENDED }) public boolean isGatherStats() { return gatherStats; } @@ -326,7 +328,7 @@ public boolean isGatherStats() { * will be aggregated. * @return key prefix used for stats publishing and aggregation. */ - @Explain(displayName = "Stats Publishing Key Prefix", normalExplain = false) + @Explain(displayName = "Stats Publishing Key Prefix", explainLevels = { Level.EXTENDED }) public String getStatsAggPrefix() { // dirName uniquely identifies destination directory of a FileSinkOperator. // If more than one FileSinkOperator write to the same partition, this dirName diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/FilterDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/FilterDesc.java index 22fd29e..8dff2fc 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/FilterDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/FilterDesc.java @@ -19,13 +19,15 @@ package org.apache.hadoop.hive.ql.plan; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * FilterDesc. * */ -@Explain(displayName = "Filter Operator") +@Explain(displayName = "Filter Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class FilterDesc extends AbstractOperatorDesc { /** @@ -100,7 +102,7 @@ public FilterDesc( this.sampleDescr = sampleDescr; } - @Explain(displayName = "predicate") + @Explain(displayName = "predicate", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getPredicateString() { StringBuffer sb = new StringBuffer(); PlanUtils.addExprToStringBuffer(predicate, sb); @@ -116,7 +118,7 @@ public void setPredicate( this.predicate = predicate; } - @Explain(displayName = "isSamplingPred", normalExplain = false) + @Explain(displayName = "isSamplingPred", explainLevels = { Level.EXTENDED }) public boolean getIsSamplingPred() { return isSamplingPred; } @@ -133,7 +135,7 @@ public void setSampleDescr(final SampleDesc sampleDescr) { this.sampleDescr = sampleDescr; } - @Explain(displayName = "sampleDesc", normalExplain = false) + @Explain(displayName = "sampleDesc", explainLevels = { Level.EXTENDED }) public String getSampleDescExpr() { return sampleDescr == null ? null : sampleDescr.toString(); } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ForwardDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ForwardDesc.java index b03fc06..14156a4 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ForwardDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ForwardDesc.java @@ -17,13 +17,15 @@ */ package org.apache.hadoop.hive.ql.plan; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ForwardDesc. * */ -@Explain(displayName = "Forward") +@Explain(displayName = "Forward", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ForwardDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantDesc.java index f1cb323..45a9829 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantDesc.java @@ -22,8 +22,10 @@ import java.util.List; import org.apache.hadoop.hive.metastore.api.PrincipalType; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Grant") + +@Explain(displayName = "Grant", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class GrantDesc extends DDLDesc implements Serializable, Cloneable { private static final long serialVersionUID = 1L; @@ -55,7 +57,7 @@ public GrantDesc(PrivilegeObjectDesc privilegeSubject, /** * @return privileges */ - @Explain(displayName = "Privileges") + @Explain(displayName = "Privileges", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getPrivileges() { return privileges; } @@ -70,7 +72,7 @@ public void setPrivileges(List privileges) { /** * @return principals */ - @Explain(displayName = "Principals") + @Explain(displayName = "Principals", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getPrincipals() { return principals; } @@ -85,7 +87,7 @@ public void setPrincipals(List principals) { /** * @return grant option */ - @Explain(displayName = "grant option") + @Explain(displayName = "grant option", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public boolean isGrantOption() { return grantOption; } @@ -100,7 +102,7 @@ public void setGrantOption(boolean grantOption) { /** * @return privilege subject */ - @Explain(displayName="privilege subject") + @Explain(displayName="privilege subject", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public PrivilegeObjectDesc getPrivilegeSubjectDesc() { return privilegeSubjectDesc; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantRevokeRoleDDL.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantRevokeRoleDDL.java index 65db04e..894a462 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantRevokeRoleDDL.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/GrantRevokeRoleDDL.java @@ -21,8 +21,10 @@ import java.util.List; import org.apache.hadoop.hive.metastore.api.PrincipalType; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName="grant or revoke roles") + +@Explain(displayName="grant or revoke roles", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class GrantRevokeRoleDDL { private boolean grant; @@ -55,7 +57,7 @@ public GrantRevokeRoleDDL(boolean grant, List roles, /** * @return grant or revoke privileges */ - @Explain(displayName="grant (or revoke)") + @Explain(displayName="grant (or revoke)", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public boolean getGrant() { return grant; } @@ -67,7 +69,7 @@ public void setGrant(boolean grant) { /** * @return a list of principals */ - @Explain(displayName="principals") + @Explain(displayName="principals", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getPrincipalDesc() { return principalDesc; } @@ -79,7 +81,7 @@ public void setPrincipalDesc(List principalDesc) { /** * @return a list of roles */ - @Explain(displayName="roles") + @Explain(displayName="roles", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getRoles() { return roles; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/GroupByDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/GroupByDesc.java index d6aad9f..0f2855e 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/GroupByDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/GroupByDesc.java @@ -25,12 +25,14 @@ import org.apache.hadoop.hive.ql.udf.UDFType; import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFEvaluator; import org.apache.hive.common.util.AnnotationUtils; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * GroupByDesc. * */ -@Explain(displayName = "Group By Operator") +@Explain(displayName = "Group By Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class GroupByDesc extends AbstractOperatorDesc { /** * Group-by Mode: COMPLETE: complete 1-phase aggregation: iterate, terminate @@ -156,7 +158,7 @@ public void setMode(final Mode mode) { this.mode = mode; } - @Explain(displayName = "keys") + @Explain(displayName = "keys", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getKeyString() { return PlanUtils.getExprListString(keys); } @@ -169,7 +171,7 @@ public void setKeys(final ArrayList keys) { this.keys = keys; } - @Explain(displayName = "outputColumnNames") + @Explain(displayName = "outputColumnNames", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ArrayList getOutputColumnNames() { return outputColumnNames; } @@ -201,7 +203,7 @@ public void setMemoryThreshold(float memoryThreshold) { this.memoryThreshold = memoryThreshold; } - @Explain(displayName = "aggregations") + @Explain(displayName = "aggregations", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getAggregatorStrings() { List res = new ArrayList(); for (AggregationDesc agg: aggregators) { diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableDummyDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableDummyDesc.java index f15ce48..b2525f1 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableDummyDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableDummyDesc.java @@ -17,12 +17,14 @@ */ package org.apache.hadoop.hive.ql.plan; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * HashTable Dummy Descriptor implementation. * */ -@Explain(displayName = "HashTable Dummy Operator") +@Explain(displayName = "HashTable Dummy Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class HashTableDummyDesc extends AbstractOperatorDesc { private TableDesc tbl; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableSinkDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableSinkDesc.java index 03ef704..7c8eee2 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableSinkDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/HashTableSinkDesc.java @@ -25,12 +25,14 @@ import java.util.Map; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Map Join operator Descriptor implementation. * */ -@Explain(displayName = "HashTable Sink Operator") +@Explain(displayName = "HashTable Sink Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class HashTableSinkDesc extends JoinDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -285,7 +287,7 @@ public void setFilterMap(int[][] filterMap) { } @Override - @Explain(displayName = "filter mappings", normalExplain = false) + @Explain(displayName = "filter mappings", explainLevels = { Level.EXTENDED }) public Map getFilterMapString() { return toCompactString(filterMap); } @@ -301,7 +303,7 @@ public void setRetainList(Map> retainList) { /** * @return the keys in string form */ - @Explain(displayName = "keys") + @Explain(displayName = "keys", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getKeysString() { Map keyMap = new LinkedHashMap(); for (Map.Entry> k: getKeys().entrySet()) { @@ -328,7 +330,7 @@ public void setKeys(Map> keys) { /** * @return the position of the big table not in memory */ - @Explain(displayName = "Position of Big Table", normalExplain = false) + @Explain(displayName = "Position of Big Table", explainLevels = { Level.EXTENDED }) public int getPosBigTable() { return posBigTable; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinCondDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinCondDesc.java index 0c65196..b307b16 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinCondDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinCondDesc.java @@ -19,6 +19,8 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Join conditions Descriptor implementation. @@ -107,7 +109,7 @@ public void setType(final int type) { this.type = type; } - @Explain + @Explain(explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getJoinCondString() { StringBuilder sb = new StringBuilder(); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinDesc.java index 990608a..566ebcd 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/JoinDesc.java @@ -29,12 +29,14 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.hive.ql.parse.QBJoinTree; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Join operator Descriptor implementation. * */ -@Explain(displayName = "Join Operator") +@Explain(displayName = "Join Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class JoinDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; public static final int INNER_JOIN = 0; @@ -209,7 +211,7 @@ public void setReversedExprs(Map reversedExprs) { /** * @return the keys in string form */ - @Explain(displayName = "keys") + @Explain(displayName = "keys", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getKeysString() { Map keyMap = new LinkedHashMap(); for (byte i = 0; i < joinKeys.length; i++) { @@ -229,7 +231,7 @@ public void setExprs(final Map> exprs) { * * @return Map from alias to filters on the alias. */ - @Explain(displayName = "filter predicates") + @Explain(displayName = "filter predicates", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getFiltersStringMap() { if (getFilters() == null || getFilters().size() == 0) { return null; @@ -275,7 +277,7 @@ public void setFilters(Map> filters) { this.filters = filters; } - @Explain(displayName = "outputColumnNames") + @Explain(displayName = "outputColumnNames", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getOutputColumnNames() { return outputColumnNames; } @@ -293,7 +295,7 @@ public void setNoOuterJoin(final boolean noOuterJoin) { this.noOuterJoin = noOuterJoin; } - @Explain(displayName = "condition map") + @Explain(displayName = "condition map", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getCondsList() { if (conds == null) { return null; @@ -453,7 +455,7 @@ public void setFilterMap(int[][] filterMap) { this.filterMap = filterMap; } - @Explain(displayName = "filter mappings", normalExplain = false) + @Explain(displayName = "filter mappings", explainLevels = { Level.EXTENDED }) public Map getFilterMapString() { return toCompactString(filterMap); } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewForwardDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewForwardDesc.java index e944b2e..64d789a 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewForwardDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewForwardDesc.java @@ -17,13 +17,15 @@ */ package org.apache.hadoop.hive.ql.plan; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * LateralViewForwardDesc. * */ -@Explain(displayName = "Lateral View Forward") +@Explain(displayName = "Lateral View Forward", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class LateralViewForwardDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewJoinDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewJoinDesc.java index 4c0c978..12f01e5 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewJoinDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LateralViewJoinDesc.java @@ -19,13 +19,15 @@ package org.apache.hadoop.hive.ql.plan; import java.util.ArrayList; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * LateralViewJoinDesc. * */ -@Explain(displayName = "Lateral View Join Operator") +@Explain(displayName = "Lateral View Join Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class LateralViewJoinDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; @@ -44,7 +46,7 @@ public void setOutputInternalColNames(ArrayList outputInternalColNames) this.outputInternalColNames = outputInternalColNames; } - @Explain(displayName = "outputColumnNames") + @Explain(displayName = "outputColumnNames", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ArrayList getOutputInternalColNames() { return outputInternalColNames; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LimitDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LimitDesc.java index be6d194..f88bf63 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LimitDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LimitDesc.java @@ -17,13 +17,14 @@ */ package org.apache.hadoop.hive.ql.plan; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * LimitDesc. * */ -@Explain(displayName = "Limit") +@Explain(displayName = "Limit", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class LimitDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; private int limit; @@ -36,7 +37,7 @@ public LimitDesc(final int limit) { this.limit = limit; } - @Explain(displayName = "Number of rows") + @Explain(displayName = "Number of rows", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public int getLimit() { return limit; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadDesc.java index 68e2afc..4d61c1e 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadDesc.java @@ -21,6 +21,7 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * LoadDesc. @@ -37,7 +38,7 @@ public LoadDesc(final Path sourcePath) { this.sourcePath = sourcePath; } - @Explain(displayName = "source", normalExplain = false) + @Explain(displayName = "source", explainLevels = { Level.EXTENDED }) public Path getSourcePath() { return sourcePath; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadTableDesc.java index f514857..3e74d95 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LoadTableDesc.java @@ -24,6 +24,7 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.ql.io.AcidUtils; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * LoadTableDesc. @@ -125,7 +126,7 @@ public boolean getHoldDDLTime() { return holdDDLTime; } - @Explain(displayName = "table") + @Explain(displayName = "table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public TableDesc getTable() { return table; } @@ -134,7 +135,7 @@ public void setTable(final org.apache.hadoop.hive.ql.plan.TableDesc table) { this.table = table; } - @Explain(displayName = "partition") + @Explain(displayName = "partition", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getPartitionSpec() { return partitionSpec; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LockDatabaseDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LockDatabaseDesc.java index cb66d54..2e29a5d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LockDatabaseDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LockDatabaseDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * LockDatabaseDesc. * */ -@Explain(displayName = "Lock Database") +@Explain(displayName = "Lock Database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class LockDatabaseDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -42,7 +44,7 @@ public LockDatabaseDesc(String databaseName, String mode, String queryId) { this.queryId = queryId; } - @Explain(displayName = "database") + @Explain(displayName = "database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDatabaseName() { return databaseName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/LockTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/LockTableDesc.java index c3c4ba4..2ef0b8f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/LockTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/LockTableDesc.java @@ -22,12 +22,14 @@ import java.util.Map; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * LockTableDesc. * */ -@Explain(displayName = "Lock Table") +@Explain(displayName = "Lock Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class LockTableDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapJoinDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapJoinDesc.java index 4ccbef7..664d6e5 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapJoinDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapJoinDesc.java @@ -27,12 +27,13 @@ import java.util.Map; import java.util.Map.Entry; import java.util.Set; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * Map Join operator Descriptor implementation. * */ -@Explain(displayName = "Map Join Operator") +@Explain(displayName = "Map Join Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class MapJoinDesc extends JoinDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -121,7 +122,7 @@ private void initRetainExprList() { } } - @Explain(displayName = "input vertices") + @Explain(displayName = "input vertices", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getParentToInput() { return parentToInput; } @@ -138,7 +139,7 @@ public void setParentToInput(Map parentToInput) { return parentDataSizes; } - @Explain(displayName = "Estimated key counts", normalExplain = false) + @Explain(displayName = "Estimated key counts", explainLevels = { Level.EXTENDED }) public String getKeyCountsExplainDesc() { StringBuilder result = null; for (Map.Entry entry : parentKeyCounts.entrySet()) { @@ -195,7 +196,7 @@ public void setDumpFilePrefix(String dumpFilePrefix) { * @return the keys in string form */ @Override - @Explain(displayName = "keys") + @Explain(displayName = "keys", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getKeysString() { Map keyMap = new LinkedHashMap(); for (Map.Entry> k: getKeys().entrySet()) { @@ -222,7 +223,7 @@ public void setKeys(Map> keys) { /** * @return the position of the big table not in memory */ - @Explain(displayName = "Position of Big Table", normalExplain = false) + @Explain(displayName = "Position of Big Table", explainLevels = { Level.EXTENDED }) public int getPosBigTable() { return posBigTable; } @@ -312,7 +313,7 @@ public void setBigTablePartSpecToFileMapping(Map> partToFil this.bigTablePartSpecToFileMapping = partToFileMapping; } - @Explain(displayName = "BucketMapJoin", normalExplain = false, displayOnlyOnTrue = true) + @Explain(displayName = "BucketMapJoin", explainLevels = { Level.EXTENDED }, displayOnlyOnTrue = true) public boolean isBucketMapJoin() { return isBucketMapJoin; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java index f6616fb..05a5841 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapWork.java @@ -40,6 +40,7 @@ import org.apache.hadoop.hive.ql.optimizer.physical.BucketingSortingCtx.BucketCol; import org.apache.hadoop.hive.ql.optimizer.physical.BucketingSortingCtx.SortCol; import org.apache.hadoop.hive.ql.parse.SplitSample; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.mapred.JobConf; import com.google.common.collect.Interner; @@ -134,7 +135,7 @@ public MapWork(String name) { super(name); } - @Explain(displayName = "Path -> Alias", normalExplain = false) + @Explain(displayName = "Path -> Alias", explainLevels = { Level.EXTENDED }) public LinkedHashMap> getPathToAliases() { return pathToAliases; } @@ -155,7 +156,7 @@ public void setPathToAliases( * * @return */ - @Explain(displayName = "Truncated Path -> Alias", normalExplain = false) + @Explain(displayName = "Truncated Path -> Alias", explainLevels = { Level.EXTENDED }) public Map> getTruncatedPathToAliases() { Map> trunPathToAliases = new LinkedHashMap>(); @@ -170,7 +171,7 @@ public void setPathToAliases( return trunPathToAliases; } - @Explain(displayName = "Path -> Partition", normalExplain = false) + @Explain(displayName = "Path -> Partition", explainLevels = { Level.EXTENDED }) public LinkedHashMap getPathToPartitionInfo() { return pathToPartitionInfo; } @@ -240,7 +241,7 @@ public void setAliasToWork( this.aliasToWork = aliasToWork; } - @Explain(displayName = "Split Sample", normalExplain = false) + @Explain(displayName = "Split Sample", explainLevels = { Level.EXTENDED }) public HashMap getNameToSplitSample() { return nameToSplitSample; } @@ -329,7 +330,7 @@ public void replaceRoots(Map, Operator> replacementMap) { } @Override - @Explain(displayName = "Map Operator Tree") + @Explain(displayName = "Map Operator Tree", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Set> getAllRootOperators() { Set> opSet = new LinkedHashSet>(); @@ -467,12 +468,12 @@ public void mergingInto(MapWork mapWork) { mapWork.useBucketizedHiveInputFormat |= useBucketizedHiveInputFormat; } - @Explain(displayName = "Path -> Bucketed Columns", normalExplain = false) + @Explain(displayName = "Path -> Bucketed Columns", explainLevels = { Level.EXTENDED }) public Map> getBucketedColsByDirectory() { return bucketedColsByDirectory; } - @Explain(displayName = "Path -> Sorted Columns", normalExplain = false) + @Explain(displayName = "Path -> Sorted Columns", explainLevels = { Level.EXTENDED }) public Map> getSortedColsByDirectory() { return sortedColsByDirectory; } @@ -493,7 +494,7 @@ public void setSamplingType(int samplingType) { this.samplingType = samplingType; } - @Explain(displayName = "Sampling", normalExplain = false) + @Explain(displayName = "Sampling", explainLevels = { Level.EXTENDED }) public String getSamplingTypeString() { return samplingType == 1 ? "SAMPLING_ON_PREV_MR" : samplingType == 2 ? "SAMPLING_ON_START" : null; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredLocalWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredLocalWork.java index 316d306..82143a6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredLocalWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredLocalWork.java @@ -31,12 +31,14 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.ql.exec.MapJoinOperator; import org.apache.hadoop.hive.ql.exec.Operator; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * MapredLocalWork. * */ -@Explain(displayName = "Map Reduce Local Work") +@Explain(displayName = "Map Reduce Local Work", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class MapredLocalWork implements Serializable { private static final long serialVersionUID = 1L; @@ -83,7 +85,7 @@ public void setDummyParentOp(List> op){ } - @Explain(displayName = "Alias -> Map Local Operator Tree") + @Explain(displayName = "Alias -> Map Local Operator Tree", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public LinkedHashMap> getAliasToWork() { return aliasToWork; } @@ -104,7 +106,7 @@ public void setAliasToWork( /** * @return the aliasToFetchWork */ - @Explain(displayName = "Alias -> Map Local Tables") + @Explain(displayName = "Alias -> Map Local Tables", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public LinkedHashMap getAliasToFetchWork() { return aliasToFetchWork; } @@ -138,7 +140,7 @@ public void deriveExplainAttributes() { } } - @Explain(displayName = "Bucket Mapjoin Context", normalExplain = false) + @Explain(displayName = "Bucket Mapjoin Context", explainLevels = { Level.EXTENDED }) public BucketMapJoinContext getBucketMapjoinContextExplain() { return bucketMapjoinContext != null && bucketMapjoinContext.getBucketFileNameMapping() != null ? bucketMapjoinContext : null; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredWork.java index f3203bf..da1010b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MapredWork.java @@ -23,13 +23,15 @@ import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * MapredWork. * */ -@Explain(displayName = "Map Reduce") +@Explain(displayName = "Map Reduce", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class MapredWork extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; @@ -38,7 +40,7 @@ private boolean finalMapRed; - @Explain(skipHeader = true, displayName = "Map") + @Explain(skipHeader = true, displayName = "Map", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public MapWork getMapWork() { return mapWork; } @@ -47,7 +49,7 @@ public void setMapWork(MapWork mapWork) { this.mapWork = mapWork; } - @Explain(skipHeader = true, displayName = "Reduce") + @Explain(skipHeader = true, displayName = "Reduce", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public ReduceWork getReduceWork() { return reduceWork; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MergeJoinWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MergeJoinWork.java index b2369fa..43bab79 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MergeJoinWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MergeJoinWork.java @@ -26,6 +26,7 @@ import org.apache.hadoop.hive.ql.exec.CommonMergeJoinOperator; import org.apache.hadoop.hive.ql.exec.HashTableDummyOperator; import org.apache.hadoop.hive.ql.exec.Operator; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.mapred.JobConf; public class MergeJoinWork extends BaseWork { @@ -79,7 +80,7 @@ public void addMergedWork(BaseWork work, BaseWork connectWork) { } } - @Explain(skipHeader = true, displayName = "Join") + @Explain(skipHeader=true, displayName = "Join", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getBaseWorkList() { return mergeWorkList; } @@ -88,7 +89,7 @@ public String getBigTableAlias() { return ((MapWork) bigTableWork).getAliasToWork().keySet().iterator().next(); } - @Explain(skipHeader = true, displayName = "Main") + @Explain(skipHeader=true, displayName = "Main", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public BaseWork getMainWork() { return bigTableWork; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MoveWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MoveWork.java index e43156f..9f498c7 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MoveWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MoveWork.java @@ -25,12 +25,14 @@ import org.apache.hadoop.hive.metastore.api.Partition; import org.apache.hadoop.hive.ql.hooks.ReadEntity; import org.apache.hadoop.hive.ql.hooks.WriteEntity; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * MoveWork. * */ -@Explain(displayName = "Move Operator") +@Explain(displayName = "Move Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class MoveWork implements Serializable { private static final long serialVersionUID = 1L; private LoadTableDesc loadTableWork; @@ -81,7 +83,7 @@ public MoveWork(HashSet inputs, HashSet outputs, this.checkFileFormat = checkFileFormat; } - @Explain(displayName = "tables") + @Explain(displayName = "tables", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public LoadTableDesc getLoadTableWork() { return loadTableWork; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/MuxDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/MuxDesc.java index 1c75e5e..71dc44c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/MuxDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/MuxDesc.java @@ -24,13 +24,15 @@ import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.hive.ql.exec.ReduceSinkOperator; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Mux operator descriptor implementation.. * */ -@Explain(displayName = "Mux Operator") +@Explain(displayName = "Mux Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class MuxDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/OrcFileMergeDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/OrcFileMergeDesc.java index 7d0ab0c..2116c79 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/OrcFileMergeDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/OrcFileMergeDesc.java @@ -18,11 +18,13 @@ package org.apache.hadoop.hive.ql.plan; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ORC fast file merge operator descriptor. */ -@Explain(displayName = "ORC File Merge Operator") +@Explain(displayName = "ORC File Merge Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class OrcFileMergeDesc extends FileMergeDesc { public OrcFileMergeDesc() { diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/PTFDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/PTFDesc.java index 5e63f2f..4461a1b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/PTFDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/PTFDesc.java @@ -32,8 +32,10 @@ import java.util.ArrayList; import java.util.Collections; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "PTF Operator") + +@Explain(displayName = "PTF Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class PTFDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; @SuppressWarnings("unused") @@ -65,7 +67,7 @@ public PartitionedTableFunctionDef getStartOfChain() { return funcDef == null ? null : funcDef.getStartOfChain(); } - @Explain(displayName = "Function definitions") + @Explain(displayName = "Function definitions", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getFuncDefExplain() { if (funcDef == null) { return null; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java index 503117d..2dbfadf 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java @@ -42,12 +42,14 @@ import org.apache.hadoop.mapred.OutputFormat; import org.apache.hadoop.util.ReflectionUtils; import org.apache.hive.common.util.HiveStringUtils; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * PartitionDesc. * */ -@Explain(displayName = "Partition") +@Explain(displayName = "Partition", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class PartitionDesc implements Serializable, Cloneable { static { @@ -94,7 +96,7 @@ public PartitionDesc(final Partition part,final TableDesc tblDesc) throws HiveEx setOutputFileFormatClass(part.getOutputFormatClass()); } - @Explain(displayName = "") + @Explain(displayName = "", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public TableDesc getTableDesc() { return tableDesc; } @@ -103,7 +105,7 @@ public void setTableDesc(TableDesc tableDesc) { this.tableDesc = tableDesc; } - @Explain(displayName = "partition values") + @Explain(displayName = "partition values", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public LinkedHashMap getPartSpec() { return partSpec; } @@ -176,7 +178,7 @@ public Properties getProperties() { return properties; } - @Explain(displayName = "properties", normalExplain = false) + @Explain(displayName = "properties", explainLevels = { Level.EXTENDED }) public Map getPropertiesExplain() { return HiveStringUtils.getPropertiesExplain(getProperties()); } @@ -196,27 +198,27 @@ public void setProperties(final Properties properties) { /** * @return the serdeClassName */ - @Explain(displayName = "serde") + @Explain(displayName = "serde", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getSerdeClassName() { return getProperties().getProperty(serdeConstants.SERIALIZATION_LIB); } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return getProperties().getProperty(hive_metastoreConstants.META_TABLE_NAME); } - @Explain(displayName = "input format") + @Explain(displayName = "input format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getInputFileFormatClassName() { return getInputFileFormatClass().getName(); } - @Explain(displayName = "output format") + @Explain(displayName = "output format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOutputFileFormatClassName() { return getOutputFileFormatClass().getName(); } - @Explain(displayName = "base file name", normalExplain = false) + @Explain(displayName = "base file name", explainLevels = { Level.EXTENDED }) public String getBaseFileName() { return baseFileName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/PrincipalDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/PrincipalDesc.java index 818a8e3..120c7e7 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/PrincipalDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/PrincipalDesc.java @@ -21,8 +21,10 @@ import java.io.Serializable; import org.apache.hadoop.hive.metastore.api.PrincipalType; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Principal") + +@Explain(displayName = "Principal", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class PrincipalDesc implements Serializable, Cloneable { private static final long serialVersionUID = 1L; @@ -41,7 +43,7 @@ public PrincipalDesc() { super(); } - @Explain(displayName="name") + @Explain(displayName="name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getName() { return name; } @@ -50,7 +52,7 @@ public void setName(String name) { this.name = name; } - @Explain(displayName="type", normalExplain = false) + @Explain(displayName="type", explainLevels = { Level.EXTENDED }) public PrincipalType getType() { return type; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeDesc.java index 03b3b6b..a85303f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeDesc.java @@ -22,8 +22,10 @@ import java.util.List; import org.apache.hadoop.hive.ql.security.authorization.Privilege; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Privilege") + +@Explain(displayName = "Privilege", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class PrivilegeDesc implements Serializable, Cloneable { private static final long serialVersionUID = 1L; @@ -44,7 +46,7 @@ public PrivilegeDesc() { /** * @return privilege definition */ - @Explain(displayName = "privilege") + @Explain(displayName = "privilege", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Privilege getPrivilege() { return privilege; } @@ -59,7 +61,7 @@ public void setPrivilege(Privilege privilege) { /** * @return columns on which the given privilege take affect. */ - @Explain(displayName = "columns") + @Explain(displayName = "columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getColumns() { return columns; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeObjectDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeObjectDesc.java index 5265289..564f464 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeObjectDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/PrivilegeObjectDesc.java @@ -20,8 +20,10 @@ import java.util.HashMap; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName="privilege subject") + +@Explain(displayName="privilege subject", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class PrivilegeObjectDesc { //default type is table @@ -53,7 +55,7 @@ public void setTable(boolean isTable) { this.table = isTable; } - @Explain(displayName="object") + @Explain(displayName="object", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getObject() { return object; } @@ -62,7 +64,7 @@ public void setObject(String object) { this.object = object; } - @Explain(displayName="partition spec") + @Explain(displayName="partition spec", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public HashMap getPartSpec() { return partSpec; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/RCFileMergeDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/RCFileMergeDesc.java index 476aa46..1a94bdb 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/RCFileMergeDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/RCFileMergeDesc.java @@ -18,11 +18,13 @@ package org.apache.hadoop.hive.ql.plan; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Descriptor for Fast file merge RC file operator. */ -@Explain(displayName = "RCFile Merge Operator") +@Explain(displayName = "RCFile Merge Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class RCFileMergeDesc extends FileMergeDesc { public RCFileMergeDesc() { diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceSinkDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceSinkDesc.java index 28cb3ba..0eb4ab6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceSinkDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceSinkDesc.java @@ -21,17 +21,20 @@ import java.util.ArrayList; import java.util.EnumSet; import java.util.List; +import java.util.Map.Entry; import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.hadoop.hive.ql.io.AcidUtils; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ReduceSinkDesc. * */ -@Explain(displayName = "Reduce Output Operator") +@Explain(displayName = "Reduce Output Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ReduceSinkDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; /** @@ -190,7 +193,7 @@ public void setOutputValueColumnNames( this.outputValueColumnNames = outputValueColumnNames; } - @Explain(displayName = "key expressions") + @Explain(displayName = "key expressions", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getKeyColString() { return PlanUtils.getExprListString(keyCols); } @@ -211,7 +214,7 @@ public void setNumDistributionKeys(int numKeys) { this.numDistributionKeys = numKeys; } - @Explain(displayName = "value expressions") + @Explain(displayName = "value expressions", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getValueColsString() { return PlanUtils.getExprListString(valueCols); } @@ -224,7 +227,7 @@ public void setValueCols(final java.util.ArrayList valueCols) { this.valueCols = valueCols; } - @Explain(displayName = "Map-reduce partition columns") + @Explain(displayName = "Map-reduce partition columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getParitionColsString() { return PlanUtils.getExprListString(partitionCols); } @@ -245,7 +248,7 @@ public boolean isPartitioning() { return false; } - @Explain(displayName = "tag", normalExplain = false) + @Explain(displayName = "tag", explainLevels = { Level.EXTENDED }) public int getTag() { return tag; } @@ -262,7 +265,7 @@ public void setTopN(int topN) { this.topN = topN; } - @Explain(displayName = "TopN", normalExplain = false) + @Explain(displayName = "TopN", explainLevels = { Level.EXTENDED }) public Integer getTopNExplain() { return topN > 0 ? topN : null; } @@ -333,7 +336,7 @@ public void setValueSerializeInfo(TableDesc valueSerializeInfo) { * of the same length as key columns, that consists of only "+" * (ascending order) and "-" (descending order). */ - @Explain(displayName = "sort order") + @Explain(displayName = "sort order", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOrder() { return keySerializeInfo.getProperties().getProperty( org.apache.hadoop.hive.serde.serdeConstants.SERIALIZATION_SORT_ORDER); @@ -361,6 +364,7 @@ public void setDistinctColumnIndices( this.distinctColumnIndices = distinctColumnIndices; } + @Explain(displayName = "outputname", explainLevels = { Level.USER }) public String getOutputName() { return outputName; } @@ -393,7 +397,7 @@ public boolean getSkipTag() { return skipTag; } - @Explain(displayName = "auto parallelism", normalExplain = false) + @Explain(displayName = "auto parallelism", explainLevels = { Level.EXTENDED }) public final boolean isAutoParallel() { return (this.reduceTraits.contains(ReducerTraits.AUTOPARALLEL)); } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceWork.java index c78184b..333df90 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ReduceWork.java @@ -24,6 +24,7 @@ import java.util.LinkedHashSet; import java.util.List; import java.util.Map; +import java.util.Map.Entry; import java.util.Set; import org.apache.commons.logging.Log; @@ -32,6 +33,7 @@ import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.hive.ql.exec.OperatorUtils; import org.apache.hadoop.hive.ql.exec.Utilities; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.hive.serde2.Deserializer; import org.apache.hadoop.hive.serde2.SerDeUtils; import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector; @@ -153,7 +155,7 @@ public String getVectorModeOn() { return vectorMode ? "vectorized" : null; } - @Explain(displayName = "Reduce Operator Tree") + @Explain(displayName = "Reduce Operator Tree", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Operator getReducer() { return reducer; } @@ -162,7 +164,7 @@ public void setReducer(final Operator reducer) { this.reducer = reducer; } - @Explain(displayName = "Needs Tagging", normalExplain = false) + @Explain(displayName = "Needs Tagging", explainLevels = { Level.EXTENDED }) public boolean getNeedsTagging() { return needsTagging; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/RevokeDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/RevokeDesc.java index c0b74ff..398794a 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/RevokeDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/RevokeDesc.java @@ -20,8 +20,10 @@ import java.io.Serializable; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName="Revoke") + +@Explain(displayName="Revoke", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class RevokeDesc extends DDLDesc implements Serializable, Cloneable { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/RoleDDLDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/RoleDDLDesc.java index 2aae751..a7e6391 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/RoleDDLDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/RoleDDLDesc.java @@ -21,8 +21,10 @@ import java.io.Serializable; import org.apache.hadoop.hive.metastore.api.PrincipalType; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Create Role") + +@Explain(displayName = "Create Role", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class RoleDDLDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -108,12 +110,12 @@ public RoleDDLDesc(String principalName, PrincipalType principalType, this.roleOwnerName = roleOwnerName; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getName() { return name; } - @Explain(displayName = "role operation") + @Explain(displayName = "role operation", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public RoleOperation getOperation() { return operation; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/SMBJoinDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/SMBJoinDesc.java index a09fc69..4762408 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/SMBJoinDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/SMBJoinDesc.java @@ -23,8 +23,10 @@ import java.util.Map; import org.apache.hadoop.hive.ql.exec.DummyStoreOperator; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName = "Sorted Merge Bucket Map Join Operator") + +@Explain(displayName = "Sorted Merge Bucket Map Join Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class SMBJoinDesc extends MapJoinDesc implements Serializable { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ScriptDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ScriptDesc.java index 4f7c0da..5317894 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ScriptDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ScriptDesc.java @@ -20,12 +20,14 @@ import org.apache.hadoop.hive.ql.exec.RecordReader; import org.apache.hadoop.hive.ql.exec.RecordWriter; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ScriptDesc. * */ -@Explain(displayName = "Transform Operator") +@Explain(displayName = "Transform Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ScriptDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; private String scriptCmd; @@ -59,7 +61,7 @@ public ScriptDesc(final String scriptCmd, final TableDesc scriptInputInfo, this.scriptErrInfo = scriptErrInfo; } - @Explain(displayName = "command") + @Explain(displayName = "command", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getScriptCmd() { return scriptCmd; } @@ -68,7 +70,7 @@ public void setScriptCmd(final String scriptCmd) { this.scriptCmd = scriptCmd; } - @Explain(displayName = "output info") + @Explain(displayName = "output info", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public TableDesc getScriptOutputInfo() { return scriptOutputInfo; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/SelectDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/SelectDesc.java index cfcfe17..e7bbab4 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/SelectDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/SelectDesc.java @@ -20,13 +20,14 @@ import java.util.ArrayList; import java.util.List; +import org.apache.hadoop.hive.ql.plan.Explain.Level; /** * SelectDesc. * */ -@Explain(displayName = "Select Operator") +@Explain(displayName = "Select Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class SelectDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; private List colList; @@ -81,7 +82,7 @@ public void setColList( this.colList = colList; } - @Explain(displayName = "outputColumnNames") + @Explain(displayName = "outputColumnNames", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getOutputColumnNames() { return outputColumnNames; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowColumnsDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowColumnsDesc.java index 28d16a3..0950f75 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowColumnsDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowColumnsDesc.java @@ -20,6 +20,7 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; public class ShowColumnsDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -64,7 +65,7 @@ public ShowColumnsDesc(Path resFile, String tableName) { /** * @return the tableName */ - @Explain(displayName = "table name") + @Explain(displayName = "table name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } @@ -80,7 +81,7 @@ public void setTableName(String tableName) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowConfDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowConfDesc.java index df385a2..7d6a481 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowConfDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowConfDesc.java @@ -18,6 +18,7 @@ package org.apache.hadoop.hive.ql.plan; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import java.io.Serializable; @@ -41,7 +42,7 @@ public ShowConfDesc(Path resFile, String confName) { this.confName = confName; } - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public Path getResFile() { return resFile; } @@ -50,7 +51,7 @@ public void setResFile(Path resFile) { this.resFile = resFile; } - @Explain(displayName = "conf name", normalExplain = false) + @Explain(displayName = "conf name", explainLevels = { Level.EXTENDED }) public String getConfName() { return confName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateTableDesc.java index 71520e8..5a1e77c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowCreateTableDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowCreateTableDesc. * */ -@Explain(displayName = "Show Create Table") +@Explain(displayName = "Show Create Table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowCreateTableDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String resFile; @@ -66,7 +68,7 @@ public ShowCreateTableDesc(String tableName, String resFile) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } @@ -82,7 +84,7 @@ public void setResFile(String resFile) { /** * @return the tableName */ - @Explain(displayName = "table name") + @Explain(displayName = "table name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowDatabasesDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowDatabasesDesc.java index 0ad0658..8ea509a 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowDatabasesDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowDatabasesDesc.java @@ -21,12 +21,14 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowDatabasesDesc. * */ -@Explain(displayName = "Show Databases") +@Explain(displayName = "Show Databases", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowDatabasesDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String pattern; @@ -89,7 +91,7 @@ public void setPattern(String pattern) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java index 5d4a821..48522c5 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowFunctionsDesc.java @@ -21,12 +21,14 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowFunctionsDesc. * */ -@Explain(displayName = "Show Functions") +@Explain(displayName = "Show Functions", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowFunctionsDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String pattern; @@ -103,7 +105,7 @@ public void setPattern(String pattern) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowGrantDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowGrantDesc.java index d27da3d..f061107 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowGrantDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowGrantDesc.java @@ -16,8 +16,10 @@ * limitations under the License. */ package org.apache.hadoop.hive.ql.plan; +import org.apache.hadoop.hive.ql.plan.Explain.Level; -@Explain(displayName="show grant desc") + +@Explain(displayName="show grant desc", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowGrantDesc { private PrincipalDesc principalDesc; @@ -48,7 +50,7 @@ public static String getSchema() { return tabularSchema; } - @Explain(displayName="principal desc") + @Explain(displayName="principal desc", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public PrincipalDesc getPrincipalDesc() { return principalDesc; } @@ -57,7 +59,7 @@ public void setPrincipalDesc(PrincipalDesc principalDesc) { this.principalDesc = principalDesc; } - @Explain(displayName="object") + @Explain(displayName="object", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public PrivilegeObjectDesc getHiveObj() { return hiveObj; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowIndexesDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowIndexesDesc.java index 10df6c8..5bbdc31 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowIndexesDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowIndexesDesc.java @@ -21,12 +21,14 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowIndexesDesc. * Returns table index information per SQL syntax. */ -@Explain(displayName = "Show Indexes") +@Explain(displayName = "Show Indexes", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowIndexesDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String tableName; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowLocksDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowLocksDesc.java index 1902d36..9e93254 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowLocksDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowLocksDesc.java @@ -23,12 +23,14 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowLocksDesc. * */ -@Explain(displayName = "Show Locks") +@Explain(displayName = "Show Locks", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowLocksDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String resFile; @@ -105,7 +107,7 @@ public void setDbName(String dbName) { /** * @return the tableName */ - @Explain(displayName = "table") + @Explain(displayName = "table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } @@ -121,7 +123,7 @@ public void setTableName(String tableName) { /** * @return the partSpec */ - @Explain(displayName = "partition") + @Explain(displayName = "partition", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public HashMap getPartSpec() { return partSpec; } @@ -137,7 +139,7 @@ public void setPartSpecs(HashMap partSpec) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowPartitionsDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowPartitionsDesc.java index 4059b92..adf56ff 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowPartitionsDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowPartitionsDesc.java @@ -22,12 +22,14 @@ import java.util.Map; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowPartitionsDesc. * */ -@Explain(displayName = "Show Partitions") +@Explain(displayName = "Show Partitions", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowPartitionsDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String tabName; @@ -71,7 +73,7 @@ public ShowPartitionsDesc(String tabName, Path resFile, /** * @return the name of the table. */ - @Explain(displayName = "table") + @Explain(displayName = "table", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTabName() { return tabName; } @@ -87,7 +89,7 @@ public void setTabName(String tabName) { /** * @return the name of the table. */ - @Explain(displayName = "partSpec") + @Explain(displayName = "partSpec", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getPartSpec() { return partSpec; } @@ -102,7 +104,7 @@ public void setPartSpec(Map partSpec) { /** * @return the results file */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTableStatusDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTableStatusDesc.java index 15613ed..0a0e540 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTableStatusDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTableStatusDesc.java @@ -22,12 +22,14 @@ import java.util.HashMap; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowTableStatusDesc. * */ -@Explain(displayName = "Show Table Status") +@Explain(displayName = "Show Table Status", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowTableStatusDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String pattern; @@ -108,7 +110,7 @@ public String getResFile() { return resFile; } - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFileString() { return getResFile(); } @@ -124,7 +126,7 @@ public void setResFile(String resFile) { /** * @return the database name */ - @Explain(displayName = "database") + @Explain(displayName = "database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDbName() { return dbName; } @@ -140,7 +142,7 @@ public void setDbName(String dbName) { /** * @return the partSpec */ - @Explain(displayName = "partition") + @Explain(displayName = "partition", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public HashMap getPartSpec() { return partSpec; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTablesDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTablesDesc.java index 850e964..9e9d639 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTablesDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTablesDesc.java @@ -21,12 +21,14 @@ import java.io.Serializable; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowTablesDesc. * */ -@Explain(displayName = "Show Tables") +@Explain(displayName = "Show Tables", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowTablesDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String pattern; @@ -98,7 +100,7 @@ public void setPattern(String pattern) { /** * @return the resFile */ - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFile() { return resFile; } @@ -114,7 +116,7 @@ public void setResFile(String resFile) { /** * @return the dbName */ - @Explain(displayName = "database name") + @Explain(displayName = "database name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDbName() { return dbName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTblPropertiesDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTblPropertiesDesc.java index 13de46e..5f41c23 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTblPropertiesDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/ShowTblPropertiesDesc.java @@ -22,12 +22,14 @@ import java.util.HashMap; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ShowTblPropertiesDesc. * */ -@Explain(displayName = "Show Table Properties") +@Explain(displayName = "Show Table Properties", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class ShowTblPropertiesDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; String resFile; @@ -77,7 +79,7 @@ public String getResFile() { return resFile; } - @Explain(displayName = "result file", normalExplain = false) + @Explain(displayName = "result file", explainLevels = { Level.EXTENDED }) public String getResFileString() { return getResFile(); } @@ -93,7 +95,7 @@ public void setResFile(String resFile) { /** * @return the tableName */ - @Explain(displayName = "table name") + @Explain(displayName = "table name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/Statistics.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/Statistics.java index b0caf23..f66279f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/Statistics.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/Statistics.java @@ -22,6 +22,7 @@ import java.util.List; import java.util.Map; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.hive.ql.stats.StatsUtils; import com.google.common.collect.Lists; @@ -101,7 +102,7 @@ public void setColumnStatsState(State columnStatsState) { } @Override - @Explain(displayName = "Statistics") + @Explain(displayName = "Statistics", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String toString() { StringBuilder sb = new StringBuilder(); sb.append("Num rows: "); diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java index 7e3f0bf..77c04f6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsNoJobWork.java @@ -22,12 +22,14 @@ import org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.TableSpec; import org.apache.hadoop.hive.ql.parse.PrunedPartitionList; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Client-side stats aggregator task. */ -@Explain(displayName = "Stats-Aggr Operator") +@Explain(displayName = "Stats-Aggr Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class StatsNoJobWork implements Serializable { private static final long serialVersionUID = 1L; diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsWork.java index 3cf0f7f..c8515db 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/StatsWork.java @@ -22,12 +22,14 @@ import org.apache.hadoop.hive.ql.exec.Task; import org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.TableSpec; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * ConditionalStats. * */ -@Explain(displayName = "Stats-Aggr Operator") +@Explain(displayName = "Stats-Aggr Operator", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class StatsWork implements Serializable { private static final long serialVersionUID = 1L; @@ -90,7 +92,7 @@ public void setAggKey(String aggK) { aggKey = aggK; } - @Explain(displayName = "Stats Aggregation Key Prefix", normalExplain = false) + @Explain(displayName = "Stats Aggregation Key Prefix", explainLevels = { Level.EXTENDED }) public String getAggKey() { return aggKey; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/SwitchDatabaseDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/SwitchDatabaseDesc.java index 0cad7c1..3991009 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/SwitchDatabaseDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/SwitchDatabaseDesc.java @@ -19,12 +19,14 @@ package org.apache.hadoop.hive.ql.plan; import java.io.Serializable; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * SwitchDatabaseDesc. * */ -@Explain(displayName = "Switch Database") +@Explain(displayName = "Switch Database", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class SwitchDatabaseDesc extends DDLDesc implements Serializable { private static final long serialVersionUID = 1L; @@ -39,7 +41,7 @@ public SwitchDatabaseDesc(String databaseName) { this.databaseName = databaseName; } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getDatabaseName() { return databaseName; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/TableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/TableDesc.java index 0e34aee..0614a17 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/TableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/TableDesc.java @@ -28,6 +28,7 @@ import org.apache.hadoop.hive.metastore.api.hive_metastoreConstants; import org.apache.hadoop.hive.ql.exec.Utilities; import org.apache.hadoop.hive.ql.io.HiveFileFormatUtils; +import org.apache.hadoop.hive.ql.plan.Explain.Level; import org.apache.hadoop.hive.serde.serdeConstants; import org.apache.hadoop.hive.serde2.Deserializer; import org.apache.hadoop.hive.serde2.SerDeUtils; @@ -117,7 +118,7 @@ public Properties getProperties() { return properties; } - @Explain(displayName = "properties", normalExplain = false) + @Explain(displayName = "properties", explainLevels = { Level.EXTENDED }) public Map getPropertiesExplain() { return HiveStringUtils.getPropertiesExplain(getProperties()); } @@ -130,7 +131,7 @@ public void setJobProperties(Map jobProperties) { this.jobProperties = jobProperties; } - @Explain(displayName = "jobProperties", normalExplain = false) + @Explain(displayName = "jobProperties", explainLevels = { Level.EXTENDED }) public Map getJobProperties() { return jobProperties; } @@ -138,23 +139,23 @@ public void setJobProperties(Map jobProperties) { /** * @return the serdeClassName */ - @Explain(displayName = "serde") + @Explain(displayName = "serde", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getSerdeClassName() { return properties.getProperty(serdeConstants.SERIALIZATION_LIB); } - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return properties .getProperty(hive_metastoreConstants.META_TABLE_NAME); } - @Explain(displayName = "input format") + @Explain(displayName = "input format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getInputFileFormatClassName() { return getInputFileFormatClass().getName(); } - @Explain(displayName = "output format") + @Explain(displayName = "output format", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOutputFileFormatClassName() { return getOutputFileFormatClass().getName(); } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java index 6530c37..aa291b9 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java @@ -27,13 +27,15 @@ import org.apache.hadoop.hive.ql.metadata.Table; import org.apache.hadoop.hive.ql.metadata.VirtualColumn; import org.apache.hadoop.hive.ql.parse.TableSample; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Table Scan Descriptor Currently, data is only read from a base source as part * of map-reduce framework. So, nothing is stored in the descriptor. But, more * things will be added here as table scan is invoked as part of local work. **/ -@Explain(displayName = "TableScan") +@Explain(displayName = "TableScan", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class TableScanDesc extends AbstractOperatorDesc { private static final long serialVersionUID = 1L; @@ -125,7 +127,7 @@ public Object clone() { return new TableScanDesc(getAlias(), vcs, this.tableMetadata); } - @Explain(displayName = "alias") + @Explain(displayName = "alias", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getAlias() { return alias; } @@ -193,7 +195,7 @@ public void setGatherStats(boolean gatherStats) { this.gatherStats = gatherStats; } - @Explain(displayName = "GatherStats", normalExplain = false) + @Explain(displayName = "GatherStats", explainLevels = { Level.EXTENDED }) public boolean isGatherStats() { return gatherStats; } @@ -218,7 +220,7 @@ public void setStatsAggPrefix(String k) { statsAggKeyPrefix = k; } - @Explain(displayName = "Statistics Aggregation Key Prefix", normalExplain = false) + @Explain(displayName = "Statistics Aggregation Key Prefix", explainLevels = { Level.EXTENDED }) public String getStatsAggPrefix() { return statsAggKeyPrefix; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java index a03e373..7b91002 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/TezWork.java @@ -36,6 +36,8 @@ import org.apache.commons.logging.LogFactory; import org.apache.hadoop.hive.ql.plan.TezEdgeProperty.EdgeType; import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * TezWork. This class encapsulates all the work objects that can be executed @@ -44,7 +46,7 @@ * */ @SuppressWarnings("serial") -@Explain(displayName = "Tez") +@Explain(displayName = "Tez", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class TezWork extends AbstractOperatorDesc { public enum VertexType { @@ -87,7 +89,7 @@ public String getName() { /** * getWorkMap returns a map of "vertex name" to BaseWork */ - @Explain(displayName = "Vertices") + @Explain(displayName = "Vertices", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getWorkMap() { Map result = new LinkedHashMap(); for (BaseWork w: getAllWork()) { @@ -286,7 +288,7 @@ public int compareTo(Dependency o) { } } - @Explain(displayName = "Edges") + @Explain(displayName = "Edges", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map> getDependencyMap() { Map> result = new LinkedHashMap>(); for (Map.Entry> entry: invertedWorkGraph.entrySet()) { diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/TruncateTableDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/TruncateTableDesc.java index 24f453f..90c123d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/TruncateTableDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/TruncateTableDesc.java @@ -22,11 +22,13 @@ import java.util.Map; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * Truncates managed table or partition */ -@Explain(displayName = "Truncate Table or Partition") +@Explain(displayName = "Truncate Table or Partition", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public class TruncateTableDesc extends DDLDesc { private static final long serialVersionUID = 1L; @@ -46,7 +48,7 @@ public TruncateTableDesc(String tableName, Map partSpec) { this.partSpec = partSpec; } - @Explain(displayName = "TableName") + @Explain(displayName = "TableName", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getTableName() { return tableName; } @@ -55,7 +57,7 @@ public void setTableName(String tableName) { this.tableName = tableName; } - @Explain(displayName = "Partition Spec") + @Explain(displayName = "Partition Spec", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public Map getPartSpec() { return partSpec; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java index 741a0e0..68f289e 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/UDTFDesc.java @@ -19,6 +19,8 @@ package org.apache.hadoop.hive.ql.plan; import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF; +import org.apache.hadoop.hive.ql.plan.Explain.Level; + /** * All member variables should have a setters and getters of the form get referencedColumns; - @Explain(displayName = "name") + @Explain(displayName = "name", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getName() { return name; } @@ -83,7 +84,7 @@ public PartitionDef getPartition() { return partition; } - @Explain(displayName = "partition by") + @Explain(displayName = "partition by", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getPartitionExplain() { if (partition == null || partition.getExpressions() == null) { return null; @@ -110,7 +111,7 @@ public void setOrder(OrderDef order) { this.order = order; } - @Explain(displayName = "order by") + @Explain(displayName = "order by", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getOrderExplain() { if (order == null || order.getExpressions() == null) { return null; @@ -144,7 +145,7 @@ public void setArgs(List args) { this.args = args; } - @Explain(displayName = "arguments") + @Explain(displayName = "arguments", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public String getArgsExplain() { if (args == null) { return null; @@ -188,7 +189,7 @@ public void setResolverClassName(String resolverClassName) { this.resolverClassName = resolverClassName; } - @Explain(displayName = "referenced columns") + @Explain(displayName = "referenced columns", explainLevels = { Level.USER, Level.DEFAULT, Level.EXTENDED }) public List getReferencedColumns() { return referencedColumns; } diff --git a/ql/src/test/org/apache/hadoop/hive/ql/parse/TestUpdateDeleteSemanticAnalyzer.java b/ql/src/test/org/apache/hadoop/hive/ql/parse/TestUpdateDeleteSemanticAnalyzer.java index 7138d51..f6038d3 100644 --- a/ql/src/test/org/apache/hadoop/hive/ql/parse/TestUpdateDeleteSemanticAnalyzer.java +++ b/ql/src/test/org/apache/hadoop/hive/ql/parse/TestUpdateDeleteSemanticAnalyzer.java @@ -297,7 +297,7 @@ private String explain(SemanticAnalyzer sem, QueryPlan plan, String astStringTre fs.create(tmp); fs.deleteOnExit(tmp); ExplainWork work = new ExplainWork(tmp, sem.getParseContext(), sem.getRootTasks(), - sem.getFetchTask(), astStringTree, sem, true, false, false, false, false); + sem.getFetchTask(), astStringTree, sem, true, false, false, false, false, false, null); ExplainTask task = new ExplainTask(); task.setWork(work); task.initialize(conf, plan, null); diff --git a/ql/src/test/queries/clientpositive/explainuser_1.q b/ql/src/test/queries/clientpositive/explainuser_1.q new file mode 100644 index 0000000..bfb4d30 --- /dev/null +++ b/ql/src/test/queries/clientpositive/explainuser_1.q @@ -0,0 +1,1348 @@ +set hive.explain.user=true; + +explain create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc; +create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc; + +alter table src_orc_merge_test_part add partition (ds='2012-01-03', ts='2012-01-03+14:46:31'); +desc extended src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31'); + +explain insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src; +insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src; +explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100; +insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100; +explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 10; +insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 10; + +explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31'; +explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31'; + +alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate; + + +explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31'; +explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31'; + +drop table src_orc_merge_test_part; + +set hive.auto.convert.join=true; + +explain select sum(hash(a.k1,a.v1,a.k2, a.v2)) +from ( +select src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (select * FROM src WHERE src.key < 10) src1 + JOIN + (select * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +) a; + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key; +explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c; + + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc; + +explain select unionsrc.key FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 + UNION ALL + select 'min' as key, min(c_int) as value from cbo_t3 s2 + UNION ALL + select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc order by unionsrc.key; + +explain select unionsrc.key, count(1) FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 + UNION ALL + select 'min' as key, min(c_int) as value from cbo_t3 s2 + UNION ALL + select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc group by unionsrc.key order by unionsrc.key; + + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 join cbo_t2 on cbo_t1.key=cbo_t2.key; +explain select cbo_t1.key from cbo_t1 join cbo_t3; +explain select cbo_t1.key from cbo_t1 join cbo_t3 where cbo_t1.key=cbo_t3.key and cbo_t1.key >= 1; +explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 left outer join cbo_t2 on cbo_t1.key=cbo_t2.key; +explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 full outer join cbo_t2 on cbo_t1.key=cbo_t2.key; + +explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key; +explain select key, cbo_t1.c_int, cbo_t2.p, q from cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.key=p join (select key as a, c_int as b, cbo_t3.c_float as c from cbo_t3)cbo_t3 on cbo_t1.key=a; +explain select a, cbo_t1.b, key, cbo_t2.c_int, cbo_t3.p from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=key join (select key as p, c_int as q, cbo_t3.c_float as r from cbo_t3)cbo_t3 on cbo_t1.a=cbo_t3.p; +explain select b, cbo_t1.c, cbo_t2.c_int, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=cbo_t2.key join cbo_t3 on cbo_t1.a=cbo_t3.key; +explain select cbo_t3.c_int, b, cbo_t2.c_int, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=cbo_t2.key join cbo_t3 on cbo_t1.a=cbo_t3.key; + +explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or cbo_t2.q >= 0); + +explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0); + +explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0); + +explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0); + +explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0); + +explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0); + +explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0); + +explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0); + + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key order by x limit 1; +explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x order by x,y limit 1; +explain select key from(select key from (select key from cbo_t1 limit 5)cbo_t2 limit 5)cbo_t3 limit 5; +explain select key, c_int from(select key, c_int from (select key, c_int from cbo_t1 order by c_int limit 5)cbo_t1 order by c_int limit 5)cbo_t2 order by c_int limit 5; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a limit 5) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc limit 5) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c limit 5; + +explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc limit 5) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 limit 5) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc limit 5; + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key; +explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0); +explain select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where (b + 1 = 2) and (R.b > 0 or c >= 0); +explain select * from (select cbo_t3.c_int, cbo_t1.c, b from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 = 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t3.c_int == 2) and (b > 0 or c_int >= 0)) R where (R.c_int + 1 = 2) and (R.b > 0 or c_int >= 0); +explain select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where (c + 1 = 2) and (R.b > 0 or c_int >= 0); +explain select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a; + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select * from cbo_t1; +explain select * from cbo_t1 as cbo_t1; +explain select * from cbo_t1 as cbo_t2; + +explain select cbo_t1.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1; + +explain select * from cbo_t1 where cbo_t1.c_int >= 0; +explain select * from cbo_t1 as cbo_t1 where cbo_t1.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100; +explain select * from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100; + +explain select cbo_t2.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100; + +explain select * from (select * from cbo_t1 where cbo_t1.c_int >= 0) as cbo_t1; +explain select * from (select * from cbo_t1 as cbo_t1 where cbo_t1.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100) as cbo_t1; +explain select * from (select cbo_t2.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100) as cbo_t1; + +explain select cbo_t2.c_int+c_float as x , c_int as c_int, (((c_int+c_float)*10)+5) as y from (select * from cbo_t1 where cbo_t1.c_int >= 0) as cbo_t2 where cbo_t2.c_int >= 0; + +explain select null from cbo_t3; + +explain select key from cbo_t1 where c_int = -6 or c_int = +6; + +explain select count(cbo_t1.dt) from cbo_t1 join cbo_t2 on cbo_t1.dt = cbo_t2.dt where cbo_t1.dt = '2014' ; + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select cbo_t1.value from cbo_t1 join cbo_t2 on cbo_t1.key = cbo_t2.key where cbo_t1.dt = '10' and cbo_t1.c_boolean = true; + + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select * +from src_cbo b +where not exists + (select distinct a.key + from src_cbo a + where b.value = a.value and a.value > 'val_2' + ) +; + +explain select * +from src_cbo b +group by key, value +having not exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +; + +create view cv1 as +select * +from src_cbo b +where exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_9') +; + +explain select * from cv1; + +explain select * +from (select * + from src_cbo b + where exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_9') + ) a +; + + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select * +from src_cbo +where src_cbo.key in (select key from src_cbo s1 where s1.key > '9') +; + + +explain select * +from src_cbo b +where b.key in + (select distinct a.key + from src_cbo a + where b.value = a.value and a.key > '9' + ) +; + +explain select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) +; + +explain select key, value, count(*) +from src_cbo b +where b.key in (select key from src_cbo where src_cbo.key > '8') +group by key, value +having count(*) in (select count(*) from src_cbo s1 where s1.key > '9' group by s1.key ) +; + +explain select p_mfgr, p_name, avg(p_size) +from part +group by p_mfgr, p_name +having p_name in + (select first_value(p_name) over(partition by p_mfgr order by p_size) from part) +; + + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select * +from src_cbo +where src_cbo.key not in + ( select key from src_cbo s1 + where s1.key > '2' + ) order by key +; + +explain select p_mfgr, b.p_name, p_size +from part b +where b.p_name not in + (select p_name + from (select p_mfgr, p_name, p_size as r from part) a + where r < 10 and b.p_mfgr = a.p_mfgr + ) +; + +explain select p_name, p_size +from +part where part.p_size not in + (select avg(p_size) + from (select p_size from part) a + where p_size < 10 + ) order by p_name +; + +explain select p_mfgr, p_name, p_size +from part b where b.p_size not in + (select min(p_size) + from (select p_mfgr, p_size from part) a + where p_size < 10 and b.p_mfgr = a.p_mfgr + ) order by p_name +; + +explain select li.l_partkey, count(*) +from lineitem li +where li.l_linenumber = 1 and + li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR') +group by li.l_partkey +; + + +explain select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) + order by b.p_mfgr +; + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select count(*), count(c_int), sum(c_int), avg(c_int), max(c_int), min(c_int) from cbo_t1; +explain select count(*), count(c_int), sum(c_int), avg(c_int), max(c_int), min(c_int), case c_int when 0 then 1 when 1 then 2 else 3 end, sum(case c_int when 0 then 1 when 1 then 2 else 3 end) from cbo_t1 group by c_int; +explain select * from (select count(*) as a, count(distinct c_int) as b, sum(c_int) as c, avg(c_int) as d, max(c_int) as e, min(c_int) as f from cbo_t1) cbo_t1; +explain select f,a,e,b from (select count(*) as a, count(c_int) as b, sum(c_int) as c, avg(c_int) as d, max(c_int) as e, min(c_int) as f from cbo_t1) cbo_t1; +explain select count(c_int) as a, avg(c_float), key from cbo_t1 group by key; +explain select count(distinct c_int) as a, avg(c_float) from cbo_t1 group by c_float; + +set hive.cbo.enable=true; +set hive.exec.check.crossproducts=false; + +set hive.stats.fetch.column.stats=true; +set hive.auto.convert.join=false; + +explain select count(c_int) over() from cbo_t1; +explain select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1; +explain select * from (select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1) cbo_t1; +explain select x from (select count(c_int) over() as x, sum(c_float) over() from cbo_t1) cbo_t1; +explain select 1+sum(c_int) over() from cbo_t1; +explain select sum(c_int)+sum(sum(c_int)) over() from cbo_t1; +explain select * from (select max(c_int) over (partition by key order by value Rows UNBOUNDED PRECEDING), min(c_int) over (partition by key order by value rows current row), count(c_int) over(partition by key order by value ROWS 1 PRECEDING), avg(value) over (partition by key order by value Rows between unbounded preceding and unbounded following), sum(value) over (partition by key order by value rows between unbounded preceding and current row), avg(c_float) over (partition by key order by value Rows between 1 preceding and unbounded following), sum(c_float) over (partition by key order by value rows between 1 preceding and current row), max(c_float) over (partition by key order by value rows between 1 preceding and unbounded following), min(c_float) over (partition by key order by value rows between 1 preceding and 1 following) from cbo_t1) cbo_t1; +explain select i, a, h, b, c, d, e, f, g, a as x, a +1 as y from (select max(c_int) over (partition by key order by value range UNBOUNDED PRECEDING) a, min(c_int) over (partition by key order by value range current row) b, count(c_int) over(partition by key order by value range 1 PRECEDING) c, avg(value) over (partition by key order by value range between unbounded preceding and unbounded following) d, sum(value) over (partition by key order by value range between unbounded preceding and current row) e, avg(c_float) over (partition by key order by value range between 1 preceding and unbounded following) f, sum(c_float) over (partition by key order by value range between 1 preceding and current row) g, max(c_float) over (partition by key order by value range between 1 preceding and unbounded following) h, min(c_float) over (partition by key order by value range between 1 preceding and 1 following) i from cbo_t1) cbo_t1; +explain select *, rank() over(partition by key order by value) as rr from src1; + + +set hive.auto.convert.join=false; +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.auto.convert.join=true; +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.auto.convert.join=false; +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.auto.convert.join=false; +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + + +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp; + +set hive.optimize.correlation=false; +explain +select x.key, y.value, count(1) AS cnt +FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value) +GROUP BY x.key, y.value; + +set hive.optimize.correlation=true; +explain +select x.key, y.value, count(1) AS cnt +FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value) +GROUP BY x.key, y.value; + +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp; + +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x FULL OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x FULL OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp; + +set hive.auto.convert.join=false; +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.value)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, x.value AS value, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key, x.value) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.value)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, x.value AS value, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key, x.value) tmp; + +set hive.optimize.correlation=false; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key AND x.value = y.value) + GROUP BY x.key) tmp; + +set hive.optimize.correlation=true; +explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key AND x.value = y.value) + GROUP BY x.key) tmp; + +explain create table abcd (a int, b int, c int, d int); +create table abcd (a int, b int, c int, d int); +LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd; + +explain select * from abcd; +set hive.map.aggr=true; +explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a; + +explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd; + +set hive.map.aggr=false; +explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a; + +explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd; + +explain create table src_rc_merge_test(key int, value string) stored as rcfile; +create table src_rc_merge_test(key int, value string) stored as rcfile; + +load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test; + +set hive.exec.compress.output = true; + +explain create table tgt_rc_merge_test(key int, value string) stored as rcfile; +create table tgt_rc_merge_test(key int, value string) stored as rcfile; +explain insert into table tgt_rc_merge_test select * from src_rc_merge_test; +insert into table tgt_rc_merge_test select * from src_rc_merge_test; +explain insert into table tgt_rc_merge_test select * from src_rc_merge_test; +insert into table tgt_rc_merge_test select * from src_rc_merge_test; + +show table extended like `tgt_rc_merge_test`; + +explain select count(1) from tgt_rc_merge_test; +explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test; + +alter table tgt_rc_merge_test concatenate; + +show table extended like `tgt_rc_merge_test`; + +explain select count(1) from tgt_rc_merge_test; +explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test; + +drop table src_rc_merge_test; +drop table tgt_rc_merge_test; + +explain select src.key from src join src src2; +explain select src.key from src cross join src src2; +explain select src.key from src cross join src src2 on src.key=src2.key; + + +create table A as +select * from src; + +create table B as +select * from src +limit 10; + +set hive.auto.convert.join.noconditionaltask.size=100; + +explain select * from A join B; + +explain select * from B d1 join B d2 on d1.key = d2.key join A; + +explain select * from A join + (select d1.key + from B d1 join B d2 on d1.key = d2.key + where 1 = 1 group by d1.key) od1; + +explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1; + +explain select * from +(select A.key from A group by key) ss join +(select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1; + + + + +explain create table nzhang_Tmp(a int, b string); +create table nzhang_Tmp(a int, b string); +explain select * from nzhang_Tmp; + +explain create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10; +create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10; + +explain select * from nzhang_CTAS1; + +describe formatted nzhang_CTAS1; + +explain create table nzhang_ctas2 as select * from src sort by key, value limit 10; +create table nzhang_ctas2 as select * from src sort by key, value limit 10; + +explain select * from nzhang_ctas2; + +describe formatted nzhang_CTAS2; + + +explain create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10; + +create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10; + +explain select * from nzhang_ctas3; + +describe formatted nzhang_CTAS3; + + +explain create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2; + +create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2; + +explain select * from nzhang_ctas3; + +describe formatted nzhang_CTAS3; + + +explain create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10; + +create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10; + +explain select * from nzhang_ctas4; + +describe formatted nzhang_CTAS4; + +explain extended create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10; + +set mapreduce.framework.name=yarn; +set mapreduce.jobtracker.address=localhost:58; +set hive.exec.mode.local.auto=true; + +explain create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10; +create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10; + +explain create table nzhang_ctas6 (key string, `to` string); +create table nzhang_ctas6 (key string, `to` string); +explain insert overwrite table nzhang_ctas6 select key, value from src tablesample (10 rows); +insert overwrite table nzhang_ctas6 select key, value from src tablesample (10 rows); +explain create table nzhang_ctas7 as select key, `to` from nzhang_ctas6; +create table nzhang_ctas7 as select key, `to` from nzhang_ctas6; + +CREATE TABLE src1_rot13_iof(key STRING, value STRING) + STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.udf.Rot13InputFormat' + OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.udf.Rot13OutputFormat'; +DESCRIBE EXTENDED src1_rot13_iof; +INSERT OVERWRITE TABLE src1_rot13_iof select * FROM src1; + +set hive.support.concurrency=true; +set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; +set hive.enforce.bucketing=true; + +explain create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); +create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); + +explain insert into table acid_danp select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint < 0 order by cint limit 10; +insert into table acid_danp select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint < 0 order by cint limit 10; + +explain select a,b from acid_danp order by a; + +set hive.support.concurrency=true; +set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; +set hive.enforce.bucketing=true; + +explain create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); +create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); + +explain insert into table acid_dap partition (ds='today') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint < 0 order by cint limit 10; +insert into table acid_dap partition (ds='today') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint < 0 order by cint limit 10; +explain insert into table acid_dap partition (ds='tomorrow') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint > 1000 order by cint limit 10; +insert into table acid_dap partition (ds='tomorrow') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint > 1000 order by cint limit 10; + +explain select a,b,ds from acid_dap order by a,b; + +set hive.support.concurrency=true; +set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; +set hive.enforce.bucketing=true; + +explain create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); +create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); + +explain insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10; + +explain select * from acid_dtt order by a; + +set hive.optimize.sort.dynamic.partition=true; +set hive.exec.dynamic.partition=true; +set hive.exec.max.dynamic.partitions=1000; +set hive.exec.max.dynamic.partitions.pernode=1000; +set hive.exec.dynamic.partition.mode=nonstrict; +set hive.vectorized.execution.enabled=true; +set hive.enforce.bucketing=false; +set hive.enforce.sorting=false; +set hive.exec.submitviachild=true; +set hive.exec.submit.local.task.via.child=true; + +create table over1k( + t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) + row format delimited + fields terminated by '|'; + +load data local inpath '../../data/files/over1k' into table over1k; + +create table over1k_orc like over1k; +alter table over1k_orc set fileformat orc; +insert overwrite table over1k_orc select * from over1k; + +create table over1k_part_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (ds string, t tinyint) stored as orc; + +create table over1k_part_limit_orc like over1k_part_orc; +alter table over1k_part_limit_orc set fileformat orc; + +create table over1k_part_buck_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) into 4 buckets stored as orc; + +create table over1k_part_buck_sort_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) + sorted by (f) into 4 buckets stored as orc; + +explain insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si; +explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10; +explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; + +explain insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si; +insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si; +explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10; +insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10; +explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; + +set hive.enforce.bucketing=true; +set hive.enforce.sorting=true; + +explain insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si; +explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10; +explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; + +explain insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si; +insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si; +explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10; +insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10; +explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; +insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27; + +set hive.optimize.sort.dynamic.partition=true; +set hive.exec.dynamic.partition=true; +set hive.exec.max.dynamic.partitions=1000; +set hive.exec.max.dynamic.partitions.pernode=1000; +set hive.exec.dynamic.partition.mode=nonstrict; +set hive.enforce.bucketing=false; +set hive.enforce.sorting=false; +set hive.exec.submitviachild=true; +set hive.exec.submit.local.task.via.child=true; + + +drop table if exists over1k; + +create table over1k( + t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) + row format delimited + fields terminated by '|'; + +load data local inpath '../../data/files/over1k' into table over1k; + +create table over1k_part( + si smallint, + i int, + b bigint, + f float) + partitioned by (ds string, t tinyint); + +create table over1k_part_limit like over1k_part; + +create table over1k_part_buck( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) into 4 buckets; + +create table over1k_part_buck_sort( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) + sorted by (f) into 4 buckets; + +explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10; +explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27; + +explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27; +insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10; +insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10; +explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27; +insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27; +insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27; + +set hive.enforce.bucketing=true; +set hive.enforce.sorting=true; + +explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10; +explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27; + +explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27; +insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10; +insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10; +explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27; +insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27; +explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27; +insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27; + +set hive.map.aggr=false; +set hive.groupby.skewindata=true; + + +explain +select src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (select * FROM src WHERE src.key < 10) src1 + JOIN + (select * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2; + + +CREATE TABLE myinput1(key int, value int); +LOAD DATA LOCAL INPATH '../../data/files/in8.txt' INTO TABLE myinput1; + +explain select * from myinput1 a join myinput1 b on a.key<=>b.value; + +explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key=c.key; + +explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key<=>c.key; + +explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value=b.key join myinput1 c on a.key<=>c.key AND a.value=c.value; + +explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value<=>b.key join myinput1 c on a.key<=>c.key AND a.value<=>c.value; + +explain select * FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key<=>b.value; +explain select * FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key<=>b.value; +explain select * FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key<=>b.value; + +explain select /*+ MAPJOIN(b) */ * FROM myinput1 a JOIN myinput1 b ON a.key<=>b.value; + +CREATE TABLE smb_input(key int, value int); +LOAD DATA LOCAL INPATH '../../data/files/in4.txt' into table smb_input; +LOAD DATA LOCAL INPATH '../../data/files/in5.txt' into table smb_input; + +set hive.enforce.sorting = true; +set hive.enforce.bucketing = true; + +CREATE TABLE smb_input1(key int, value int) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS; +CREATE TABLE smb_input2(key int, value int) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS; + +from smb_input +insert overwrite table smb_input1 select * +insert overwrite table smb_input2 select *; + +SET hive.optimize.bucketmapjoin = true; +SET hive.optimize.bucketmapjoin.sortedmerge = true; +SET hive.input.format = org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat; + +explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key; +explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value; +explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key; +explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key; +explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key; + +drop table sales; +drop table things; + +set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat; + +CREATE TABLE sales (name STRING, id INT) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'; + +CREATE TABLE things (id INT, name STRING) partitioned by (ds string) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'; + +load data local inpath '../../data/files/sales.txt' INTO TABLE sales; +load data local inpath '../../data/files/things.txt' INTO TABLE things partition(ds='2011-10-23'); +load data local inpath '../../data/files/things2.txt' INTO TABLE things partition(ds='2011-10-24'); + +explain select name,id FROM sales LEFT SEMI JOIN things ON (sales.id = things.id); + +drop table sales; +drop table things; + +set hive.auto.convert.join=true; +set hive.auto.convert.join.noconditionaltask=true; +set hive.auto.convert.join.noconditionaltask.size=10000; + + +explain extended select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key); + +explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450'; + + + +set hive.mapjoin.optimized.hashtable=false; + +explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450'; + + + +set hive.mapjoin.optimized.hashtable=true; + +explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450'; + + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part + partition by p_mfgr + order by p_name + ); + +explain +select p_mfgr, p_name, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j +distribute by j.p_mfgr +sort by j.p_name) +; + +explain +select p_mfgr, p_name, p_size +from noop(on part +partition by p_mfgr +order by p_name); + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part + partition by p_mfgr + order by p_name + ) abc; + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop(on part + partition by p_mfgr + order by p_name + ) +; + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop(on part + partition by p_mfgr + order by p_name + ) +group by p_mfgr, p_name, p_size +; + +explain +select abc.* +from noop(on part +partition by p_mfgr +order by p_name +) abc join part p1 on abc.p_partkey = p1.p_partkey; + + +explain +select abc.* +from part p1 join noop(on part +partition by p_mfgr +order by p_name +) abc on abc.p_partkey = p1.p_partkey; + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name, p_size desc) as r +from noopwithmap(on part +partition by p_mfgr +order by p_name, p_size desc); + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noopwithmap(on part + partition by p_mfgr + order by p_name); + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part +partition by p_mfgr +order by p_name) +; + +explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on noopwithmap(on noop(on part +partition by p_mfgr +order by p_mfgr DESC, p_name +))); + +explain +select p_mfgr, p_name, +sub1.cd, sub1.s1 +from (select p_mfgr, p_name, +count(p_size) over (partition by p_mfgr order by p_name) as cd, +p_retailprice, +sum(p_retailprice) over w1 as s1 +from noop(on part +partition by p_mfgr +order by p_name) +window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) +) sub1 ; + + +explain +select abc.p_mfgr, abc.p_name, +rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, +dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, +count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, +abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, +abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz +from noop(on part +partition by p_mfgr +order by p_name +) abc join part p1 on abc.p_partkey = p1.p_partkey +; + + +explain +select DISTINCT p_mfgr, p_name, p_size +from noop(on part +partition by p_mfgr +order by p_name); + + +explain create view IF NOT EXISTS mfgr_price_view as +select p_mfgr, p_brand, +sum(p_retailprice) as s +from part +group by p_mfgr, p_brand; + +CREATE TABLE part_4( +p_mfgr STRING, +p_name STRING, +p_size INT, +r INT, +dr INT, +s DOUBLE); + +CREATE TABLE part_5( +p_mfgr STRING, +p_name STRING, +p_size INT, +s2 INT, +r INT, +dr INT, +cud DOUBLE, +fv1 INT); + +explain +from noop(on part +partition by p_mfgr +order by p_name) +INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, +rank() over (distribute by p_mfgr sort by p_name) as r, +dense_rank() over (distribute by p_mfgr sort by p_name) as dr, +sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s +INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, +round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, +rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, +dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, +cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, +first_value(p_size, true) over w1 as fv1 +window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following); + + +explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr,p_name) as r, +dense_rank() over (partition by p_mfgr,p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 +from noop(on + noopwithmap(on + noop(on + noop(on part + partition by p_mfgr + order by p_mfgr) + ) + partition by p_mfgr,p_name + order by p_mfgr,p_name) + partition by p_mfgr,p_name + order by p_mfgr,p_name) ; + +explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on + noop(on + noop(on + noop(on part + partition by p_mfgr + order by p_mfgr) + ) + partition by p_mfgr,p_name + order by p_mfgr,p_name) + partition by p_mfgr + order by p_mfgr ) ; + +explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 +from noop(on + noop(on + noop(on + noop(on part + partition by p_mfgr,p_name + order by p_mfgr,p_name) + ) + partition by p_mfgr + order by p_mfgr)); + +explain select distinct src.* from src; + +explain select explode(array('a', 'b')); + +set hive.optimize.skewjoin = true; +set hive.skewjoin.key = 2; + +CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE; +CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE; +CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE; +CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE; +CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE; + +LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1; +LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2; +LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3; +LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4; + + +explain +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value; + +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value; + + + +explain +select /*+ STREAMTABLE(a) */ * +FROM T1 a JOIN T2 b ON a.key = b.key + JOIN T3 c ON b.key = c.key + JOIN T4 d ON c.key = d.key; + +explain +select /*+ STREAMTABLE(a,c) */ * +FROM T1 a JOIN T2 b ON a.key = b.key + JOIN T3 c ON b.key = c.key + JOIN T4 d ON c.key = d.key; + +explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)); +FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)); + +explain +select * FROM +(select src.* FROM src) x +JOIN +(select src.* FROM src) Y +ON (x.key = Y.key); + + +explain select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val; + +explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key; + +explain select count(1) from T1 a join T1 b on a.key = b.key; + +explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)); + +explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)); + +explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)); + + + +explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key; + +explain select * +from src b +where exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_9' + ) +; + + +explain select * +from src b +where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +; + +explain +select p_name, p_size +from +part where part.p_size in + (select avg(p_size) + from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a + where r <= 2 + ) +; + +explain + select count(1) FROM (select s1.key as key, s1.value as value from src s1 UNION + select s2.key as key, s2.value as value from src s2) unionsrc; + + +SET hive.vectorized.execution.enabled=true; +SET hive.auto.convert.join=true; + + +explain +select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') +; + +explain +select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) +; + + +CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) +CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; +load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08'); +load data local inpath '../../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08'); + +CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE; +load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); + +load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); +load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); +load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); +load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); + +set hive.auto.convert.join=true; +set hive.auto.convert.sortmerge.join=true; +set hive.optimize.bucketmapjoin = true; +set hive.optimize.bucketmapjoin.sortedmerge = true; + +set hive.auto.convert.sortmerge.join.to.mapjoin=false; +set hive.auto.convert.sortmerge.join.bigtable.selection.policy = org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ; + +explain select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key; + +explain select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key; + +set hive.auto.convert.sortmerge.join.to.mapjoin=true; +explain select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key; diff --git a/ql/src/test/queries/clientpositive/explainuser_2.q b/ql/src/test/queries/clientpositive/explainuser_2.q new file mode 100644 index 0000000..c22ff71 --- /dev/null +++ b/ql/src/test/queries/clientpositive/explainuser_2.q @@ -0,0 +1,220 @@ +set hive.explain.user=true; + +CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE; + +CREATE TABLE ss(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE; + +CREATE TABLE sr(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE; + +CREATE TABLE cs(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE; + +INSERT OVERWRITE TABLE ss +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11); + +INSERT OVERWRITE TABLE sr +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=12); + +INSERT OVERWRITE TABLE cs +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08'); + + +ANALYZE TABLE ss COMPUTE STATISTICS; +ANALYZE TABLE ss COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3; + +ANALYZE TABLE sr COMPUTE STATISTICS; +ANALYZE TABLE sr COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3; + +ANALYZE TABLE cs COMPUTE STATISTICS; +ANALYZE TABLE cs COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3; + +set hive.auto.convert.join=false; + +EXPLAIN +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11); + +EXPLAIN +select +ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) +FROM +ss,sr,cs,src d1,src d2,src d3,src1,srcpart +where + ss.k1 = d1.key +and sr.k1 = d2.key +and cs.k1 = d3.key +and ss.k2 = sr.k2 +and ss.k3 = sr.k3 +and ss.v1 = src1.value +and ss.v2 = srcpart.value +and sr.v2 = cs.v2 +and sr.v3 = cs.v3 +and ss.v3='ssv3' +and sr.v1='srv1' +and src1.key = 'src1key' +and srcpart.key = 'srcpartkey' +and d1.value = 'd1value' +and d2.value in ('2000Q1','2000Q2','2000Q3') +and d3.value in ('2000Q1','2000Q2','2000Q3') +group by +ss.k1,sr.k2,cs.k3 +order by +ss.k1,sr.k2,cs.k3 +limit 100; + +explain +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value); + + +explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value); + + +set hive.auto.convert.join=true; +set hive.auto.convert.join.noconditionaltask=true; +set hive.auto.convert.join.noconditionaltask.size=10000; + + +EXPLAIN +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11); + +EXPLAIN +select +ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) +FROM +ss,sr,cs,src d1,src d2,src d3,src1,srcpart +where + ss.k1 = d1.key +and sr.k1 = d2.key +and cs.k1 = d3.key +and ss.k2 = sr.k2 +and ss.k3 = sr.k3 +and ss.v1 = src1.value +and ss.v2 = srcpart.value +and sr.v2 = cs.v2 +and sr.v3 = cs.v3 +and ss.v3='ssv3' +and sr.v1='srv1' +and src1.key = 'src1key' +and srcpart.key = 'srcpartkey' +and d1.value = 'd1value' +and d2.value in ('2000Q1','2000Q2','2000Q3') +and d3.value in ('2000Q1','2000Q2','2000Q3') +group by +ss.k1,sr.k2,cs.k3 +order by +ss.k1,sr.k2,cs.k3 +limit 100; + +explain +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value); + + +explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value); + + +set hive.auto.convert.join=true; +set hive.auto.convert.join.noconditionaltask=true; +set hive.auto.convert.join.noconditionaltask.size=10000; +set hive.auto.convert.sortmerge.join.bigtable.selection.policy = org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ; + +CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; +CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE; +CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE; + +load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08'); + +load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08'); +load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08'); + +set hive.enforce.bucketing=true; +set hive.enforce.sorting = true; +set hive.optimize.bucketingsorting=false; +insert overwrite table tab_part partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin_part; + +CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; +insert overwrite table tab partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin; + +CREATE TABLE tab2(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; +insert overwrite table tab2 partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin; + +set hive.convert.join.bucket.mapjoin.tez = false; +set hive.auto.convert.sortmerge.join = true; + +set hive.auto.convert.join.noconditionaltask.size=500; + + +explain +select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key; + +explain +select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value; + +explain +select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key; + +explain +select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key join tab2 s2 on s1.value=s2.value; + +explain +select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key +UNION ALL +select s2.key as key, s2.value as value from tab s2 +) a join tab_part b on (a.key = b.key); + + +explain +select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value +UNION ALL +select s2.key as key, s2.value as value from tab s2 +) a join tab_part b on (a.key = b.key); \ No newline at end of file diff --git a/ql/src/test/queries/clientpositive/explainuser_3.q b/ql/src/test/queries/clientpositive/explainuser_3.q new file mode 100644 index 0000000..91cb81d --- /dev/null +++ b/ql/src/test/queries/clientpositive/explainuser_3.q @@ -0,0 +1,78 @@ +set hive.explain.user=true; + +explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value); + +explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value); + +CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE; +CREATE TABLE b(key STRING, value STRING) STORED AS TEXTFILE; +CREATE TABLE c(key STRING, value STRING) STORED AS TEXTFILE; + +explain +from +( +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +) tmp +INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value; + +explain +FROM +( +SELECT x.key as key, y.value as value from src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key as key, y.value as value from src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key as key, y.value as value from src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +) tmp +INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value; + + +CREATE TABLE DEST1(key STRING, value STRING) STORED AS TEXTFILE; +CREATE TABLE DEST2(key STRING, val1 STRING, val2 STRING) STORED AS TEXTFILE; + +explain +FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1 + UNION DISTINCT + select s2.key as key, s2.value as value from src s2) unionsrc +INSERT OVERWRITE TABLE DEST1 SELECT unionsrc.key, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key +INSERT OVERWRITE TABLE DEST2 SELECT unionsrc.key, unionsrc.value, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key, unionsrc.value; + diff --git a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out new file mode 100644 index 0000000..c47c255 --- /dev/null +++ b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out @@ -0,0 +1,18156 @@ +PREHOOK: query: explain create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + columns:["key int","value string"] + input format:org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + name:default.src_orc_merge_test_part + output format:org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition columns:["ds string","ts string"] +PREHOOK: query: create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src_orc_merge_test_part +POSTHOOK: query: create table src_orc_merge_test_part(key int, value string) partitioned by (ds string, ts string) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_orc_merge_test_part +PREHOOK: query: alter table src_orc_merge_test_part add partition (ds='2012-01-03', ts='2012-01-03+14:46:31') +PREHOOK: type: ALTERTABLE_ADDPARTS +PREHOOK: Output: default@src_orc_merge_test_part +POSTHOOK: query: alter table src_orc_merge_test_part add partition (ds='2012-01-03', ts='2012-01-03+14:46:31') +POSTHOOK: type: ALTERTABLE_ADDPARTS +POSTHOOK: Output: default@src_orc_merge_test_part +POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +PREHOOK: query: desc extended src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@src_orc_merge_test_part +POSTHOOK: query: desc extended src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@src_orc_merge_test_part +key int +value string +ds string +ts string + +# Partition Information +# col_name data_type comment + +ds string +ts string + +#### A masked pattern was here #### +PREHOOK: query: explain insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ts":"2012-01-03+14:46:31","ds":"2012-01-03"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Map 1 + File Output Operator [FS_3] + compressed:false + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: query: insert overwrite table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ts":"2012-01-03+14:46:31","ds":"2012-01-03"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Limit [LIM_5] + Number of rows:100 + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_4] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + sort order: + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col1 (type: string) + Limit [LIM_2] + Number of rows:100 + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: query: insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ts":"2012-01-03+14:46:31","ds":"2012-01-03"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.src_orc_merge_test_part","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Limit [LIM_5] + Number of rows:10 + Statistics:Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_4] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + sort order: + Statistics:Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col1 (type: string) + Limit [LIM_2] + Number of rows:10 + Statistics:Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: query: insert into table src_orc_merge_test_part partition(ds='2012-01-03', ts='2012-01-03+14:46:31') select * from src limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_orc_merge_test_part PARTITION(ds=2012-01-03,ts=2012-01-03+14:46:31).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_7] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_5] + aggregations:["count(1)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + Statistics:Num rows: 610 Data size: 57340 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src_orc_merge_test_part + Statistics:Num rows: 610 Data size: 57340 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_7] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_5] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 610 Data size: 57340 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src_orc_merge_test_part + Statistics:Num rows: 610 Data size: 57340 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate +PREHOOK: type: ALTER_PARTITION_MERGE +PREHOOK: Input: default@src_orc_merge_test_part +PREHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +POSTHOOK: query: alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate +POSTHOOK: type: ALTER_PARTITION_MERGE +POSTHOOK: Input: default@src_orc_merge_test_part +POSTHOOK: Output: default@src_orc_merge_test_part@ds=2012-01-03/ts=2012-01-03+14%3A46%3A31 +PREHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_7] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_5] + aggregations:["count(1)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + Statistics:Num rows: 0 Data size: 3443 Basic stats: PARTIAL Column stats: NONE + TableScan [TS_0] + alias:src_orc_merge_test_part + Statistics:Num rows: 0 Data size: 3443 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from src_orc_merge_test_part where ds='2012-01-03' and ts='2012-01-03+14:46:31' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_7] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_5] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 33 Data size: 3443 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src_orc_merge_test_part + Statistics:Num rows: 33 Data size: 3443 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: drop table src_orc_merge_test_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@src_orc_merge_test_part +PREHOOK: Output: default@src_orc_merge_test_part +POSTHOOK: query: drop table src_orc_merge_test_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@src_orc_merge_test_part +POSTHOOK: Output: default@src_orc_merge_test_part +Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: explain select sum(hash(a.k1,a.v1,a.k2, a.v2)) +from ( +select src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (select * FROM src WHERE src.key < 10) src1 + JOIN + (select * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +) a +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(hash(a.k1,a.v1,a.k2, a.v2)) +from ( +select src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (select * FROM src WHERE src.key < 10) src1 + JOIN + (select * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +) a +POSTHOOK: type: QUERY +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_17] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_15] + | aggregations:["sum(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_13] + aggregations:["sum(hash(_col0,_col1,_col2,_col3))"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_11] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order:++++ + Statistics:Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_20] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_7] + | sort order: + | Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col1 (type: string) + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_19] + | predicate:(key < 10) (type: boolean) + | Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_3] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_18] + predicate:(key < 10) (type: boolean) + Statistics:Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key +PREHOOK: type: QUERY +POSTHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_4] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x +PREHOOK: type: QUERY +POSTHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: bigint), _col1 (type: float) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: float) + sort order:++ + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count()"] + keys:_col0 (type: bigint), _col1 (type: float) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_4] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 10 <- Map 9 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) +Reducer 8 <- Reducer 11 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_50] + compressed:false + Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_49] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_48] + key expressions:(UDFToLong(_col0) + _col1) (type: bigint), _col1 (type: bigint) + sort order:-+ + Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: bigint) + Group By Operator [GBY_46] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_45] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_44] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_40] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_56] + predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean) + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_62] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3","_col4"] + | Statistics:Num rows: 19 Data size: 1566 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_36] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_57] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_32] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_58] + predicate:((_col3 + _col1) >= 0) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_61] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_30] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_25] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_24] + | key expressions:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_23] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_22] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_20] + | aggregations:["sum(_col1)"] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_17] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_60] + | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_15] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_28] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col3 (type: double), _col2 (type: bigint) + sort order:-+ + Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string), _col1 (type: int) + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_9] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_7] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_4] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_59] + predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 6 + File Output Operator [FS_45] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_44] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_43] + key expressions:(UDFToLong(_col0) % _col1) (type: bigint), _col0 (type: int) + sort order:+- + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: bigint), _col2 (type: bigint) + Group By Operator [GBY_41] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_40] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_39] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator [SEL_37] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator [FIL_36] + predicate:(((_col1 > 0) or (_col6 >= 0)) and (((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0))) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_55] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 5 Data size: 391 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_34] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_30] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_53] + | predicate:((c_int > 0) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_28] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_25] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator [FIL_50] + predicate:((_col3 + _col1) >= 0) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_54] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_5] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_51] + | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_20] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col3 (type: bigint), _col1 (type: int) + sort order:+- + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col0 (type: string), _col2 (type: bigint) + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_17] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_16] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_14] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_52] + predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_9] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 + File Output Operator [FS_38] + compressed:false + Statistics:Num rows: 2 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_36] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 2 Data size: 160 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_35] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_34] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_32] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_42] + predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 4 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_47] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 22 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_29] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_27] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_26] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_28] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint), _col4 (type: int) + Select Operator [SEL_25] + outputColumnNames:["_col0","_col1","_col2","_col4"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_46] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_5] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_44] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_20] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col3 (type: bigint), _col0 (type: string) + sort order:+- + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_17] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_16] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_14] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_45] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_9] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 7 + File Output Operator [FS_45] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_44] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_43] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: bigint), _col2 (type: bigint) + Group By Operator [GBY_41] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_40] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_39] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator [SEL_37] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator [FIL_48] + predicate:(((((_col1 + _col4) >= 0) and ((_col1 > 0) or (_col6 >= 0))) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_54] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 6 Data size: 489 Basic stats: COMPLETE Column stats: NONE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_34] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_32] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_52] + | predicate:(c_int > 0) (type: boolean) + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_30] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_33] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint), _col4 (type: int) + Select Operator [SEL_29] + outputColumnNames:["_col0","_col1","_col2","_col4"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_53] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_24] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Reducer 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_23] + | key expressions:_col3 (type: double) + | sort order:- + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_21] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_20] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_18] + | aggregations:["sum(_col1)"] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_15] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_51] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | TableScan [TS_13] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_26] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_11] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col3 (type: double), _col2 (type: bigint) + sort order:-+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col0 (type: string), _col1 (type: int) + Select Operator [SEL_9] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_8] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_7] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_5] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_50] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_41] + compressed:false + Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_39] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_37] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_33] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_47] + predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean) + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_53] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3","_col4"] + | Statistics:Num rows: 19 Data size: 1566 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_29] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_48] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_31] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_25] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator [FIL_49] + predicate:((_col3 + _col1) >= 0) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_52] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_10] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Map 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_7] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_4] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_50] + | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_19] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_18] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_16] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_51] + predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_11] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc +PREHOOK: type: QUERY +POSTHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:false + Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_4] + aggregations:["count(1)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select unionsrc.key FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 + UNION ALL + select 'min' as key, min(c_int) as value from cbo_t3 s2 + UNION ALL + select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc order by unionsrc.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select unionsrc.key FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 + UNION ALL + select 'min' as key, min(c_int) as value from cbo_t3 s2 + UNION ALL + select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc order by unionsrc.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 4 <- Union 3 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_29] + compressed:false + Statistics:Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_28] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Union 3 [SIMPLE_EDGE] + |<-Reducer 2 [CONTAINS] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | sort order:+ + | Select Operator [SEL_6] + | outputColumnNames:["_col0"] + | Group By Operator [GBY_5] + | | aggregations:["count(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | sort order: + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: bigint) + | Group By Operator [GBY_3] + | aggregations:["count(_col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:s1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [CONTAINS] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | sort order:+ + | Select Operator [SEL_14] + | outputColumnNames:["_col0"] + | Group By Operator [GBY_13] + | | aggregations:["count(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_12] + | sort order: + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: bigint) + | Group By Operator [GBY_11] + | aggregations:["count(_col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_9] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_8] + | alias:s1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [CONTAINS] + Reduce Output Operator [RS_27] + key expressions:_col0 (type: string) + sort order:+ + Select Operator [SEL_24] + outputColumnNames:["_col0"] + Group By Operator [GBY_23] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_22] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_21] + aggregations:["count(_col0)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_19] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_18] + alias:s1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select unionsrc.key, count(1) FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 + UNION ALL + select 'min' as key, min(c_int) as value from cbo_t3 s2 + UNION ALL + select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc group by unionsrc.key order by unionsrc.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select unionsrc.key, count(1) FROM (select 'max' as key, max(c_int) as value from cbo_t3 s1 + UNION ALL + select 'min' as key, min(c_int) as value from cbo_t3 s2 + UNION ALL + select 'avg' as key, avg(c_int) as value from cbo_t3 s3) unionsrc group by unionsrc.key order by unionsrc.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Union 3 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 3 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 + File Output Operator [FS_34] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_33] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_30] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Union 3 [SIMPLE_EDGE] + |<-Reducer 2 [CONTAINS] + | Reduce Output Operator [RS_29] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | value expressions:_col1 (type: bigint) + | Group By Operator [GBY_28] + | aggregations:["count(1)"] + | keys:_col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_6] + | outputColumnNames:["_col0"] + | Group By Operator [GBY_5] + | | aggregations:["count(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | sort order: + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: bigint) + | Group By Operator [GBY_3] + | aggregations:["count(_col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:s1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [CONTAINS] + | Reduce Output Operator [RS_29] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | value expressions:_col1 (type: bigint) + | Group By Operator [GBY_28] + | aggregations:["count(1)"] + | keys:_col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_14] + | outputColumnNames:["_col0"] + | Group By Operator [GBY_13] + | | aggregations:["count(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | |<-Map 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_12] + | sort order: + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: bigint) + | Group By Operator [GBY_11] + | aggregations:["count(_col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_9] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_8] + | alias:s1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [CONTAINS] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + value expressions:_col1 (type: bigint) + Group By Operator [GBY_28] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_24] + outputColumnNames:["_col0"] + Group By Operator [GBY_23] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_22] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_21] + aggregations:["count(_col0)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_19] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_18] + alias:s1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 join cbo_t2 on cbo_t1.key=cbo_t2.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 join cbo_t2 on cbo_t1.key=cbo_t2.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_10] + compressed:false + Statistics:Num rows: 81 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_9] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 81 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_15] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3"] + | Statistics:Num rows: 81 Data size: 648 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_13] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_14] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.key from cbo_t1 join cbo_t3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.key from cbo_t1 join cbo_t3 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:false + Statistics:Num rows: 22 Data size: 1683 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_11] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 22 Data size: 1683 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | sort order: + | Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_3] + Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t3 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.key from cbo_t1 join cbo_t3 where cbo_t1.key=cbo_t3.key and cbo_t1.key >= 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.key from cbo_t1 join cbo_t3 where cbo_t1.key=cbo_t3.key and cbo_t1.key >= 1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:false + Statistics:Num rows: 18 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_15] + | predicate:(UDFToDouble(key) >= 1.0) (type: boolean) + | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_16] + predicate:(UDFToDouble(key) >= 1.0) (type: boolean) + Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t3 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 left outer join cbo_t2 on cbo_t1.key=cbo_t2.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 left outer join cbo_t2 on cbo_t1.key=cbo_t2.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_11] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3"] + | Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 full outer join cbo_t2 on cbo_t1.key=cbo_t2.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.c_int, cbo_t2.c_int from cbo_t1 full outer join cbo_t2 on cbo_t1.key=cbo_t2.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_9] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3"] + | Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key +PREHOOK: type: QUERY +POSTHOOK: query: explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_25] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col5","_col6"] + | Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_22] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_23] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_24] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_4] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select key, cbo_t1.c_int, cbo_t2.p, q from cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.key=p join (select key as a, c_int as b, cbo_t3.c_float as c from cbo_t3)cbo_t3 on cbo_t1.key=a +PREHOOK: type: QUERY +POSTHOOK: query: explain select key, cbo_t1.c_int, cbo_t2.p, q from cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2) cbo_t2 on cbo_t1.key=p join (select key as a, c_int as b, cbo_t3.c_float as c from cbo_t3)cbo_t3 on cbo_t1.key=a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_25] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col3","_col4"] + | Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_22] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_3] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_23] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_24] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_4] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select a, cbo_t1.b, key, cbo_t2.c_int, cbo_t3.p from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=key join (select key as p, c_int as q, cbo_t3.c_float as r from cbo_t3)cbo_t3 on cbo_t1.a=cbo_t3.p +PREHOOK: type: QUERY +POSTHOOK: query: explain select a, cbo_t1.b, key, cbo_t2.c_int, cbo_t3.p from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=key join (select key as p, c_int as q, cbo_t3.c_float as r from cbo_t3)cbo_t3 on cbo_t1.a=cbo_t3.p +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 291 Data size: 76533 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 291 Data size: 76533 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_24] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 291 Data size: 76533 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_21] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_3] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_22] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_23] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_4] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select b, cbo_t1.c, cbo_t2.c_int, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=cbo_t2.key join cbo_t3 on cbo_t1.a=cbo_t3.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select b, cbo_t1.c, cbo_t2.c_int, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=cbo_t2.key join cbo_t3 on cbo_t1.a=cbo_t3.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 291 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 291 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_25] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 291 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_22] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_23] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_24] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_4] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, b, cbo_t2.c_int, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=cbo_t2.key join cbo_t3 on cbo_t1.a=cbo_t3.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, b, cbo_t2.c_int, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1) cbo_t1 join cbo_t2 on cbo_t1.a=cbo_t2.key join cbo_t3 on cbo_t1.a=cbo_t3.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 291 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 291 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_25] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 291 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_22] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_23] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_24] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_4] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or cbo_t2.q >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select b, cbo_t1.c, cbo_t2.p, q, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or cbo_t2.q >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_23] + compressed:false + Statistics:Num rows: 28 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 28 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_33] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3","_col4","_col5","_col6"] + | Statistics:Num rows: 28 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 8 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) + Filter Operator [FIL_14] + predicate:(((_col1 + _col4) = 2) and ((_col1 > 0) or (_col4 >= 0))) (type: boolean) + Statistics:Num rows: 8 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_32] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 25 Data size: 4550 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_4] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_30] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_31] + predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_5] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 28 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 28 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 28 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 43 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_28] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 12 Data size: 2184 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) + Filter Operator [FIL_10] + predicate:((_col1 + _col4) = 2) (type: boolean) + Statistics:Num rows: 12 Data size: 2184 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_29] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 25 Data size: 4550 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_26] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_27] + predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 32 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 9 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) + Filter Operator [FIL_26] + predicate:(((_col1 + _col4) = 2) and _col0 is not null) (type: boolean) + Statistics:Num rows: 9 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_30] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 18 Data size: 3276 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_27] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_28] + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 32 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_28] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 9 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) + Filter Operator [FIL_25] + predicate:(((_col1 + _col4) = 2) and _col0 is not null) (type: boolean) + Statistics:Num rows: 9 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_29] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 18 Data size: 3276 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_26] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_27] + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 14 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_28] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) + Filter Operator [FIL_25] + predicate:((((_col1 + _col4) = 2) and ((_col4 + 1) = 2)) and _col0 is not null) (type: boolean) + Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_29] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 18 Data size: 3276 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_26] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_27] + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_17] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_27] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) + Filter Operator [FIL_22] + predicate:(((_col1 + _col4) = 2) and ((_col4 + 1) = 2)) (type: boolean) + Statistics:Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 18 Data size: 3276 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_23] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_24] + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 right outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_14] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_18] + predicate:((((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0))) and ((_col4 + 1) = 2)) (type: boolean) + Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_21] + | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_19] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_20] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_8] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_7] + alias:cbo_t3 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select q, b, cbo_t2.p, cbo_t1.c, cbo_t3.c_int from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 full outer join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q == 2) and (b > 0 or c_int >= 0)) R where (q + 1 = 2) and (R.b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_14] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_17] + predicate:((((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0))) and ((_col4 + 1) = 2)) (type: boolean) + Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Outer Join 0 to 1"},{"":"Right Outer Join0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_18] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_19] + | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_8] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_7] + alias:cbo_t3 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key order by x limit 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select key, (c_int+1)+2 as x, sum(c_int) from cbo_t1 group by c_float, cbo_t1.c_int, key order by x limit 1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:1 + Stage-1 + Reducer 3 + File Output Operator [FS_11] + compressed:false + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_10] + Number of rows:1 + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col1 (type: int) + sort order:+ + Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string), _col2 (type: bigint) + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_4] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x order by x,y limit 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select x, y, count(*) from (select key, (c_int+c_float+1+2) as x, sum(c_int) as y from cbo_t1 group by c_float, cbo_t1.c_int, key) R group by y, x order by x,y limit 1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:1 + Stage-1 + Reducer 4 + File Output Operator [FS_17] + compressed:false + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_16] + Number of rows:1 + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: float), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: bigint), _col1 (type: float) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: float) + sort order:++ + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count()"] + keys:_col0 (type: bigint), _col1 (type: float) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_4] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select key from(select key from (select key from cbo_t1 limit 5)cbo_t2 limit 5)cbo_t3 limit 5 +PREHOOK: type: QUERY +POSTHOOK: query: explain select key from(select key from (select key from cbo_t1 limit 5)cbo_t2 limit 5)cbo_t3 limit 5 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:5 + Stage-1 + Reducer 3 + File Output Operator [FS_13] + compressed:false + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_12] + Number of rows:5 + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_10] + Number of rows:5 + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + sort order: + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Limit [LIM_7] + Number of rows:5 + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_5] + Number of rows:5 + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_4] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + sort order: + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Limit [LIM_2] + Number of rows:5 + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select key, c_int from(select key, c_int from (select key, c_int from cbo_t1 order by c_int limit 5)cbo_t1 order by c_int limit 5)cbo_t2 order by c_int limit 5 +PREHOOK: type: QUERY +POSTHOOK: query: explain select key, c_int from(select key, c_int from (select key, c_int from cbo_t1 order by c_int limit 5)cbo_t1 order by c_int limit 5)cbo_t2 order by c_int limit 5 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:5 + Stage-1 + Reducer 4 + File Output Operator [FS_13] + compressed:false + Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_12] + Number of rows:5 + Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col1 (type: int) + sort order:+ + Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col0 (type: string) + Limit [LIM_8] + Number of rows:5 + Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_7] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col1 (type: int) + sort order:+ + Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Limit [LIM_4] + Number of rows:5 + Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col1 (type: int) + sort order:+ + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a limit 5) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc limit 5) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c limit 5 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key order by a limit 5) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key order by q/10 desc, r asc limit 5) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c order by cbo_t3.c_int+c desc, c limit 5 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 10 <- Map 9 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) +Reducer 8 <- Reducer 11 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:5 + Stage-1 + Reducer 4 + File Output Operator [FS_53] + compressed:false + Statistics:Num rows: 5 Data size: 410 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_52] + Number of rows:5 + Statistics:Num rows: 5 Data size: 410 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_51] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_50] + key expressions:(UDFToLong(_col0) + _col1) (type: bigint), _col1 (type: bigint) + sort order:-+ + Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: bigint) + Group By Operator [GBY_48] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 494 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_47] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_46] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_42] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_59] + predicate:((_col3 > 0) or (_col1 >= 0)) (type: boolean) + Statistics:Num rows: 12 Data size: 989 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_67] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3","_col4"] + | Statistics:Num rows: 19 Data size: 1566 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_38] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_60] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_40] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_34] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_61] + predicate:((_col3 + _col1) >= 0) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_66] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_32] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Filter Operator [FIL_64] + | predicate:_col0 is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | Limit [LIM_27] + | Number of rows:5 + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_26] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_24] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_23] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_21] + | aggregations:["sum(_col1)"] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_18] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_65] + | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_16] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_30] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Filter Operator [FIL_62] + predicate:_col0 is not null (type: boolean) + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_14] + Number of rows:5 + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col3 (type: double), _col2 (type: bigint) + sort order:-+ + Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string), _col1 (type: int) + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_9] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_7] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_4] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_63] + predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc limit 5) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 limit 5) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc limit 5 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b % c asc, b desc limit 5) cbo_t1 left outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 limit 5) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int % c asc, cbo_t3.c_int desc limit 5 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:5 + Stage-1 + Reducer 7 + File Output Operator [FS_52] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_51] + Number of rows:5 + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator [SEL_50] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_49] + key expressions:(UDFToLong(_col0) % _col1) (type: bigint), _col0 (type: int) + sort order:+- + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: bigint), _col2 (type: bigint) + Group By Operator [GBY_47] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_46] + key expressions:_col0 (type: int), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_45] + aggregations:["count()"] + keys:_col0 (type: int), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator [SEL_43] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator [FIL_42] + predicate:(((_col1 > 0) or (_col6 >= 0)) and (((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0))) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_64] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 5 Data size: 391 Basic stats: COMPLETE Column stats: NONE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_40] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_36] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_62] + | predicate:((c_int > 0) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_34] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_31] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator [FIL_57] + predicate:((_col3 + _col1) >= 0) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Merge Join Operator [MERGEJOIN_63] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_29] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Filter Operator [FIL_60] + | predicate:_col0 is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Limit [LIM_26] + | Number of rows:5 + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_25] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Reducer 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_24] + | key expressions:_col3 (type: bigint), _col1 (type: int) + | sort order:+- + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col2 (type: bigint) + | Select Operator [SEL_23] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_22] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_21] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_19] + | aggregations:["sum(_col1)"] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_16] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_61] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | TableScan [TS_14] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_28] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: int) + Filter Operator [FIL_58] + predicate:_col0 is not null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Limit [LIM_12] + Number of rows:5 + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_11] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + sort order: + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col0 (type: string), _col1 (type: int) + Limit [LIM_9] + Number of rows:5 + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_8] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_7] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_5] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_59] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:false + Statistics:Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_11] + outputColumnNames:["_col0"] + Statistics:Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_15] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_13] + compressed:false + Statistics:Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_12] + outputColumnNames:["_col0"] + Statistics:Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_18] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_16] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_4] + outputColumnNames:["_col0"] + Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_17] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where (b + 1 = 2) and (R.b > 0 or c >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where (b + 1 = 2) and (R.b > 0 or c >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_14] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_28] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_16] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_10] + | keys:_col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_8] + outputColumnNames:["_col0"] + Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_30] + predicate:key is not null (type: boolean) + Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_7] + alias:cbo_t3 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select cbo_t3.c_int, cbo_t1.c, b from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 = 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t3.c_int == 2) and (b > 0 or c_int >= 0)) R where (R.c_int + 1 = 2) and (R.b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select cbo_t3.c_int, cbo_t1.c, b from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 = 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t3.c_int == 2) and (b > 0 or c_int >= 0)) R where (R.c_int + 1 = 2) and (R.b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_23] + compressed:false + Statistics:Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_27] + predicate:((((_col3 + _col1) = 2) and ((_col1 + 1) = 2)) and ((_col3 > 0) or (_col1 >= 0))) (type: boolean) + Statistics:Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_32] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3","_col4"] + | Statistics:Num rows: 40 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float) + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_12] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_4] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_10] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_30] + predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_5] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where (c + 1 = 2) and (R.b > 0 or c_int >= 0) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where (c + 1 = 2) and (R.b > 0 or c_int >= 0) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_23] + compressed:false + Statistics:Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_20] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_28] + predicate:((((_col3 > 0) or (_col1 >= 0)) and ((_col3 + 1) = 2)) and ((_col4 + 1.0) = 2.0)) (type: boolean) + Statistics:Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_32] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col3","_col4"] + | Statistics:Num rows: 40 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: float) + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_12] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: float) + | Select Operator [SEL_4] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_10] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_30] + predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_5] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a +PREHOOK: type: QUERY +POSTHOOK: query: explain select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 6 + File Output Operator [FS_48] + compressed:false + Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_47] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_46] + key expressions:_col1 (type: bigint), _col0 (type: string) + sort order:++ + Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_44] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: bigint) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 431 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_43] + key expressions:_col0 (type: string), _col1 (type: bigint) + Map-reduce partition columns:_col0 (type: string), _col1 (type: bigint) + sort order:++ + Statistics:Num rows: 13 Data size: 935 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_42] + aggregations:["count()"] + keys:_col0 (type: string), _col1 (type: bigint) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 13 Data size: 935 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_60] + | condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}] + | keys:{"2":"_col0 (type: string)","1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 13 Data size: 935 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_39] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_33] + | keys:_col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_29] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_59] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_28] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_35] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col1 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: double), _col2 (type: bigint) + | sort order:-+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col0 (type: string) + | Select Operator [SEL_9] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_55] + | predicate:(((_col1 + 1) >= 0) and ((_col1 > 0) or (UDFToDouble(_col0) >= 0.0))) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_56] + | predicate:(((UDFToDouble(_col2) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col2) >= 1.0) or (_col3 >= 1))) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | sort order:+++ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col1)"] + | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_57] + | predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_31] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_26] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_25] + key expressions:_col1 (type: double), _col0 (type: string) + sort order:-+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_23] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_22] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_20] + aggregations:["sum(_col1)"] + keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_17] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_58] + predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_15] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from cbo_t1 as cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cbo_t1 as cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from cbo_t1 as cbo_t2 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cbo_t1 as cbo_t2 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + TableScan [TS_0] + alias:cbo_t2 +PREHOOK: query: explain select cbo_t1.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from cbo_t1 where cbo_t1.c_int >= 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cbo_t1 where cbo_t1.c_int >= 0 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_4] + predicate:(c_int >= 0) (type: boolean) + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from cbo_t1 as cbo_t1 where cbo_t1.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cbo_t1 as cbo_t1 where cbo_t1.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_4] + predicate:(((c_int >= 0) and ((c_float + UDFToFloat(c_int)) >= 0.0)) or (c_float <= 100.0)) (type: boolean) + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_4] + predicate:(((c_int >= 0) and ((c_float + UDFToFloat(c_int)) >= 0.0)) or (c_float <= 100.0)) (type: boolean) + TableScan [TS_0] + alias:cbo_t2 +PREHOOK: query: explain select cbo_t2.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t2.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_5] + predicate:(((c_int >= 0) and ((c_float + UDFToFloat(c_int)) >= 0.0)) or (c_float <= 100.0)) (type: boolean) + TableScan [TS_0] + alias:cbo_t2 +PREHOOK: query: explain select * from (select * from cbo_t1 where cbo_t1.c_int >= 0) as cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select * from cbo_t1 where cbo_t1.c_int >= 0) as cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_4] + predicate:(c_int >= 0) (type: boolean) + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from (select * from cbo_t1 as cbo_t1 where cbo_t1.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100) as cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select * from cbo_t1 as cbo_t1 where cbo_t1.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100) as cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_4] + predicate:(((c_int >= 0) and ((c_float + UDFToFloat(c_int)) >= 0.0)) or (c_float <= 100.0)) (type: boolean) + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select * from (select cbo_t2.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100) as cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select cbo_t2.key as x, c_int as c_int, (((c_int+c_float)*10)+5) as y from cbo_t1 as cbo_t2 where cbo_t2.c_int >= 0 and c_float+c_int >= 0 or c_float <= 100) as cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_5] + predicate:(((c_int >= 0) and ((c_float + UDFToFloat(c_int)) >= 0.0)) or (c_float <= 100.0)) (type: boolean) + TableScan [TS_0] + alias:cbo_t2 +PREHOOK: query: explain select cbo_t2.c_int+c_float as x , c_int as c_int, (((c_int+c_float)*10)+5) as y from (select * from cbo_t1 where cbo_t1.c_int >= 0) as cbo_t2 where cbo_t2.c_int >= 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t2.c_int+c_float as x , c_int as c_int, (((c_int+c_float)*10)+5) as y from (select * from cbo_t1 where cbo_t1.c_int >= 0) as cbo_t2 where cbo_t2.c_int >= 0 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_5] + predicate:(c_int >= 0) (type: boolean) + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select null from cbo_t3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select null from cbo_t3 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0"] + TableScan [TS_0] + alias:cbo_t3 +PREHOOK: query: explain select key from cbo_t1 where c_int = -6 or c_int = +6 +PREHOOK: type: QUERY +POSTHOOK: query: explain select key from cbo_t1 where c_int = -6 or c_int = +6 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_2] + outputColumnNames:["_col0"] + Filter Operator [FIL_5] + predicate:((c_int = -6) or (c_int = 6)) (type: boolean) + TableScan [TS_0] + alias:cbo_t1 +PREHOOK: query: explain select count(cbo_t1.dt) from cbo_t1 join cbo_t2 on cbo_t1.dt = cbo_t2.dt where cbo_t1.dt = '2014' +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(cbo_t1.dt) from cbo_t1 join cbo_t2 on cbo_t1.dt = cbo_t2.dt where cbo_t1.dt = '2014' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(_col0)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_10] + outputColumnNames:["_col0"] + Statistics:Num rows: 22 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | Statistics:Num rows: 22 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | sort order: + | Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Select Operator [SEL_2] + | Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + sort order: + Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + Statistics:Num rows: 20 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select cbo_t1.value from cbo_t1 join cbo_t2 on cbo_t1.key = cbo_t2.key where cbo_t1.dt = '10' and cbo_t1.c_boolean = true +PREHOOK: type: QUERY +POSTHOOK: query: explain select cbo_t1.value from cbo_t1 join cbo_t2 on cbo_t1.key = cbo_t2.key where cbo_t1.dt = '10' and cbo_t1.c_boolean = true +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:false + Statistics:Num rows: 19 Data size: 1496 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_10] + outputColumnNames:["_col0"] + Statistics:Num rows: 19 Data size: 1496 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col2"] + | Statistics:Num rows: 19 Data size: 1496 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_15] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] +PREHOOK: query: explain select * +from src_cbo b +where not exists + (select distinct a.key + from src_cbo a + where b.value = a.value and a.value > 'val_2' + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src_cbo b +where not exists + (select distinct a.key + from src_cbo a + where b.value = a.value and a.value > 'val_2' + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_16] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_18] + predicate:_col2 is null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 193 Data size: 51917 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_10] + outputColumnNames:["_col0"] + Statistics:Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_9] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_7] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:(value > 'val_2') (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * +from src_cbo b +group by key, value +having not exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src_cbo b +group by key, value +having not exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_17] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_16] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:_col3 is null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_21] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col3"] + | Statistics:Num rows: 8 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_10] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_20] + | predicate:(value > 'val_12') (type: boolean) + | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_8] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col1 (type: string), _col0 (type: string) + Map-reduce partition columns:_col1 (type: string), _col0 (type: string) + sort order:++ + Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_4] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: create view cv1 as +select * +from src_cbo b +where exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_9') +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@src_cbo +PREHOOK: Output: database:default +PREHOOK: Output: default@cv1 +POSTHOOK: query: create view cv1 as +select * +from src_cbo b +where exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_9') +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@src_cbo +POSTHOOK: Output: database:default +POSTHOOK: Output: default@cv1 +PREHOOK: query: explain select * from cv1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from cv1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col1 (type: string), _col0 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_18] + | predicate:(value is not null and key is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_8] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((value > 'val_9') and key is not null) (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * +from (select * + from src_cbo b + where exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_9') + ) a +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from (select * + from src_cbo b + where exists + (select a.key + from src_cbo a + where b.value = a.value and a.key = b.key and a.value > 'val_9') + ) a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col1 (type: string), _col0 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_18] + | predicate:(value is not null and key is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_8] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((value > 'val_9') and key is not null) (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * +from src_cbo +where src_cbo.key in (select key from src_cbo s1 where s1.key > '9') +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src_cbo +where src_cbo.key in (select key from src_cbo s1 where s1.key > '9') +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 168 Data size: 29904 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_19] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 168 Data size: 29904 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: string) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_17] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src_cbo + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_7] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_18] + predicate:(key > '9') (type: boolean) + Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:src_cbo + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * +from src_cbo b +where b.key in + (select distinct a.key + from src_cbo a + where b.value = a.value and a.key > '9' + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src_cbo b +where b.key in + (select distinct a.key + from src_cbo a + where b.value = a.value and a.key > '9' + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_24] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_14] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_22] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [GBY_12] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [GBY_9] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_7] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_23] + predicate:((key > '9') and value is not null) (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) +PREHOOK: type: QUERY +POSTHOOK: query: explain select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_28] + compressed:false + Statistics:Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_38] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: int)","0":"_col1 (type: int)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col1 (type: int) + | Map-reduce partition columns:_col1 (type: int) + | sort order:+ + | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col2 (type: int) + | Merge Join Operator [MERGEJOIN_37] + | | condition map:[{"":"Left Semi Join 0 to 1"}] + | | keys:{"1":"_col0 (type: int), _col1 (type: int)","0":"_col0 (type: int), _col3 (type: int)"} + | | outputColumnNames:["_col1","_col2"] + | | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_17] + | | key expressions:_col0 (type: int), _col3 (type: int) + | | Map-reduce partition columns:_col0 (type: int), _col3 (type: int) + | | sort order:++ + | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + | | value expressions:_col1 (type: int), _col2 (type: int) + | | Select Operator [SEL_2] + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + | | Filter Operator [FIL_34] + | | predicate:(((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) + | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + | | TableScan [TS_0] + | | alias:lineitem + | | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | key expressions:_col0 (type: int), _col1 (type: int) + | Map-reduce partition columns:_col0 (type: int), _col1 (type: int) + | sort order:++ + | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_15] + | keys:_col0 (type: int), _col1 (type: int) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_35] + | predicate:(((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) (type: boolean) + | Statistics:Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:lineitem + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_24] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | keys:KEY._col0 (type: int) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_10] + keys:_col0 (type: int) + outputColumnNames:["_col0"] + Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_8] + outputColumnNames:["_col0"] + Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_36] + predicate:l_partkey is not null (type: boolean) + Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_7] + alias:lineitem + Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select key, value, count(*) +from src_cbo b +where b.key in (select key from src_cbo where src_cbo.key > '8') +group by key, value +having count(*) in (select count(*) from src_cbo s1 where s1.key > '9' group by s1.key ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select key, value, count(*) +from src_cbo b +where b.key in (select key from src_cbo where src_cbo.key > '8') +group by key, value +having count(*) in (select count(*) from src_cbo s1 where s1.key > '9' group by s1.key ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_34] + compressed:false + Statistics:Num rows: 41 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_46] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: bigint)","0":"_col2 (type: bigint)"} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 41 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_29] + | key expressions:_col2 (type: bigint) + | Map-reduce partition columns:_col2 (type: bigint) + | sort order:+ + | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: string) + | Filter Operator [FIL_40] + | predicate:_col2 is not null (type: boolean) + | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_16] + | | aggregations:["count(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col2 (type: bigint) + | Group By Operator [GBY_14] + | aggregations:["count()"] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 84 Data size: 15624 Basic stats: COMPLETE Column stats: COMPLETE + | Merge Join Operator [MERGEJOIN_45] + | | condition map:[{"":"Left Semi Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 168 Data size: 29904 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_9] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_2] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | | Filter Operator [FIL_41] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | | TableScan [TS_0] + | | alias:b + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | keys:_col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 69 Data size: 6003 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_42] + | predicate:(key > '8') (type: boolean) + | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_31] + key expressions:_col0 (type: bigint) + Map-reduce partition columns:_col0 (type: bigint) + sort order:+ + Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_27] + keys:_col0 (type: bigint) + outputColumnNames:["_col0"] + Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_25] + outputColumnNames:["_col0"] + Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_43] + predicate:_col1 is not null (type: boolean) + Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_24] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_22] + aggregations:["count()"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_20] + outputColumnNames:["_col0"] + Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_44] + predicate:(key > '9') (type: boolean) + Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_18] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select p_mfgr, p_name, avg(p_size) +from part +group by p_mfgr, p_name +having p_name in + (select first_value(p_name) over(partition by p_mfgr order by p_size) from part) +PREHOOK: type: QUERY +POSTHOOK: query: explain select p_mfgr, p_name, avg(p_size) +from part +group by p_mfgr, p_name +having p_name in + (select first_value(p_name) over(partition by p_mfgr order by p_size) from part) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_24] + compressed:false + Statistics:Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_29] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 6 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col2 (type: double) + | Group By Operator [GBY_7] + | | aggregations:["avg(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col2 (type: struct) + | Group By Operator [GBY_5] + | aggregations:["avg(_col2)"] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_27] + | predicate:p_name is not null (type: boolean) + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:part + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_17] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_14] + outputColumnNames:["_col0"] + Statistics:Num rows: 13 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_28] + predicate:_wcol0 is not null (type: boolean) + Statistics:Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_13] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col1","name:":"windowingtablefunction","order by:":"_col2"}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_12] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col1 (type: string), _col2 (type: int) + Map-reduce partition columns:_col1 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_9] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * +from src_cbo +where src_cbo.key not in + ( select key from src_cbo s1 + where s1.key > '2' + ) order by key +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src_cbo +where src_cbo.key not in + ( select key from src_cbo s1 + where s1.key > '2' + ) order by key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_27] + compressed:false + Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_26] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_25] + key expressions:_col0 (type: string) + sort order:+ + Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: string) + Select Operator [SEL_24] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_30] + predicate:_col3 is null (type: boolean) + Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_35] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col3"] + | Statistics:Num rows: 605 Data size: 107690 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_15] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_33] + | predicate:(key > '2') (type: boolean) + | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_13] + | alias:src_cbo + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_20] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: string) + Merge Join Operator [MERGEJOIN_34] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | sort order: + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: string) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src_cbo + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_10] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Filter Operator [FIL_31] + predicate:(_col0 = 0) (type: boolean) + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_9] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + sort order: + Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_7] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_32] + predicate:((key > '2') and key is null) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_3] + alias:src_cbo + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select p_mfgr, b.p_name, p_size +from part b +where b.p_name not in + (select p_name + from (select p_mfgr, p_name, p_size as r from part) a + where r < 10 and b.p_mfgr = a.p_mfgr + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select p_mfgr, b.p_name, p_size +from part b +where b.p_name not in + (select p_name + from (select p_mfgr, p_name, p_size as r from part) a + where r < 10 and b.p_mfgr = a.p_mfgr + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_29] + compressed:false + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_27] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_32] + predicate:_col4 is null (type: boolean) + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_37] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 30 Data size: 7014 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_24] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_16] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_35] + | predicate:(p_size < 10) (type: boolean) + | Statistics:Num rows: 8 Data size: 1784 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_14] + | alias:b + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: int) + Merge Join Operator [MERGEJOIN_36] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | sort order: + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + sort order: + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Filter Operator [FIL_33] + predicate:(_col0 = 0) (type: boolean) + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_10] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + sort order: + Statistics:Num rows: 1 Data size: 231 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_8] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 231 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_34] + predicate:((p_size < 10) and (p_name is null or p_mfgr is null)) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select p_name, p_size +from +part where part.p_size not in + (select avg(p_size) + from (select p_size from part) a + where p_size < 10 + ) order by p_name +PREHOOK: type: QUERY +POSTHOOK: query: explain select p_name, p_size +from +part where part.p_size not in + (select avg(p_size) + from (select p_size from part) a + where p_size < 10 + ) order by p_name +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_39] + compressed:false + Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_38] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: string) + sort order:+ + Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int) + Merge Join Operator [MERGEJOIN_49] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 6 Data size: 825 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_31] + | sort order: + | Statistics:Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int) + | Filter Operator [FIL_42] + | predicate:_col2 is null (type: boolean) + | Statistics:Num rows: 6 Data size: 750 Basic stats: COMPLETE Column stats: COMPLETE + | Merge Join Operator [MERGEJOIN_48] + | | condition map:[{"":"Left Outer Join0 to 1"}] + | | keys:{"1":"_col0 (type: double)","0":"UDFToDouble(_col1) (type: double)"} + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_28] + | | key expressions:UDFToDouble(_col1) (type: double) + | | Map-reduce partition columns:UDFToDouble(_col1) (type: double) + | | sort order:+ + | | Statistics:Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE + | | value expressions:_col0 (type: string), _col1 (type: int) + | | Select Operator [SEL_2] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE + | | TableScan [TS_0] + | | alias:part + | | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_29] + | key expressions:_col0 (type: double) + | Map-reduce partition columns:_col0 (type: double) + | sort order:+ + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_9] + | | aggregations:["avg(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_8] + | sort order: + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | value expressions:_col0 (type: struct) + | Group By Operator [GBY_7] + | aggregations:["avg(_col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_44] + | predicate:(p_size < 10) (type: boolean) + | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:part + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + sort order: + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_24] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_45] + predicate:(_col0 = 0) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_23] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_18] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_46] + predicate:_col0 is null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_17] + | aggregations:["avg(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col0 (type: struct) + Group By Operator [GBY_15] + aggregations:["avg(_col0)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0"] + Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_47] + predicate:(p_size < 10) (type: boolean) + Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_11] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select p_mfgr, p_name, p_size +from part b where b.p_size not in + (select min(p_size) + from (select p_mfgr, p_size from part) a + where p_size < 10 and b.p_mfgr = a.p_mfgr + ) order by p_name +PREHOOK: type: QUERY +POSTHOOK: query: explain select p_mfgr, p_name, p_size +from part b where b.p_size not in + (select min(p_size) + from (select p_mfgr, p_size from part) a + where p_size < 10 and b.p_mfgr = a.p_mfgr + ) order by p_name +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_39] + compressed:false + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_38] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col1 (type: string) + sort order:+ + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col2 (type: int) + Select Operator [SEL_35] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_42] + predicate:_col4 is null (type: boolean) + Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_49] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: int), _col1 (type: string)","0":"_col2 (type: int), _col1 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 30 Data size: 7014 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_31] + | key expressions:_col2 (type: int), _col1 (type: string) + | Map-reduce partition columns:_col2 (type: int), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string) + | Merge Join Operator [MERGEJOIN_48] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{} + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE + | |<-Map 1 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_28] + | | sort order: + | | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + | | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) + | | Select Operator [SEL_2] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + | | TableScan [TS_0] + | | alias:b + | | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_29] + | sort order: + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Select Operator [SEL_16] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Filter Operator [FIL_43] + | predicate:(_col0 = 0) (type: boolean) + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_15] + | | aggregations:["count(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_14] + | sort order: + | Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: bigint) + | Group By Operator [GBY_13] + | aggregations:["count()"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_11] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_44] + | predicate:(_col1 is null or _col0 is null) (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_9] + | | aggregations:["min(VALUE._col0)"] + | | keys:KEY._col0 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Group By Operator [GBY_7] + | aggregations:["min(_col1)"] + | keys:_col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_45] + | predicate:(p_size < 10) (type: boolean) + | Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:b + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: int), _col1 (type: string) + Map-reduce partition columns:_col0 (type: int), _col1 (type: string) + sort order:++ + Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_25] + | aggregations:["min(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_24] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Group By Operator [GBY_23] + aggregations:["min(_col1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_47] + predicate:(p_size < 10) (type: boolean) + Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_19] + alias:b + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select li.l_partkey, count(*) +from lineitem li +where li.l_linenumber = 1 and + li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR') +group by li.l_partkey +PREHOOK: type: QUERY +POSTHOOK: query: explain select li.l_partkey, count(*) +from lineitem li +where li.l_linenumber = 1 and + li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR') +group by li.l_partkey +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_32] + compressed:false + Statistics:Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_30] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 9 Data size: 77 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_28] + aggregations:["count()"] + keys:_col0 (type: int) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 9 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_26] + outputColumnNames:["_col0"] + Statistics:Num rows: 9 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_35] + predicate:_col4 is null (type: boolean) + Statistics:Num rows: 9 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_41] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: int)","0":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col4"] + | Statistics:Num rows: 18 Data size: 154 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_23] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_16] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_39] + | predicate:(l_shipmode = 'AIR') (type: boolean) + | Statistics:Num rows: 14 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_14] + | alias:li + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_22] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 17 Data size: 140 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int) + Merge Join Operator [MERGEJOIN_40] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 17 Data size: 140 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | sort order: + | Statistics:Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: int), _col1 (type: int) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_36] + | predicate:(l_linenumber = 1) (type: boolean) + | Statistics:Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:li + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_20] + sort order: + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Filter Operator [FIL_37] + predicate:(_col0 = 0) (type: boolean) + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_10] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + sort order: + Statistics:Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_8] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_38] + predicate:((l_shipmode = 'AIR') and l_orderkey is null) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + TableScan [TS_3] + alias:li + Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) + order by b.p_mfgr +PREHOOK: type: QUERY +POSTHOOK: query: explain select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) + order by b.p_mfgr +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 10 <- Map 9 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 + File Output Operator [FS_42] + compressed:false + Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_41] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_40] + key expressions:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: double) + Select Operator [SEL_39] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_45] + predicate:_col3 is null (type: boolean) + Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_51] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: double)","0":"_col0 (type: string), _col1 (type: double)"} + | outputColumnNames:["_col0","_col1","_col3"] + | Statistics:Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_36] + | key expressions:_col0 (type: string), _col1 (type: double) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: double) + | sort order:++ + | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_30] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_48] + | predicate:((_col2 - _col1) > 600.0) (type: boolean) + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_28] + | | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] + | | keys:KEY._col0 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: double), _col2 (type: double) + | Group By Operator [GBY_26] + | aggregations:["min(_col1)","max(_col1)"] + | keys:_col0 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_24] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_23] + | alias:b + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_35] + key expressions:_col0 (type: string), _col1 (type: double) + Map-reduce partition columns:_col0 (type: string), _col1 (type: double) + sort order:++ + Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_50] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_32] + | sort order: + | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: double) + | Group By Operator [GBY_6] + | | aggregations:["min(VALUE._col0)"] + | | keys:KEY._col0 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: double) + | Group By Operator [GBY_4] + | aggregations:["min(_col1)"] + | keys:_col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_33] + sort order: + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_20] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Filter Operator [FIL_46] + predicate:(_col0 = 0) (type: boolean) + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_19] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_17] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Filter Operator [FIL_47] + predicate:((_col0 is null or _col2 is null) and ((_col1 - _col2) > 600.0)) (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_13] + | aggregations:["max(VALUE._col0)","min(VALUE._col1)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: double), _col2 (type: double) + Group By Operator [GBY_11] + aggregations:["max(_col1)","min(_col1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_8] + alias:b + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select count(*), count(c_int), sum(c_int), avg(c_int), max(c_int), min(c_int) from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*), count(c_int), sum(c_int), avg(c_int), max(c_int), min(c_int) from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","avg(VALUE._col3)","max(VALUE._col4)","min(VALUE._col5)"] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: struct), _col4 (type: int), _col5 (type: int) + Group By Operator [GBY_3] + aggregations:["count()","count(_col0)","sum(_col0)","avg(_col0)","max(_col0)","min(_col0)"] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select count(*), count(c_int), sum(c_int), avg(c_int), max(c_int), min(c_int), case c_int when 0 then 1 when 1 then 2 else 3 end, sum(case c_int when 0 then 1 when 1 then 2 else 3 end) from cbo_t1 group by c_int +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*), count(c_int), sum(c_int), avg(c_int), max(c_int), min(c_int), case c_int when 0 then 1 when 1 then 2 else 3 end, sum(case c_int when 0 then 1 when 1 then 2 else 3 end) from cbo_t1 group by c_int +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Statistics:Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","avg(VALUE._col3)","max(VALUE._col4)","min(VALUE._col5)","sum(VALUE._col6)"] + | keys:KEY._col0 (type: int) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + | Statistics:Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 2 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: struct), _col5 (type: int), _col6 (type: int), _col7 (type: bigint) + Group By Operator [GBY_4] + aggregations:["count()","count(_col0)","sum(_col0)","avg(_col0)","max(_col0)","min(_col0)","sum(_col1)"] + keys:_col0 (type: int) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Statistics:Num rows: 2 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select count(*) as a, count(distinct c_int) as b, sum(c_int) as c, avg(c_int) as d, max(c_int) as e, min(c_int) as f from cbo_t1) cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select count(*) as a, count(distinct c_int) as b, sum(c_int) as c, avg(c_int) as d, max(c_int) as e, min(c_int) as f from cbo_t1) cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["count(VALUE._col0)","count(DISTINCT KEY._col0:0._col0)","sum(VALUE._col2)","avg(VALUE._col3)","max(VALUE._col4)","min(VALUE._col5)"] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint), _col3 (type: bigint), _col4 (type: struct), _col5 (type: int), _col6 (type: int) + Group By Operator [GBY_3] + aggregations:["count()","count(DISTINCT _col0)","sum(_col0)","avg(_col0)","max(_col0)","min(_col0)"] + keys:_col0 (type: int) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Statistics:Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select f,a,e,b from (select count(*) as a, count(c_int) as b, sum(c_int) as c, avg(c_int) as d, max(c_int) as e, min(c_int) as f from cbo_t1) cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select f,a,e,b from (select count(*) as a, count(c_int) as b, sum(c_int) as c, avg(c_int) as d, max(c_int) as e, min(c_int) as f from cbo_t1) cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["min(VALUE._col0)","count(VALUE._col1)","max(VALUE._col2)","count(VALUE._col3)"] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: bigint), _col2 (type: int), _col3 (type: bigint) + Group By Operator [GBY_3] + aggregations:["min(_col0)","count()","max(_col0)","count(_col0)"] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select count(c_int) as a, avg(c_float), key from cbo_t1 group by key +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(c_int) as a, avg(c_float), key from cbo_t1 group by key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 5 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + | aggregations:["count(VALUE._col0)","avg(VALUE._col1)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 5 Data size: 420 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint), _col2 (type: struct) + Group By Operator [GBY_3] + aggregations:["count(_col1)","avg(_col2)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 5 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select count(distinct c_int) as a, avg(c_float) from cbo_t1 group by c_float +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(distinct c_int) as a, avg(c_float) from cbo_t1 group by c_float +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_6] + | aggregations:["count(DISTINCT KEY._col1:0._col0)","avg(VALUE._col1)"] + | keys:KEY._col0 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: float), _col1 (type: int) + Map-reduce partition columns:_col0 (type: float) + sort order:++ + Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: struct) + Group By Operator [GBY_4] + aggregations:["count(DISTINCT _col1)","avg(_col0)"] + keys:_col0 (type: float), _col1 (type: int) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select count(c_int) over() from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(c_int) over() from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:0 (type: int) + Map-reduce partition columns:0 (type: int) + sort order:+ + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int) + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] + Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:0 (type: int) + Map-reduce partition columns:0 (type: int) + sort order:+ + Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: float) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1) cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select count(c_int) over(), sum(c_float) over(), max(c_int) over(), min(c_int) over(), row_number() over(), rank() over(), dense_rank() over(), percent_rank() over(), lead(c_int, 2, c_int) over(), lag(c_float, 2, c_float) over() from cbo_t1) cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Statistics:Num rows: 20 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] + Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:0 (type: int) + Map-reduce partition columns:0 (type: int) + sort order:+ + Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: float) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 20 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select x from (select count(c_int) over() as x, sum(c_float) over() from cbo_t1) cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select x from (select count(c_int) over() as x, sum(c_float) over() from cbo_t1) cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:0 (type: int) + Map-reduce partition columns:0 (type: int) + sort order:+ + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int) + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select 1+sum(c_int) over() from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select 1+sum(c_int) over() from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:0 (type: int) + Map-reduce partition columns:0 (type: int) + sort order:+ + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int) + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select sum(c_int)+sum(sum(c_int)) over() from cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(c_int)+sum(sum(c_int)) over() from cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_12] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_8] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"0","name:":"windowingtablefunction","order by:":"0"}] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:0 (type: int) + Map-reduce partition columns:0 (type: int) + sort order:+ + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_3] + aggregations:["sum(_col0)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from (select max(c_int) over (partition by key order by value Rows UNBOUNDED PRECEDING), min(c_int) over (partition by key order by value rows current row), count(c_int) over(partition by key order by value ROWS 1 PRECEDING), avg(value) over (partition by key order by value Rows between unbounded preceding and unbounded following), sum(value) over (partition by key order by value rows between unbounded preceding and current row), avg(c_float) over (partition by key order by value Rows between 1 preceding and unbounded following), sum(c_float) over (partition by key order by value rows between 1 preceding and current row), max(c_float) over (partition by key order by value rows between 1 preceding and unbounded following), min(c_float) over (partition by key order by value rows between 1 preceding and 1 following) from cbo_t1) cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from (select max(c_int) over (partition by key order by value Rows UNBOUNDED PRECEDING), min(c_int) over (partition by key order by value rows current row), count(c_int) over(partition by key order by value ROWS 1 PRECEDING), avg(value) over (partition by key order by value Rows between unbounded preceding and unbounded following), sum(value) over (partition by key order by value rows between unbounded preceding and current row), avg(c_float) over (partition by key order by value Rows between 1 preceding and unbounded following), sum(c_float) over (partition by key order by value rows between 1 preceding and current row), max(c_float) over (partition by key order by value rows between 1 preceding and unbounded following), min(c_float) over (partition by key order by value rows between 1 preceding and 1 following) from cbo_t1) cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 20 Data size: 1120 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Statistics:Num rows: 20 Data size: 1120 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:++ + Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: int), _col3 (type: float) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select i, a, h, b, c, d, e, f, g, a as x, a +1 as y from (select max(c_int) over (partition by key order by value range UNBOUNDED PRECEDING) a, min(c_int) over (partition by key order by value range current row) b, count(c_int) over(partition by key order by value range 1 PRECEDING) c, avg(value) over (partition by key order by value range between unbounded preceding and unbounded following) d, sum(value) over (partition by key order by value range between unbounded preceding and current row) e, avg(c_float) over (partition by key order by value range between 1 preceding and unbounded following) f, sum(c_float) over (partition by key order by value range between 1 preceding and current row) g, max(c_float) over (partition by key order by value range between 1 preceding and unbounded following) h, min(c_float) over (partition by key order by value range between 1 preceding and 1 following) i from cbo_t1) cbo_t1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select i, a, h, b, c, d, e, f, g, a as x, a +1 as y from (select max(c_int) over (partition by key order by value range UNBOUNDED PRECEDING) a, min(c_int) over (partition by key order by value range current row) b, count(c_int) over(partition by key order by value range 1 PRECEDING) c, avg(value) over (partition by key order by value range between unbounded preceding and unbounded following) d, sum(value) over (partition by key order by value range between unbounded preceding and current row) e, avg(c_float) over (partition by key order by value range between 1 preceding and unbounded following) f, sum(c_float) over (partition by key order by value range between 1 preceding and current row) g, max(c_float) over (partition by key order by value range between 1 preceding and unbounded following) h, min(c_float) over (partition by key order by value range between 1 preceding and 1 following) i from cbo_t1) cbo_t1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 20 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] + Statistics:Num rows: 20 Data size: 1280 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:++ + Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: int), _col3 (type: float) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 20 Data size: 3204 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:cbo_t1 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select *, rank() over(partition by key order by value) as rr from src1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select *, rank() over(partition by key order by value) as rr from src1 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 25 Data size: 4475 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 25 Data size: 4475 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:++ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src1 + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:key is not null (type: boolean) + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:key is not null (type: boolean) + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator [MAPJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"_col0 (type: string)","Map 4":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_3] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_25] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_2] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + |<-Select Operator [SEL_1] + outputColumnNames:["_col0"] + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_24] + predicate:key is not null (type: boolean) + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:y + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_22] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_20] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_18] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_16] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_15] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_13] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_27] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_25] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_26] + predicate:key is not null (type: boolean) + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:y + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_22] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_20] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_18] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_16] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_15] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_13] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_27] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_25] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + keys:_col0 (type: string) + outputColumnNames:["_col0"] + Statistics:Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_26] + predicate:key is not null (type: boolean) + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:y + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select x.key, y.value, count(1) AS cnt +FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value) +GROUP BY x.key, y.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +select x.key, y.value, count(1) AS cnt +FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value) +GROUP BY x.key, y.value +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select x.key, y.value, count(1) AS cnt +FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value) +GROUP BY x.key, y.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +select x.key, y.value, count(1) AS cnt +FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key AND x.value = y.value) +GROUP BY x.key, y.value +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select y.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY y.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x FULL OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x FULL OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x FULL OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x FULL OUTER JOIN src y ON (x.key = y.key) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_19] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_15] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_12] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_10] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_7] + outputColumnNames:["_col0"] + Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.value)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, x.value AS value, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key, x.value) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.value)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, x.value AS value, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key, x.value) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)","sum(_col2)"] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: string) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:key is not null (type: boolean) + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.value)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, x.value AS value, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key, x.value) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.value)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, x.value AS value, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key) + GROUP BY x.key, x.value) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)","sum(_col2)"] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 30 Data size: 5490 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: string) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:key is not null (type: boolean) + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key AND x.value = y.value) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key AND x.value = y.value) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:(key is not null and value is not null) (type: boolean) + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key AND x.value = y.value) + GROUP BY x.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain +select SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (select x.key AS key, count(1) AS cnt + FROM src1 x JOIN src y ON (x.key = y.key AND x.value = y.value) + GROUP BY x.key) tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_21] + compressed:false + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_19] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [GBY_17] + aggregations:["sum(_col0)","sum(_col1)"] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator [GBY_14] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + value expressions:_col1 (type: bigint) + Group By Operator [GBY_12] + aggregations:["count(1)"] + keys:_col0 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col2"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:(key is not null and value is not null) (type: boolean) + Statistics:Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain create table abcd (a int, b int, c int, d int) +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table abcd (a int, b int, c int, d int) +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + columns:["a int","b int","c int","d int"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.abcd + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +PREHOOK: query: create table abcd (a int, b int, c int, d int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@abcd +POSTHOOK: query: create table abcd (a int, b int, c int, d int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@abcd +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@abcd +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@abcd +PREHOOK: query: explain select * from abcd +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from abcd +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3"] + TableScan [TS_0] + alias:abcd +PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a +PREHOOK: type: QUERY +POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col2)"] + | keys:KEY._col0 (type: int) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+++ + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + value expressions:_col5 (type: bigint) + Group By Operator [GBY_3] + aggregations:["count(DISTINCT _col1)","count(DISTINCT _col2)","sum(_col3)"] + keys:_col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:abcd + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_6] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)","count(VALUE._col3)","count(VALUE._col4)","count(VALUE._col5)","count(DISTINCT KEY._col0:0._col0)","count(DISTINCT KEY._col0:1._col0)","count(DISTINCT KEY._col0:2._col0)","count(DISTINCT KEY._col0:3._col0)","count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1)","count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1)","count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1)","count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1)","count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1)","count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1)","count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2)","count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2)","count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2)","count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2)","count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3)"] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] + | Statistics:Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) + sort order:++++ + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + Group By Operator [GBY_4] + aggregations:["count(1)","count()","count(_col1)","count(_col2)","count(_col3)","count(_col4)","count(DISTINCT _col1)","count(DISTINCT _col2)","count(DISTINCT _col3)","count(DISTINCT _col4)","count(DISTINCT _col1, _col2)","count(DISTINCT _col2, _col3)","count(DISTINCT _col3, _col4)","count(DISTINCT _col1, _col4)","count(DISTINCT _col1, _col3)","count(DISTINCT _col2, _col4)","count(DISTINCT _col1, _col2, _col3)","count(DISTINCT _col2, _col3, _col4)","count(DISTINCT _col1, _col3, _col4)","count(DISTINCT _col1, _col2, _col4)","count(DISTINCT _col1, _col2, _col3, _col4)"] + keys:_col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24"] + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_1] + outputColumnNames:["_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:abcd + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a +PREHOOK: type: QUERY +POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:false + Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_4] + | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col0)"] + | keys:KEY._col0 (type: int) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+++ + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: int) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:abcd + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:false + Statistics:Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["count(1)","count()","count(KEY._col0:0._col0)","count(KEY._col0:1._col0)","count(KEY._col0:2._col0)","count(KEY._col0:3._col0)","count(DISTINCT KEY._col0:0._col0)","count(DISTINCT KEY._col0:1._col0)","count(DISTINCT KEY._col0:2._col0)","count(DISTINCT KEY._col0:3._col0)","count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1)","count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1)","count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1)","count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1)","count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1)","count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1)","count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2)","count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2)","count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2)","count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2)","count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3)"] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] + | Statistics:Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + sort order:++++ + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_1] + outputColumnNames:["_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:abcd + Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain create table src_rc_merge_test(key int, value string) stored as rcfile +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table src_rc_merge_test(key int, value string) stored as rcfile +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + columns:["key int","value string"] + input format:org.apache.hadoop.hive.ql.io.RCFileInputFormat + name:default.src_rc_merge_test + output format:org.apache.hadoop.hive.ql.io.RCFileOutputFormat +PREHOOK: query: create table src_rc_merge_test(key int, value string) stored as rcfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src_rc_merge_test +POSTHOOK: query: create table src_rc_merge_test(key int, value string) stored as rcfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_rc_merge_test +PREHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@src_rc_merge_test +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@src_rc_merge_test +PREHOOK: query: explain create table tgt_rc_merge_test(key int, value string) stored as rcfile +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table tgt_rc_merge_test(key int, value string) stored as rcfile +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + columns:["key int","value string"] + input format:org.apache.hadoop.hive.ql.io.RCFileInputFormat + name:default.tgt_rc_merge_test + output format:org.apache.hadoop.hive.ql.io.RCFileOutputFormat +PREHOOK: query: create table tgt_rc_merge_test(key int, value string) stored as rcfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: query: create table tgt_rc_merge_test(key int, value string) stored as rcfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tgt_rc_merge_test +PREHOOK: query: explain insert into table tgt_rc_merge_test select * from src_rc_merge_test +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table tgt_rc_merge_test select * from src_rc_merge_test +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe","name:":"default.tgt_rc_merge_test","input format:":"org.apache.hadoop.hive.ql.io.RCFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.RCFileOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Map 1 + File Output Operator [FS_2] + compressed:true + Statistics:Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe","name:":"default.tgt_rc_merge_test","input format:":"org.apache.hadoop.hive.ql.io.RCFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.RCFileOutputFormat"} + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src_rc_merge_test + Statistics:Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test +PREHOOK: type: QUERY +PREHOOK: Input: default@src_rc_merge_test +PREHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_rc_merge_test +POSTHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: Lineage: tgt_rc_merge_test.key SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tgt_rc_merge_test.value SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain insert into table tgt_rc_merge_test select * from src_rc_merge_test +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table tgt_rc_merge_test select * from src_rc_merge_test +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe","name:":"default.tgt_rc_merge_test","input format:":"org.apache.hadoop.hive.ql.io.RCFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.RCFileOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Map 1 + File Output Operator [FS_2] + compressed:true + Statistics:Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe","name:":"default.tgt_rc_merge_test","input format:":"org.apache.hadoop.hive.ql.io.RCFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.RCFileOutputFormat"} + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:src_rc_merge_test + Statistics:Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test +PREHOOK: type: QUERY +PREHOOK: Input: default@src_rc_merge_test +PREHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_rc_merge_test +POSTHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: Lineage: tgt_rc_merge_test.key SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tgt_rc_merge_test.value SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: show table extended like `tgt_rc_merge_test` +PREHOOK: type: SHOW_TABLESTATUS +POSTHOOK: query: show table extended like `tgt_rc_merge_test` +POSTHOOK: type: SHOW_TABLESTATUS +tableName:tgt_rc_merge_test +#### A masked pattern was here #### +inputformat:org.apache.hadoop.hive.ql.io.RCFileInputFormat +outputformat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat +columns:struct columns { i32 key, string value} +partitioned:false +partitionColumns: +totalNumberFiles:2 +totalFileSize:342 +maxFileSize:171 +minFileSize:171 +#### A masked pattern was here #### + +PREHOOK: query: explain select count(1) from tgt_rc_merge_test +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from tgt_rc_merge_test +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["count(1)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 10 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + Statistics:Num rows: 10 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:tgt_rc_merge_test + Statistics:Num rows: 10 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:true + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 10 Data size: 64 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col1 (type: int) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 64 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:tgt_rc_merge_test + Statistics:Num rows: 10 Data size: 64 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: alter table tgt_rc_merge_test concatenate +PREHOOK: type: ALTER_TABLE_MERGE +PREHOOK: Input: default@tgt_rc_merge_test +PREHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: query: alter table tgt_rc_merge_test concatenate +POSTHOOK: type: ALTER_TABLE_MERGE +POSTHOOK: Input: default@tgt_rc_merge_test +POSTHOOK: Output: default@tgt_rc_merge_test +PREHOOK: query: show table extended like `tgt_rc_merge_test` +PREHOOK: type: SHOW_TABLESTATUS +POSTHOOK: query: show table extended like `tgt_rc_merge_test` +POSTHOOK: type: SHOW_TABLESTATUS +tableName:tgt_rc_merge_test +#### A masked pattern was here #### +inputformat:org.apache.hadoop.hive.ql.io.RCFileInputFormat +outputformat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat +columns:struct columns { i32 key, string value} +partitioned:false +partitionColumns: +totalNumberFiles:1 +totalFileSize:243 +maxFileSize:243 +minFileSize:243 +#### A masked pattern was here #### + +PREHOOK: query: explain select count(1) from tgt_rc_merge_test +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from tgt_rc_merge_test +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["count(1)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 0 Data size: 243 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_1] + Statistics:Num rows: 0 Data size: 243 Basic stats: PARTIAL Column stats: COMPLETE + TableScan [TS_0] + alias:tgt_rc_merge_test + Statistics:Num rows: 0 Data size: 243 Basic stats: PARTIAL Column stats: COMPLETE +PREHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_7] + compressed:true + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + sort order: + Statistics:Num rows: 2 Data size: 243 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col1 (type: int) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 2 Data size: 243 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:tgt_rc_merge_test + Statistics:Num rows: 2 Data size: 243 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: drop table src_rc_merge_test +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@src_rc_merge_test +PREHOOK: Output: default@src_rc_merge_test +POSTHOOK: query: drop table src_rc_merge_test +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@src_rc_merge_test +POSTHOOK: Output: default@src_rc_merge_test +PREHOOK: query: drop table tgt_rc_merge_test +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@tgt_rc_merge_test +PREHOOK: Output: default@tgt_rc_merge_test +POSTHOOK: query: drop table tgt_rc_merge_test +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@tgt_rc_merge_test +POSTHOOK: Output: default@tgt_rc_merge_test +PREHOOK: query: explain select src.key from src join src src2 +PREHOOK: type: QUERY +POSTHOOK: query: explain select src.key from src join src src2 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_11] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | sort order: + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_3] + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + TableScan [TS_2] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select src.key from src cross join src src2 +PREHOOK: type: QUERY +POSTHOOK: query: explain select src.key from src cross join src src2 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_11] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | sort order: + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_3] + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + TableScan [TS_2] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select src.key from src cross join src src2 on src.key=src2.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select src.key from src cross join src src2 on src.key=src2.key +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_10] + compressed:true + Statistics:Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_15] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_13] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_14] + predicate:key is not null (type: boolean) + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: create table A as +select * from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@A +POSTHOOK: query: create table A as +select * from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@A +PREHOOK: query: create table B as +select * from src +limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@B +POSTHOOK: query: create table B as +select * from src +limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@B +PREHOOK: query: explain select * from A join B +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from A join B +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_11] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | sort order: + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col1 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + sort order: + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col1 (type: string) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:b + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 5 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | sort order: + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | value expressions:key (type: string), value (type: string) + | TableScan [TS_2] + | alias:a + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + sort order: + Statistics:Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: string)","0":"key (type: string)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: string) + | Filter Operator [FIL_15] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:d1 + | Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:key (type: string) + Map-reduce partition columns:key (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: string) + Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_1] + alias:d2 + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from A join + (select d1.key + from B d1 join B d2 on d1.key = d2.key + where 1 = 1 group by d1.key) od1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from A join + (select d1.key + from B d1 join B d2 on d1.key = d2.key + where 1 = 1 group by d1.key) od1 +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_17] + compressed:true + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_16] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_23] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col5"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | sort order: + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | value expressions:key (type: string), value (type: string) + | TableScan [TS_12] + | alias:a + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + sort order: + Statistics:Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string) + Group By Operator [GBY_10] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_22] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: string)","0":"key (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_20] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:d1 + | Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:key (type: string) + Map-reduce partition columns:key (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_21] + predicate:key is not null (type: boolean) + Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_1] + alias:d2 + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_15] + compressed:true + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_14] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col5"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_11] + | sort order: + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | value expressions:key (type: string), value (type: string) + | TableScan [TS_10] + | alias:a + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + sort order: + Statistics:Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string) + Group By Operator [GBY_8] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_16] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | sort order: + | Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + | value expressions:key (type: string) + | TableScan [TS_0] + | alias:d1 + | Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + sort order: + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_1] + alias:d2 + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from +(select A.key from A group by key) ss join +(select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from +(select A.key from A group by key) ss join +(select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_21] + compressed:true + Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_27] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | sort order: + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string) + | Group By Operator [GBY_3] + | | keys:KEY._col0 (type: string) + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_1] + | outputColumnNames:["key"] + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + sort order: + Statistics:Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string) + Group By Operator [GBY_15] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_26] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: string)","0":"key (type: string)"} + | outputColumnNames:["_col0"] + | Statistics:Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_24] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_5] + | alias:d1 + | Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:key (type: string) + Map-reduce partition columns:key (type: string) + sort order:+ + Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_25] + predicate:key is not null (type: boolean) + Statistics:Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_6] + alias:d2 + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain create table nzhang_Tmp(a int, b string) +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table nzhang_Tmp(a int, b string) +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + columns:["a int","b string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_Tmp + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +PREHOOK: query: create table nzhang_Tmp(a int, b string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_Tmp +POSTHOOK: query: create table nzhang_Tmp(a int, b string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_Tmp +PREHOOK: query: explain select * from nzhang_Tmp +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from nzhang_Tmp +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + TableScan [TS_0] + alias:nzhang_tmp +PREHOOK: query: explain create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-4 + Create Table Operator: + columns:["k string","value string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_CTAS1 + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_CTAS1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_7] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Stage-0 + Move Operator + Please refer to the previous Stage-1 +PREHOOK: query: create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_CTAS1 +POSTHOOK: query: create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_CTAS1 +PREHOOK: query: explain select * from nzhang_CTAS1 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from nzhang_CTAS1 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + TableScan [TS_0] + alias:nzhang_ctas1 +PREHOOK: query: describe formatted nzhang_CTAS1 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@nzhang_ctas1 +POSTHOOK: query: describe formatted nzhang_CTAS1 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@nzhang_ctas1 +# col_name data_type comment + +k string +value string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 10 + rawDataSize 96 + totalSize 39 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: explain create table nzhang_ctas2 as select * from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain create table nzhang_ctas2 as select * from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-4 + Create Table Operator: + columns:["key string","value string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_ctas2 + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_ctas2","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_7] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Stage-0 + Move Operator + Please refer to the previous Stage-1 +PREHOOK: query: create table nzhang_ctas2 as select * from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_ctas2 +POSTHOOK: query: create table nzhang_ctas2 as select * from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_ctas2 +PREHOOK: query: explain select * from nzhang_ctas2 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from nzhang_ctas2 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + TableScan [TS_0] + alias:nzhang_ctas2 +PREHOOK: query: describe formatted nzhang_CTAS2 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@nzhang_ctas2 +POSTHOOK: query: describe formatted nzhang_CTAS2 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@nzhang_ctas2 +# col_name data_type comment + +key string +value string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 10 + rawDataSize 96 + totalSize 39 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: explain create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-4 + Create Table Operator: + columns:["half_key double","conb string"] + input format:org.apache.hadoop.hive.ql.io.RCFileInputFormat + name:default.nzhang_ctas3 + output format:org.apache.hadoop.hive.ql.io.RCFileOutputFormat + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe","name:":"default.nzhang_ctas3","input format:":"org.apache.hadoop.hive.ql.io.RCFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.RCFileOutputFormat"} + Limit [LIM_7] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: double), _col1 (type: string) + sort order:++ + Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: double), _col1 (type: string) + sort order:++ + Statistics:Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Stage-0 + Move Operator + Please refer to the previous Stage-1 +PREHOOK: query: create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_ctas3 +POSTHOOK: query: create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_ctas3 +PREHOOK: query: explain select * from nzhang_ctas3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from nzhang_ctas3 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + TableScan [TS_0] + alias:nzhang_ctas3 +PREHOOK: query: describe formatted nzhang_CTAS3 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@nzhang_ctas3 +POSTHOOK: query: describe formatted nzhang_CTAS3 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@nzhang_ctas3 +# col_name data_type comment + +half_key double +conb string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 10 + rawDataSize 120 + totalSize 191 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: explain create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 +POSTHOOK: type: CREATETABLE +PREHOOK: query: create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table if not exists nzhang_ctas3 as select key, value from src sort by key, value limit 2 +POSTHOOK: type: CREATETABLE +PREHOOK: query: explain select * from nzhang_ctas3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from nzhang_ctas3 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + TableScan [TS_0] + alias:nzhang_ctas3 +PREHOOK: query: describe formatted nzhang_CTAS3 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@nzhang_ctas3 +POSTHOOK: query: describe formatted nzhang_CTAS3 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@nzhang_ctas3 +# col_name data_type comment + +half_key double +conb string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 10 + rawDataSize 120 + totalSize 191 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: explain create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-4 + Create Table Operator: + columns:["key string","value string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_ctas4 + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_ctas4","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_7] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Stage-0 + Move Operator + Please refer to the previous Stage-1 +PREHOOK: query: create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_ctas4 +POSTHOOK: query: create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_ctas4 +PREHOOK: query: explain select * from nzhang_ctas4 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from nzhang_ctas4 +POSTHOOK: type: QUERY +CBO Succeeded + +Stage-0 + Fetch Operator + limit:-1 + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + TableScan [TS_0] + alias:nzhang_ctas4 +PREHOOK: query: describe formatted nzhang_CTAS4 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@nzhang_ctas4 +POSTHOOK: query: describe formatted nzhang_CTAS4 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@nzhang_ctas4 +# col_name data_type comment + +key string +value string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Protect Mode: None +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 10 + rawDataSize 96 + totalSize 39 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + field.delim , + serialization.format , +PREHOOK: query: explain extended create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain extended create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +ABSTRACT SYNTAX TREE: + +TOK_CREATETABLE + TOK_TABNAME + nzhang_ctas5 + TOK_LIKETABLE + TOK_TABLEROWFORMAT + TOK_SERDEPROPS + TOK_TABLEROWFORMATFIELD + ',' + TOK_TABLEROWFORMATLINES + '\012' + TOK_FILEFORMAT_GENERIC + textfile + TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + src + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + key + TOK_SELEXPR + TOK_TABLE_OR_COL + value + TOK_SORTBY + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + key + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + value + TOK_LIMIT + 10 + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-4 depends on stages: Stage-2, Stage-0 + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: true + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [src] + Reducer 2 + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Reducer 3 + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: true + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns key,value + columns.types string:string + field.delim , + line.delim + + name default.nzhang_ctas5 + serialization.format , + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_ctas5 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-4 + Create Table Operator: + Create Table + columns: key string, value string + field delimiter: , + input format: org.apache.hadoop.mapred.TextInputFormat + line delimiter: + + output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_ctas5 + + Stage: Stage-3 + Stats-Aggr Operator +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: explain create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-4 + Create Table Operator: + columns:["key string","value string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_ctas5 + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_ctas5","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_7] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Stage-0 + Move Operator + Please refer to the previous Stage-1 +PREHOOK: query: create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_ctas5 +POSTHOOK: query: create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_ctas5 +PREHOOK: query: explain create table nzhang_ctas6 (key string, `to` string) +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table nzhang_ctas6 (key string, `to` string) +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + columns:["key string","to string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_ctas6 + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat +PREHOOK: query: create table nzhang_ctas6 (key string, `to` string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_ctas6 +POSTHOOK: query: create table nzhang_ctas6 (key string, `to` string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_ctas6 +PREHOOK: query: explain insert overwrite table nzhang_ctas6 select key, value from src tablesample (10 rows) +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table nzhang_ctas6 select key, value from src tablesample (10 rows) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has unsupported tokens + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_ctas6","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Map 1 + File Output Operator [FS_2] + compressed:true + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_ctas6","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: insert overwrite table nzhang_ctas6 select key, value from src tablesample (10 rows) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@nzhang_ctas6 +POSTHOOK: query: insert overwrite table nzhang_ctas6 select key, value from src tablesample (10 rows) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@nzhang_ctas6 +POSTHOOK: Lineage: nzhang_ctas6.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: nzhang_ctas6.to SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain create table nzhang_ctas7 as select key, `to` from nzhang_ctas6 +PREHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: query: explain create table nzhang_ctas7 as select key, `to` from nzhang_ctas6 +POSTHOOK: type: CREATETABLE_AS_SELECT +CBO Succeeded + +Stage-3 + Stats-Aggr Operator + Stage-4 + Create Table Operator: + columns:["key string","to string"] + input format:org.apache.hadoop.mapred.TextInputFormat + name:default.nzhang_ctas7 + output format:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + Stage-2 + Dependency Collection{} + Stage-1 + Map 1 + File Output Operator [FS_2] + compressed:true + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.nzhang_ctas7","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:nzhang_ctas6 + Statistics:Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Stage-0 + Move Operator + Please refer to the previous Stage-1 +PREHOOK: query: create table nzhang_ctas7 as select key, `to` from nzhang_ctas6 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@nzhang_ctas6 +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_ctas7 +POSTHOOK: query: create table nzhang_ctas7 as select key, `to` from nzhang_ctas6 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@nzhang_ctas6 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_ctas7 +PREHOOK: query: CREATE TABLE src1_rot13_iof(key STRING, value STRING) + STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.udf.Rot13InputFormat' + OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.udf.Rot13OutputFormat' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src1_rot13_iof +POSTHOOK: query: CREATE TABLE src1_rot13_iof(key STRING, value STRING) + STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.udf.Rot13InputFormat' + OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.udf.Rot13OutputFormat' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src1_rot13_iof +PREHOOK: query: DESCRIBE EXTENDED src1_rot13_iof +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@src1_rot13_iof +POSTHOOK: query: DESCRIBE EXTENDED src1_rot13_iof +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@src1_rot13_iof +key string +value string + +#### A masked pattern was here #### +PREHOOK: query: INSERT OVERWRITE TABLE src1_rot13_iof select * FROM src1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +PREHOOK: Output: default@src1_rot13_iof +POSTHOOK: query: INSERT OVERWRITE TABLE src1_rot13_iof select * FROM src1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@src1_rot13_iof +POSTHOOK: Lineage: src1_rot13_iof.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src1_rot13_iof.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + # buckets:2 + bucket columns:["a"] + columns:["a int","b varchar(128)"] + input format:org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + name:default.acid_danp + output format:org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +PREHOOK: query: create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@acid_danp +POSTHOOK: query: create table acid_danp(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@acid_danp +PREHOOK: query: explain insert into table acid_danp select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint < 0 order by cint limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table acid_danp select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint < 0 order by cint limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_danp","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_danp","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + Map-reduce partition columns:_col0 (type: int) + sort order: + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: varchar(128)) + Limit [LIM_6] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: varchar(128)) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_10] + predicate:(cint < 0) (type: boolean) + Statistics:Num rows: 4096 Data size: 299684 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:alltypesorc + Statistics:Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: insert into table acid_danp select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint < 0 order by cint limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: default@acid_danp +POSTHOOK: query: insert into table acid_danp select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint < 0 order by cint limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: default@acid_danp +POSTHOOK: Lineage: acid_danp.a SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: acid_danp.b EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +PREHOOK: query: explain select a,b from acid_danp order by a +PREHOOK: type: QUERY +POSTHOOK: query: explain select a,b from acid_danp order by a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_4] + compressed:true + Statistics:Num rows: 10 Data size: 1007 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 1007 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 10 Data size: 1007 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: varchar(128)) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 10 Data size: 1007 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:acid_danp + Statistics:Num rows: 10 Data size: 1007 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + # buckets:2 + bucket columns:["a"] + columns:["a int","b varchar(128)"] + input format:org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + name:default.acid_dap + output format:org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition columns:["ds string"] +PREHOOK: query: create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@acid_dap +POSTHOOK: query: create table acid_dap(a int, b varchar(128)) partitioned by (ds string) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@acid_dap +PREHOOK: query: explain insert into table acid_dap partition (ds='today') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint < 0 order by cint limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table acid_dap partition (ds='today') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint < 0 order by cint limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"today"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_dap","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_dap","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + Map-reduce partition columns:_col0 (type: int) + sort order: + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: varchar(128)) + Limit [LIM_6] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: varchar(128)) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_10] + predicate:(cint < 0) (type: boolean) + Statistics:Num rows: 4096 Data size: 299684 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:alltypesorc + Statistics:Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: insert into table acid_dap partition (ds='today') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint < 0 order by cint limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: default@acid_dap@ds=today +POSTHOOK: query: insert into table acid_dap partition (ds='today') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint < 0 order by cint limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: default@acid_dap@ds=today +POSTHOOK: Lineage: acid_dap PARTITION(ds=today).a SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: acid_dap PARTITION(ds=today).b EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +PREHOOK: query: explain insert into table acid_dap partition (ds='tomorrow') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint > 1000 order by cint limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table acid_dap partition (ds='tomorrow') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint > 1000 order by cint limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"tomorrow"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_dap","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_dap","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + Map-reduce partition columns:_col0 (type: int) + sort order: + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: varchar(128)) + Limit [LIM_6] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: varchar(128)) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 4096 Data size: 880584 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_10] + predicate:(cint > 1000) (type: boolean) + Statistics:Num rows: 4096 Data size: 299684 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:alltypesorc + Statistics:Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: insert into table acid_dap partition (ds='tomorrow') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint > 1000 order by cint limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: default@acid_dap@ds=tomorrow +POSTHOOK: query: insert into table acid_dap partition (ds='tomorrow') select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null and cint > 1000 order by cint limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: default@acid_dap@ds=tomorrow +POSTHOOK: Lineage: acid_dap PARTITION(ds=tomorrow).a SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: acid_dap PARTITION(ds=tomorrow).b EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +PREHOOK: query: explain select a,b,ds from acid_dap order by a,b +PREHOOK: type: QUERY +POSTHOOK: query: explain select a,b,ds from acid_dap order by a,b +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_4] + compressed:true + Statistics:Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: PARTIAL + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: PARTIAL + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: int), _col1 (type: varchar(128)) + sort order:++ + Statistics:Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: PARTIAL + value expressions:_col2 (type: string) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: PARTIAL + TableScan [TS_0] + alias:acid_dap + Statistics:Num rows: 20 Data size: 1947 Basic stats: COMPLETE Column stats: PARTIAL +PREHOOK: query: explain create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +POSTHOOK: query: explain create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +Stage-0 + Create Table Operator: + # buckets:2 + bucket columns:["a"] + columns:["a int","b varchar(128)"] + input format:org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + name:default.acid_dtt + output format:org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +PREHOOK: query: create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@acid_dtt +POSTHOOK: query: create temporary table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@acid_dtt +PREHOOK: query: explain insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_dtt","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.acid_dtt","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + Map-reduce partition columns:_col0 (type: int) + sort order: + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: int), _col1 (type: varchar(128)) + Limit [LIM_6] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 9173 Data size: 1972068 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 9173 Data size: 1972068 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: varchar(128)) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 9173 Data size: 1972068 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_10] + predicate:cint is not null (type: boolean) + Statistics:Num rows: 9173 Data size: 671104 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:alltypesorc + Statistics:Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * from acid_dtt order by a +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from acid_dtt order by a +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_4] + compressed:true + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:_col0 (type: int) + sort order:+ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:_col1 (type: varchar(128)) + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + TableScan [TS_0] + alias:acid_dtt + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE +PREHOOK: query: create table over1k( + t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) + row format delimited + fields terminated by '|' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k +POSTHOOK: query: create table over1k( + t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) + row format delimited + fields terminated by '|' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k +PREHOOK: query: load data local inpath '../../data/files/over1k' into table over1k +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@over1k +POSTHOOK: query: load data local inpath '../../data/files/over1k' into table over1k +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@over1k +PREHOOK: query: create table over1k_orc like over1k +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_orc +POSTHOOK: query: create table over1k_orc like over1k +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_orc +PREHOOK: query: alter table over1k_orc set fileformat orc +PREHOOK: type: ALTERTABLE_FILEFORMAT +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_orc +POSTHOOK: query: alter table over1k_orc set fileformat orc +POSTHOOK: type: ALTERTABLE_FILEFORMAT +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_orc +PREHOOK: query: insert overwrite table over1k_orc select * from over1k +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_orc +POSTHOOK: query: insert overwrite table over1k_orc select * from over1k +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_orc +POSTHOOK: Lineage: over1k_orc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_orc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ] +POSTHOOK: Lineage: over1k_orc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ] +POSTHOOK: Lineage: over1k_orc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ] +POSTHOOK: Lineage: over1k_orc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ] +POSTHOOK: Lineage: over1k_orc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_orc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_orc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ] +POSTHOOK: Lineage: over1k_orc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_orc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ] +POSTHOOK: Lineage: over1k_orc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ] +PREHOOK: query: create table over1k_part_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (ds string, t tinyint) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_orc +POSTHOOK: query: create table over1k_part_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (ds string, t tinyint) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_orc +PREHOOK: query: create table over1k_part_limit_orc like over1k_part_orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_limit_orc +POSTHOOK: query: create table over1k_part_limit_orc like over1k_part_orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_limit_orc +PREHOOK: query: alter table over1k_part_limit_orc set fileformat orc +PREHOOK: type: ALTERTABLE_FILEFORMAT +PREHOOK: Input: default@over1k_part_limit_orc +PREHOOK: Output: default@over1k_part_limit_orc +POSTHOOK: query: alter table over1k_part_limit_orc set fileformat orc +POSTHOOK: type: ALTERTABLE_FILEFORMAT +POSTHOOK: Input: default@over1k_part_limit_orc +POSTHOOK: Output: default@over1k_part_limit_orc +PREHOOK: query: create table over1k_part_buck_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) into 4 buckets stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_buck_orc +POSTHOOK: query: create table over1k_part_buck_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) into 4 buckets stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_buck_orc +PREHOOK: query: create table over1k_part_buck_sort_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) + sorted by (f) into 4 buckets stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_buck_sort_orc +POSTHOOK: query: create table over1k_part_buck_sort_orc( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) + sorted by (f) into 4 buckets stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_buck_sort_orc +PREHOOK: query: explain insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint), _col0 (type: smallint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: smallint) + sort order:+ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_20] + compressed:true + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_19] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_17] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_16] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + sort order: + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_14] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_12] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_11] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_9] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_8] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_11] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_9] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_8] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint), _col0 (type: smallint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: smallint) + sort order:+ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_orc@ds=foo +POSTHOOK: query: insert overwrite table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_orc@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part_orc@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_20] + compressed:true + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_19] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_17] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_16] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + sort order: + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_14] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_12] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_limit_orc@ds=foo +POSTHOOK: query: insert overwrite table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_limit_orc@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part_limit_orc@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_11] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_9] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_8] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_buck_orc +POSTHOOK: query: insert overwrite table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_buck_orc@t=27 +POSTHOOK: Output: default@over1k_part_buck_orc@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_11] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_9] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_8] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_buck_sort_orc +POSTHOOK: query: insert overwrite table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_buck_sort_orc@t=27 +POSTHOOK: Output: default@over1k_part_buck_sort_orc@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint), _col0 (type: smallint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: smallint) + sort order:+ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_20] + compressed:true + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_19] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_17] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_16] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + sort order: + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_14] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_12] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint), _col0 (type: smallint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: smallint) + sort order:+ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_orc@ds=foo +POSTHOOK: query: insert into table over1k_part_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by si +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_orc@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part_orc@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_20] + compressed:true + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_limit_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_19] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_17] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_16] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + sort order: + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_14] + Number of rows:10 + Statistics:Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_12] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_limit_orc@ds=foo +POSTHOOK: query: insert into table over1k_part_limit_orc partition(ds="foo", t) select si,i,b,f,t from over1k_orc where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_limit_orc@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part_limit_orc@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit_orc PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_buck_orc +POSTHOOK: query: insert into table over1k_part_buck_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_buck_orc@t=27 +POSTHOOK: Output: default@over1k_part_buck_orc@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.ql.io.orc.OrcSerde","name:":"default.over1k_part_buck_sort_orc","input format:":"org.apache.hadoop.hive.ql.io.orc.OrcInputFormat","output format:":"org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"} + Select Operator [OP_13] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [OP_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_10] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k_orc + Statistics:Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k_orc +PREHOOK: Output: default@over1k_part_buck_sort_orc +POSTHOOK: query: insert into table over1k_part_buck_sort_orc partition(t) select si,i,b,f,t from over1k_orc where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k_orc +POSTHOOK: Output: default@over1k_part_buck_sort_orc@t=27 +POSTHOOK: Output: default@over1k_part_buck_sort_orc@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=27).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort_orc PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k_orc)over1k_orc.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: drop table if exists over1k +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k +POSTHOOK: query: drop table if exists over1k +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k +PREHOOK: query: create table over1k( + t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) + row format delimited + fields terminated by '|' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k +POSTHOOK: query: create table over1k( + t tinyint, + si smallint, + i int, + b bigint, + f float, + d double, + bo boolean, + s string, + ts timestamp, + dec decimal(4,2), + bin binary) + row format delimited + fields terminated by '|' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k +PREHOOK: query: load data local inpath '../../data/files/over1k' into table over1k +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@over1k +POSTHOOK: query: load data local inpath '../../data/files/over1k' into table over1k +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@over1k +PREHOOK: query: create table over1k_part( + si smallint, + i int, + b bigint, + f float) + partitioned by (ds string, t tinyint) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part +POSTHOOK: query: create table over1k_part( + si smallint, + i int, + b bigint, + f float) + partitioned by (ds string, t tinyint) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part +PREHOOK: query: create table over1k_part_limit like over1k_part +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_limit +POSTHOOK: query: create table over1k_part_limit like over1k_part +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_limit +PREHOOK: query: create table over1k_part_buck( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) into 4 buckets +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_buck +POSTHOOK: query: create table over1k_part_buck( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) into 4 buckets +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_buck +PREHOOK: query: create table over1k_part_buck_sort( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) + sorted by (f) into 4 buckets +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@over1k_part_buck_sort +POSTHOOK: query: create table over1k_part_buck_sort( + si smallint, + i int, + b bigint, + f float) + partitioned by (t tinyint) + clustered by (si) + sorted by (f) into 4 buckets +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@over1k_part_buck_sort +PREHOOK: query: explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_13] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_12] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + sort order: + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_9] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part@ds=foo +POSTHOOK: query: insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_13] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_12] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + sort order: + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_9] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part_limit@ds=foo +POSTHOOK: query: insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part_buck +POSTHOOK: query: insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part_buck@t=27 +POSTHOOK: Output: default@over1k_part_buck@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part_buck_sort +POSTHOOK: query: insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part_buck_sort@t=27 +POSTHOOK: Output: default@over1k_part_buck_sort@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_13] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_12] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + sort order: + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_9] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_10] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_7] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_10] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_7] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_8] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_5] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part@ds=foo +POSTHOOK: query: insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{"ds":"foo"} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_limit","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_15] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col4 (type: tinyint) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+ + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_13] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [OP_12] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + sort order: + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + Limit [LIM_4] + Number of rows:10 + Statistics:Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_9] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part_limit@ds=foo +POSTHOOK: query: insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=27 +POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_10] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_7] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part_buck +POSTHOOK: query: insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part_buck@t=27 +POSTHOOK: Output: default@over1k_part_buck@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +POSTHOOK: query: explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + partition:{} + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.over1k_part_buck_sort","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_10] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_bucket_number"] + | Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) + Map-reduce partition columns:_col4 (type: tinyint) + sort order:+++ + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_7] + predicate:(t is null or (t = 27)) (type: boolean) + Statistics:Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:over1k + Statistics:Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +PREHOOK: type: QUERY +PREHOOK: Input: default@over1k +PREHOOK: Output: default@over1k_part_buck_sort +POSTHOOK: query: insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@over1k +POSTHOOK: Output: default@over1k_part_buck_sort@t=27 +POSTHOOK: Output: default@over1k_part_buck_sort@t=__HIVE_DEFAULT_PARTITION__ +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] +POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] +PREHOOK: query: explain +select src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (select * FROM src WHERE src.key < 10) src1 + JOIN + (select * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (select * FROM src WHERE src.key < 10) src1 + JOIN + (select * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +Not invoking CBO because the statement has sort by + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_17] + compressed:true + Statistics:Num rows: 13778 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [OP_16] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 13778 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order:++++ + Statistics:Num rows: 13778 Data size: 4904968 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_15] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{} + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 13778 Data size: 4904968 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | sort order: + | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: string) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_13] + | predicate:(key < 10) (type: boolean) + | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + sort order: + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string), _col1 (type: string) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_14] + predicate:(key < 10) (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: CREATE TABLE myinput1(key int, value int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@myinput1 +POSTHOOK: query: CREATE TABLE myinput1(key int, value int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@myinput1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in8.txt' INTO TABLE myinput1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@myinput1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in8.txt' INTO TABLE myinput1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@myinput1 +PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:value (type: int) + Map-reduce partition columns:value (type: int) + sort order:+ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + value expressions:key (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key=c.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key=c.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_21] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"key (type: int)","1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] + | Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | Filter Operator [FIL_18] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:value (type: int) + | Map-reduce partition columns:value (type: int) + | sort order:+ + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | value expressions:key (type: int) + | Filter Operator [FIL_19] + | predicate:value is not null (type: boolean) + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:key (type: int) + Map-reduce partition columns:key (type: int) + sort order:+ + Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: int) + Filter Operator [FIL_20] + predicate:key is not null (type: boolean) + Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:c + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key<=>c.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value join myinput1 c on a.key<=>c.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_9] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"key (type: int)","1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] + | Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:value (type: int) + | Map-reduce partition columns:value (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:key (type: int) + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:key (type: int) + Map-reduce partition columns:key (type: int) + sort order:+ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: int) + TableScan [TS_2] + alias:c + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value=b.key join myinput1 c on a.key<=>c.key AND a.value=c.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value=b.key join myinput1 c on a.key<=>c.key AND a.value=c.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_15] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"key (type: int), value (type: int)","1":"value (type: int), key (type: int)","0":"key (type: int), value (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] + | Statistics:Num rows: 4 Data size: 37 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:key (type: int), value (type: int) + | Map-reduce partition columns:key (type: int), value (type: int) + | sort order:++ + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_12] + | predicate:value is not null (type: boolean) + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:value (type: int), key (type: int) + | Map-reduce partition columns:value (type: int), key (type: int) + | sort order:++ + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_13] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:key (type: int), value (type: int) + Map-reduce partition columns:key (type: int), value (type: int) + sort order:++ + Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_14] + predicate:value is not null (type: boolean) + Statistics:Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:c + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value<=>b.key join myinput1 c on a.key<=>c.key AND a.value<=>c.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from myinput1 a join myinput1 b on a.key<=>b.value AND a.value<=>b.key join myinput1 c on a.key<=>c.key AND a.value<=>c.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_9] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] + | keys:{"2":"key (type: int), value (type: int)","1":"value (type: int), key (type: int)","0":"key (type: int), value (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11"] + | Statistics:Num rows: 6 Data size: 57 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:key (type: int), value (type: int) + | Map-reduce partition columns:key (type: int), value (type: int) + | sort order:++ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:value (type: int), key (type: int) + | Map-reduce partition columns:value (type: int), key (type: int) + | sort order:++ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:key (type: int), value (type: int) + Map-reduce partition columns:key (type: int), value (type: int) + sort order:++ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:c + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key<=>b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * FROM myinput1 a LEFT OUTER JOIN myinput1 b ON a.key<=>b.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:value (type: int) + Map-reduce partition columns:value (type: int) + sort order:+ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + value expressions:key (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key<=>b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * FROM myinput1 a RIGHT OUTER JOIN myinput1 b ON a.key<=>b.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:value (type: int) + Map-reduce partition columns:value (type: int) + sort order:+ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + value expressions:key (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select * FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key<=>b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * FROM myinput1 a FULL OUTER JOIN myinput1 b ON a.key<=>b.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:value (type: int) + Map-reduce partition columns:value (type: int) + sort order:+ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + value expressions:key (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM myinput1 a JOIN myinput1 b ON a.key<=>b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM myinput1 a JOIN myinput1 b ON a.key<=>b.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"value (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:value (type: int) + Map-reduce partition columns:value (type: int) + sort order:+ + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE + value expressions:key (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: CREATE TABLE smb_input(key int, value int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@smb_input +POSTHOOK: query: CREATE TABLE smb_input(key int, value int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@smb_input +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' into table smb_input +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@smb_input +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' into table smb_input +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@smb_input +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in5.txt' into table smb_input +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@smb_input +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in5.txt' into table smb_input +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@smb_input +PREHOOK: query: CREATE TABLE smb_input1(key int, value int) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@smb_input1 +POSTHOOK: query: CREATE TABLE smb_input1(key int, value int) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@smb_input1 +PREHOOK: query: CREATE TABLE smb_input2(key int, value int) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@smb_input2 +POSTHOOK: query: CREATE TABLE smb_input2(key int, value int) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@smb_input2 +PREHOOK: query: from smb_input +insert overwrite table smb_input1 select * +insert overwrite table smb_input2 select * +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_input +PREHOOK: Output: default@smb_input1 +PREHOOK: Output: default@smb_input2 +POSTHOOK: query: from smb_input +insert overwrite table smb_input1 select * +insert overwrite table smb_input2 select * +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_input +POSTHOOK: Output: default@smb_input1 +POSTHOOK: Output: default@smb_input2 +POSTHOOK: Lineage: smb_input1.key SIMPLE [(smb_input)smb_input.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: smb_input1.value SIMPLE [(smb_input)smb_input.FieldSchema(name:value, type:int, comment:null), ] +POSTHOOK: Lineage: smb_input2.key SIMPLE [(smb_input)smb_input.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: smb_input2.value SIMPLE [(smb_input)smb_input.FieldSchema(name:value, type:int, comment:null), ] +PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:key (type: int) + Map-reduce partition columns:key (type: int) + sort order:+ + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int), value (type: int)","0":"key (type: int), value (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int), value (type: int) + | Map-reduce partition columns:key (type: int), value (type: int) + | sort order:++ + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:key (type: int), value (type: int) + Map-reduce partition columns:key (type: int), value (type: int) + sort order:++ + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_1] + alias:b + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"1":"key (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:key (type: int) + Map-reduce partition columns:key (type: int) + sort order:+ + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:key (type: int) + Map-reduce partition columns:key (type: int) + sort order:+ + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: <=> is not yet supported for cbo. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_6] + compressed:true + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_7] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"1":"key (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1","_col5","_col6"] + | Statistics:Num rows: 28 Data size: 209 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: int) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:key (type: int) + Map-reduce partition columns:key (type: int) + sort order:+ + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: int) + TableScan [TS_1] + alias:b + Statistics:Num rows: 26 Data size: 190 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: drop table sales +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table sales +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table things +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table things +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE sales (name STRING, id INT) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@sales +POSTHOOK: query: CREATE TABLE sales (name STRING, id INT) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@sales +PREHOOK: query: CREATE TABLE things (id INT, name STRING) partitioned by (ds string) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@things +POSTHOOK: query: CREATE TABLE things (id INT, name STRING) partitioned by (ds string) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@things +PREHOOK: query: load data local inpath '../../data/files/sales.txt' INTO TABLE sales +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@sales +POSTHOOK: query: load data local inpath '../../data/files/sales.txt' INTO TABLE sales +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@sales +PREHOOK: query: load data local inpath '../../data/files/things.txt' INTO TABLE things partition(ds='2011-10-23') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@things +POSTHOOK: query: load data local inpath '../../data/files/things.txt' INTO TABLE things partition(ds='2011-10-23') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@things +POSTHOOK: Output: default@things@ds=2011-10-23 +PREHOOK: query: load data local inpath '../../data/files/things2.txt' INTO TABLE things partition(ds='2011-10-24') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@things +POSTHOOK: query: load data local inpath '../../data/files/things2.txt' INTO TABLE things partition(ds='2011-10-24') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@things +POSTHOOK: Output: default@things@ds=2011-10-24 +PREHOOK: query: explain select name,id FROM sales LEFT SEMI JOIN things ON (sales.id = things.id) +PREHOOK: type: QUERY +POSTHOOK: query: explain select name,id FROM sales LEFT SEMI JOIN things ON (sales.id = things.id) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: int)","0":"_col1 (type: int)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:_col1 (type: int) + | Map-reduce partition columns:_col1 (type: int) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:_col0 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | Filter Operator [FIL_15] + | predicate:id is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_0] + | alias:sales + | Statistics:Num rows: 0 Data size: 13 Basic stats: PARTIAL Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_5] + keys:_col0 (type: int) + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_16] + predicate:id is not null (type: boolean) + Statistics:Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:things + Statistics:Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: drop table sales +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@sales +PREHOOK: Output: default@sales +POSTHOOK: query: drop table sales +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@sales +POSTHOOK: Output: default@sales +PREHOOK: query: drop table things +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@things +PREHOOK: Output: default@things +POSTHOOK: query: drop table things +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@things +POSTHOOK: Output: default@things +PREHOOK: query: explain extended select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_JOIN + TOK_JOIN + TOK_TABREF + TOK_TABNAME + srcpart + TOK_TABREF + TOK_TABNAME + src + = + . + TOK_TABLE_OR_COL + srcpart + value + . + TOK_TABLE_OR_COL + src + value + TOK_TABREF + TOK_TABNAME + src1 + = + . + TOK_TABLE_OR_COL + srcpart + key + . + TOK_TABLE_OR_COL + src1 + key + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + . + TOK_TABLE_OR_COL + srcpart + key + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Map 3 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [src] + Map 3 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Estimated key counts: Map 4 => 25 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 4 + Position of Big Table: 0 + Statistics: Num rows: 243 Data size: 43254 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 243 Data size: 43254 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string) + auto parallelism: true + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Map 4 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + auto parallelism: true + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src1 + numFiles 1 + numRows 25 + rawDataSize 191 + serialization.ddl struct src1 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src1 + name: default.src1 + Truncated Path -> Alias: + /src1 [src1] + Reducer 2 + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col1 + Position of Big Table: 0 + Statistics: Num rows: 567 Data size: 49329 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 567 Data size: 49329 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: true + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 567 Data size: 49329 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' +PREHOOK: type: QUERY +POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +Map 3 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_21] + compressed:true + Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_19] + outputColumnNames:["_col0"] + Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_27] + | predicate:(value > 'val_450') (type: boolean) + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + key expressions:_col1 (type: string) + Map-reduce partition columns:_col1 (type: string) + sort order:+ + Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Map Join Operator [MAPJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_7] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_6] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + |<-Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_28] + predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) + Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:srcpart + Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' +PREHOOK: type: QUERY +POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +Map 3 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_21] + compressed:true + Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_19] + outputColumnNames:["_col0"] + Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_27] + | predicate:(value > 'val_450') (type: boolean) + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + key expressions:_col1 (type: string) + Map-reduce partition columns:_col1 (type: string) + sort order:+ + Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Map Join Operator [MAPJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_7] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_6] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + |<-Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_28] + predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) + Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:srcpart + Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' +PREHOOK: type: QUERY +POSTHOOK: query: explain select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450' +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +Map 3 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_21] + compressed:true + Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_19] + outputColumnNames:["_col0"] + Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_31] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1"] + | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_27] + | predicate:(value > 'val_450') (type: boolean) + | Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + key expressions:_col1 (type: string) + Map-reduce partition columns:_col1 (type: string) + sort order:+ + Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: string) + Map Join Operator [MAPJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 3":"_col0 (type: string)","Map 4":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_7] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_6] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + |<-Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_28] + predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) + Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:srcpart + Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part + partition by p_mfgr + order by p_name + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part + partition by p_mfgr + order by p_name + ) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j +distribute by j.p_mfgr +sort by j.p_name) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j +distribute by j.p_mfgr +sort by j.p_name) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_16] + compressed:true + Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_14] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_13] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_12] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_10] + Function definitions:[{"Input definition":{"type:":"SUBQUERY"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 29 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 29 Data size: 6467 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int) + Map Join Operator [MAPJOIN_21] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"p_partkey (type: int)","Map 4":"p_partkey (type: int)"} + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 29 Data size: 6467 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:p_partkey (type: int) + | Map-reduce partition columns:p_partkey (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_20] + | predicate:p_partkey is not null (type: boolean) + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_1] + | alias:p2 + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Filter Operator [FIL_19] + predicate:p_partkey is not null (type: boolean) + Statistics:Num rows: 26 Data size: 5902 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:p1 + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size +from noop(on part +partition by p_mfgr +order by p_name) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size +from noop(on part +partition by p_mfgr +order by p_name) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_5] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_4] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part + partition by p_mfgr + order by p_name + ) abc +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part + partition by p_mfgr + order by p_name + ) abc +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop(on part + partition by p_mfgr + order by p_name + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop(on part + partition by p_mfgr + order by p_name + ) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop(on part + partition by p_mfgr + order by p_name + ) +group by p_mfgr, p_name, p_size +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz +from noop(on part + partition by p_mfgr + order by p_name + ) +group by p_mfgr, p_name, p_size +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_12] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_11] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_10] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_9] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:++ + Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col2 (type: int) + Group By Operator [GBY_8] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order:+++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [OP_15] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col2 (type: string), _col1 (type: string), _col5 (type: int) + Map-reduce partition columns:rand() (type: double) + sort order:+++ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select abc.* +from noop(on part +partition by p_mfgr +order by p_name +) abc join part p1 on abc.p_partkey = p1.p_partkey +PREHOOK: type: QUERY +POSTHOOK: query: explain +select abc.* +from noop(on part +partition by p_mfgr +order by p_name +) abc join part p1 on abc.p_partkey = p1.p_partkey +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Map Join Operator [MAPJOIN_16] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Reducer 2":"_col0 (type: int)","Map 3":"p_partkey (type: int)"} + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:p_partkey (type: int) + | Map-reduce partition columns:p_partkey (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_15] + | predicate:p_partkey is not null (type: boolean) + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_1] + | alias:p1 + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Filter Operator [FIL_14] + predicate:_col0 is not null (type: boolean) + Statistics:Num rows: 13 Data size: 8047 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + | Statistics:Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select abc.* +from part p1 join noop(on part +partition by p_mfgr +order by p_name +) abc on abc.p_partkey = p1.p_partkey +PREHOOK: type: QUERY +POSTHOOK: query: explain +select abc.* +from part p1 join noop(on part +partition by p_mfgr +order by p_name +) abc on abc.p_partkey = p1.p_partkey +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 3 <- Map 1 (BROADCAST_EDGE), Map 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Map Join Operator [MAPJOIN_16] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Reducer 3":"_col0 (type: int)","Map 1":"p_partkey (type: int)"} + | outputColumnNames:["_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] + | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 1 [BROADCAST_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:p_partkey (type: int) + | Map-reduce partition columns:p_partkey (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_14] + | predicate:p_partkey is not null (type: boolean) + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:p1 + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Filter Operator [FIL_15] + predicate:_col0 is not null (type: boolean) + Statistics:Num rows: 13 Data size: 8047 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + | Statistics:Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + TableScan [TS_1] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name, p_size desc) as r +from noopwithmap(on part +partition by p_mfgr +order by p_name, p_size desc) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name, p_size desc) as r +from noopwithmap(on part +partition by p_mfgr +order by p_name, p_size desc) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_10] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_8] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_7] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1, _col5(DESC)"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col2 (type: string), _col1 (type: string), _col5 (type: int) + Map-reduce partition columns:_col2 (type: string) + sort order:++- + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col1, _col5(DESC)"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:p_mfgr (type: string), p_name (type: string), p_size (type: int) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++- + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_1] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"p_mfgr","name:":"noopwithmap","order by:":"p_name, p_size(DESC)"}}] + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noopwithmap(on part + partition by p_mfgr + order by p_name) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noopwithmap(on part + partition by p_mfgr + order by p_name) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_10] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_8] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_7] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + PTF Operator [PTF_1] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"p_mfgr","name:":"noopwithmap","order by:":"p_name"}}] + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part +partition by p_mfgr +order by p_name) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on part +partition by p_mfgr +order by p_name) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on noopwithmap(on noop(on part +partition by p_mfgr +order by p_mfgr DESC, p_name +))) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, p_size, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on noopwithmap(on noop(on part +partition by p_mfgr +order by p_mfgr DESC, p_name +))) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_10] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_7] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col2(DESC), _col1"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2(DESC), _col1"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:-+ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noopwithmap","order by:":"_col2(DESC), _col1"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2(DESC), _col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2(DESC), _col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:-+ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, +sub1.cd, sub1.s1 +from (select p_mfgr, p_name, +count(p_size) over (partition by p_mfgr order by p_name) as cd, +p_retailprice, +sum(p_retailprice) over w1 as s1 +from noop(on part +partition by p_mfgr +order by p_name) +window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) +) sub1 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, +sub1.cd, sub1.s1 +from (select p_mfgr, p_name, +count(p_size) over (partition by p_mfgr order by p_name) as cd, +p_retailprice, +sum(p_retailprice) over w1 as s1 +from noop(on part +partition by p_mfgr +order by p_name) +window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) +) sub1 +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_10] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select abc.p_mfgr, abc.p_name, +rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, +dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, +count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, +abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, +abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz +from noop(on part +partition by p_mfgr +order by p_name +) abc join part p1 on abc.p_partkey = p1.p_partkey +PREHOOK: type: QUERY +POSTHOOK: query: explain +select abc.p_mfgr, abc.p_name, +rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, +dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, +count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, +abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, +abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz +from noop(on part +partition by p_mfgr +order by p_name +) abc join part p1 on abc.p_partkey = p1.p_partkey +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (BROADCAST_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_15] + compressed:true + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_12] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + Map Join Operator [MAPJOIN_20] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Reducer 2":"_col0 (type: int)","Map 4":"p_partkey (type: int)"} + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 14 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:p_partkey (type: int) + | Map-reduce partition columns:p_partkey (type: int) + | sort order:+ + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_19] + | predicate:p_partkey is not null (type: boolean) + | Statistics:Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_1] + | alias:p1 + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Filter Operator [FIL_18] + predicate:_col0 is not null (type: boolean) + Statistics:Num rows: 13 Data size: 3055 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 6110 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6110 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_2] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_partkey (type: int), p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select DISTINCT p_mfgr, p_name, p_size +from noop(on part +partition by p_mfgr +order by p_name) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select DISTINCT p_mfgr, p_name, p_size +from noop(on part +partition by p_mfgr +order by p_name) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_10] + compressed:true + Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_8] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 13 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order:+++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [OP_11] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col2 (type: string), _col1 (type: string), _col5 (type: int) + Map-reduce partition columns:rand() (type: double) + sort order:+++ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain create view IF NOT EXISTS mfgr_price_view as +select p_mfgr, p_brand, +sum(p_retailprice) as s +from part +group by p_mfgr, p_brand +PREHOOK: type: CREATEVIEW +POSTHOOK: query: explain create view IF NOT EXISTS mfgr_price_view as +select p_mfgr, p_brand, +sum(p_retailprice) as s +from part +group by p_mfgr, p_brand +POSTHOOK: type: CREATEVIEW +Not invoking CBO because the statement doesn't have QUERY or EXPLAIN as root and not a CTAS; has create view + +Stage-0 + Create View Operator: + name:default.mfgr_price_view + original text:select p_mfgr, p_brand, +sum(p_retailprice) as s +from part +group by p_mfgr, p_brand +PREHOOK: query: CREATE TABLE part_4( +p_mfgr STRING, +p_name STRING, +p_size INT, +r INT, +dr INT, +s DOUBLE) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@part_4 +POSTHOOK: query: CREATE TABLE part_4( +p_mfgr STRING, +p_name STRING, +p_size INT, +r INT, +dr INT, +s DOUBLE) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@part_4 +PREHOOK: query: CREATE TABLE part_5( +p_mfgr STRING, +p_name STRING, +p_size INT, +s2 INT, +r INT, +dr INT, +cud DOUBLE, +fv1 INT) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@part_5 +POSTHOOK: query: CREATE TABLE part_5( +p_mfgr STRING, +p_name STRING, +p_size INT, +s2 INT, +r INT, +dr INT, +cud DOUBLE, +fv1 INT) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@part_5 +PREHOOK: query: explain +from noop(on part +partition by p_mfgr +order by p_name) +INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, +rank() over (distribute by p_mfgr sort by p_name) as r, +dense_rank() over (distribute by p_mfgr sort by p_name) as dr, +sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s +INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, +round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, +rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, +dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, +cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, +first_value(p_size, true) over w1 as fv1 +window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) +PREHOOK: type: QUERY +POSTHOOK: query: explain +from noop(on part +partition by p_mfgr +order by p_name) +INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, +rank() over (distribute by p_mfgr sort by p_name) as r, +dense_rank() over (distribute by p_mfgr sort by p_name) as dr, +sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s +INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, +round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, +rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, +dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, +cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, +first_value(p_size, true) over w1 as fv1 +window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) +POSTHOOK: type: QUERY +Not invoking CBO because the statement is not a query, CTAS, or insert + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 2 (SIMPLE_EDGE) + +Stage-5 + Stats-Aggr Operator + Stage-1 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_5","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-3 + Dependency Collection{} + Stage-2 + Reducer 3 + File Output Operator [FS_9] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_4","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int), _col7 (type: double) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col1"}}] + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5","_col7"] + | Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int), p_retailprice (type: double) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 5 + File Output Operator [FS_20] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_5","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_17] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_16] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col3","name:":"windowingtablefunction","order by:":"_col3, _col2"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_15] + | outputColumnNames:["_col0","_col2","_col3","_col6"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_wcol0 (type: bigint), _col5 (type: int) + Select Operator [SEL_13] + outputColumnNames:["_col1","_col2","_col5","_wcol0"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_12] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col5"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col2 (type: string), _col5 (type: int) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: string) + Please refer to the previous PTF Operator [PTF_3] +Stage-4 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.part_4","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Stage-3 +PREHOOK: query: explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr,p_name) as r, +dense_rank() over (partition by p_mfgr,p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 +from noop(on + noopwithmap(on + noop(on + noop(on part + partition by p_mfgr + order by p_mfgr) + ) + partition by p_mfgr,p_name + order by p_mfgr,p_name) + partition by p_mfgr,p_name + order by p_mfgr,p_name) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr,p_name) as r, +dense_rank() over (partition by p_mfgr,p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 +from noop(on + noopwithmap(on + noop(on + noop(on part + partition by p_mfgr + order by p_mfgr) + ) + partition by p_mfgr,p_name + order by p_mfgr,p_name) + partition by p_mfgr,p_name + order by p_mfgr,p_name) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_11] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_10] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2, _col1","name:":"windowingtablefunction","order by:":"_col2, _col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_7] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noopwithmap","order by:":"_col2, _col1"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_6] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_5] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_4] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noopwithmap","order by:":"_col2, _col1"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:+ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_name (type: string), p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on + noop(on + noop(on + noop(on part + partition by p_mfgr + order by p_mfgr) + ) + partition by p_mfgr,p_name + order by p_mfgr,p_name) + partition by p_mfgr + order by p_mfgr ) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 +from noop(on + noop(on + noop(on + noop(on part + partition by p_mfgr + order by p_mfgr) + ) + partition by p_mfgr,p_name + order by p_mfgr,p_name) + partition by p_mfgr + order by p_mfgr ) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 + File Output Operator [FS_15] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_12] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_9] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_8] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col2 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:+ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col1 (type: string), _col5 (type: int) + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string) + Map-reduce partition columns:p_mfgr (type: string) + sort order:+ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_name (type: string), p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 +from noop(on + noop(on + noop(on + noop(on part + partition by p_mfgr,p_name + order by p_mfgr,p_name) + ) + partition by p_mfgr + order by p_mfgr)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_mfgr, p_name, +rank() over (partition by p_mfgr order by p_name) as r, +dense_rank() over (partition by p_mfgr order by p_name) as dr, +p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 +from noop(on + noop(on + noop(on + noop(on part + partition by p_mfgr,p_name + order by p_mfgr,p_name) + ) + partition by p_mfgr + order by p_mfgr)) +POSTHOOK: type: QUERY +Not invoking CBO because the statement has PTF + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_10] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + PTF Operator [PTF_9] + Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col2","name:":"windowingtablefunction","order by:":"_col1"}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_8] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col2 (type: string), _col1 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + value expressions:_col5 (type: int) + PTF Operator [PTF_6] + Function definitions:[{"Input definition":{"type:":"PTFCOMPONENT"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}},{"Partition table definition":{"partition by:":"_col2","name:":"noop","order by:":"_col2"}}] + Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_5] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col2 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:+ + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: string), _col5 (type: int) + PTF Operator [PTF_3] + Function definitions:[{"Input definition":{"type:":"TABLE"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}},{"Partition table definition":{"partition by:":"_col2, _col1","name:":"noop","order by:":"_col2, _col1"}}] + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_1] + key expressions:p_mfgr (type: string), p_name (type: string) + Map-reduce partition columns:p_mfgr (type: string), p_name (type: string) + sort order:++ + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:p_size (type: int) + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select distinct src.* from src +PREHOOK: type: QUERY +POSTHOOK: query: explain select distinct src.* from src +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_8] + compressed:true + Statistics:Num rows: 250 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_6] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 250 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [OP_9] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:rand() (type: double) + sort order:++ + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_1] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select explode(array('a', 'b')) +PREHOOK: type: QUERY +POSTHOOK: query: explain select explode(array('a', 'b')) +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Unsupported + +Stage-0 + Fetch Operator + limit:-1 + UDTF Operator [UDTF_2] + function name:explode + Select Operator [SEL_1] + outputColumnNames:["_col0"] + TableScan [TS_0] + alias:_dummy_table +PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2 +POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2 +PREHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3 +POSTHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3 +PREHOOK: query: CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T4 +POSTHOOK: query: CREATE TABLE T4(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T4 +PREHOOK: query: CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest_j1 +POSTHOOK: query: CREATE TABLE dest_j1(key INT, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest_j1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t4 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T4 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t4 +PREHOOK: query: explain +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-3 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest_j1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-2 + Dependency Collection{} + Stage-1 + Reducer 2 + File Output Operator [FS_12] + compressed:true + Statistics:Num rows: 1219 Data size: 115805 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest_j1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_9] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1219 Data size: 115805 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_17] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 1219 Data size: 216982 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_15] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:src1 + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest_j1 +POSTHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) +INSERT OVERWRITE TABLE dest_j1 select src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest_j1 +POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain +select /*+ STREAMTABLE(a) */ * +FROM T1 a JOIN T2 b ON a.key = b.key + JOIN T3 c ON b.key = c.key + JOIN T4 d ON c.key = d.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+ STREAMTABLE(a) */ * +FROM T1 a JOIN T2 b ON a.key = b.key + JOIN T3 c ON b.key = c.key + JOIN T4 d ON c.key = d.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ STREAMTABLE(a) */. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator [MAPJOIN_31] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 1 to 2"},{"":"Inner Join 2 to 3"}] + | keys:{"Map 1":"key (type: string)","Map 2":"key (type: string)","Map 3":"key (type: string)","Map 4":"key (type: string)"} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11","_col15","_col16"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_30] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_3] + | alias:d + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Map 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_2] + | alias:c + | Statistics:Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_28] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Filter Operator [FIL_27] + predicate:key is not null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + TableScan [TS_0] + alias:a + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain +select /*+ STREAMTABLE(a,c) */ * +FROM T1 a JOIN T2 b ON a.key = b.key + JOIN T3 c ON b.key = c.key + JOIN T4 d ON c.key = d.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+ STREAMTABLE(a,c) */ * +FROM T1 a JOIN T2 b ON a.key = b.key + JOIN T3 c ON b.key = c.key + JOIN T4 d ON c.key = d.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ STREAMTABLE(a,c) */. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_13] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator [MAPJOIN_31] + | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 1 to 2"},{"":"Inner Join 2 to 3"}] + | keys:{"Map 1":"key (type: string)","Map 2":"key (type: string)","Map 3":"key (type: string)","Map 4":"key (type: string)"} + | outputColumnNames:["_col0","_col1","_col5","_col6","_col10","_col11","_col15","_col16"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_30] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_3] + | alias:d + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Map 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_2] + | alias:c + | Statistics:Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_7] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_28] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Filter Operator [FIL_27] + predicate:key is not null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + TableScan [TS_0] + alias:a + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +PREHOOK: type: QUERY +POSTHOOK: query: explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ STREAMTABLE(a) */. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Reducer 3 <- Map 2 (SIMPLE_EDGE) +Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Group By Operator [OP_20] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Map 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 275 Data size: 23925 Basic stats: COMPLETE Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"UDFToDouble(key) (type: double)","Map 2":"(key + 1) (type: double)"} + | outputColumnNames:["_col0","_col1","_col5"] + | Statistics:Num rows: 275 Data size: 23925 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [BROADCAST_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:UDFToDouble(key) (type: double) + | Map-reduce partition columns:UDFToDouble(key) (type: double) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:key (type: string), val (type: string) + | Filter Operator [FIL_16] + | predicate:UDFToDouble(key) is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Filter Operator [FIL_17] + predicate:(key + 1) is not null (type: boolean) + Statistics:Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_1] + alias:c + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +198 6274 194 +PREHOOK: query: explain +select * FROM +(select src.* FROM src) x +JOIN +(select src.* FROM src) Y +ON (x.key = Y.key) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select * FROM +(select src.* FROM src) x +JOIN +(select src.* FROM src) Y +ON (x.key = Y.key) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_10] + compressed:true + Statistics:Num rows: 1219 Data size: 433964 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_15] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1219 Data size: 433964 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_13] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:src + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: string) + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_14] + predicate:key is not null (type: boolean) + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_2] + alias:src + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ mapjoin(k)*/. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [OP_20] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col6) (type: int) + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"key (type: string)","Map 4":"val (type: string)"} + | outputColumnNames:["_col0","_col6"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:val (type: string) + | Map-reduce partition columns:val (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | Filter Operator [FIL_17] + | predicate:val is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_1] + | alias:v + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + TableScan [TS_0] + alias:k + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [OP_20] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col6) (type: int) + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"key (type: string)","Map 4":"key (type: string)"} + | outputColumnNames:["_col0","_col6"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | value expressions:val (type: string) + | Filter Operator [FIL_17] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_1] + | alias:v + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + TableScan [TS_0] + alias:k + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain select count(1) from T1 a join T1 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(1) from T1 a join T1 b on a.key = b.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [OP_20] + | aggregations:["count(1)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"key (type: string)","Map 4":"key (type: string)"} + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | Filter Operator [FIL_17] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + TableScan [TS_0] + alias:a + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +PREHOOK: type: QUERY +POSTHOOK: query: explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_9] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Group By Operator [OP_16] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) + Map Join Operator [MAPJOIN_14] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"Map 1":"UDFToDouble(key) (type: double)","Map 4":"(key + 1) (type: double)"} + | outputColumnNames:["_col0","_col1","_col5"] + | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:(key + 1) (type: double) + | Map-reduce partition columns:(key + 1) (type: double) + | sort order:+ + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + | value expressions:key (type: string) + | TableScan [TS_1] + | alias:c + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-TableScan [TS_0] + alias:a + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +PREHOOK: type: QUERY +POSTHOOK: query: explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ STREAMTABLE(a) */. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Reducer 3 <- Map 2 (SIMPLE_EDGE) +Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_9] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Group By Operator [OP_16] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Map 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) + Map Join Operator [MAPJOIN_14] + | condition map:[{"":"Right Outer Join0 to 1"}] + | keys:{"Map 1":"UDFToDouble(key) (type: double)","Map 2":"(key + 1) (type: double)"} + | outputColumnNames:["_col0","_col1","_col5"] + | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + |<-Map 1 [BROADCAST_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:UDFToDouble(key) (type: double) + | Map-reduce partition columns:UDFToDouble(key) (type: double) + | sort order:+ + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + | value expressions:key (type: string), val (type: string) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-TableScan [TS_1] + alias:c + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +PREHOOK: type: QUERY +POSTHOOK: query: explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ STREAMTABLE(a) */. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_9] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + sort order: + Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) + Group By Operator [OP_13] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col1) (type: int), hash(_col5) (type: int) + Merge Join Operator [MERGEJOIN_12] + | condition map:[{"":"Outer Join 0 to 1"}] + | keys:{"1":"(key + 1) (type: double)","0":"UDFToDouble(key) (type: double)"} + | outputColumnNames:["_col0","_col1","_col5"] + | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_2] + | key expressions:UDFToDouble(key) (type: double) + | Map-reduce partition columns:UDFToDouble(key) (type: double) + | sort order:+ + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + | value expressions:key (type: string), val (type: string) + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_3] + key expressions:(key + 1) (type: double) + Map-reduce partition columns:(key + 1) (type: double) + sort order:+ + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + value expressions:key (type: string) + TableScan [TS_1] + alias:c + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key +POSTHOOK: type: QUERY +CBO failed, skipping CBO. org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException: Hint specified for /*+ mapjoin(v)*/. Currently we don't support hints in CBO, turn off cbo to use hints. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_11] + compressed:true + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_9] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + sort order: + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint), _col1 (type: bigint) + Group By Operator [OP_16] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_6] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + value expressions:hash(_col0) (type: int), hash(_col6) (type: int) + Map Join Operator [MAPJOIN_14] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"Map 1":"(key + 1) (type: double)","Map 4":"UDFToDouble(key) (type: double)"} + | outputColumnNames:["_col0","_col6"] + | Statistics:Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:UDFToDouble(key) (type: double) + | Map-reduce partition columns:UDFToDouble(key) (type: double) + | sort order:+ + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + | value expressions:val (type: string) + | TableScan [TS_1] + | alias:v + | Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE + |<-TableScan [TS_0] + alias:k + Statistics:Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE +PREHOOK: query: explain select * +from src b +where exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_9' + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src b +where exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_9' + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_15] + compressed:true + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_20] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col1 (type: string), _col0 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col1 (type: string), _col0 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_18] + | predicate:(value is not null and key is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_8] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] + predicate:((value > 'val_9') and key is not null) (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain select * +from src b +where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select * +from src b +where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:true + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_19] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"1":"_col0 (type: string), _col1 (type: string)","0":"_col0 (type: string), _col1 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_17] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_7] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_18] + predicate:((key > '9') and value is not null) (type: boolean) + Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p_name, p_size +from +part where part.p_size in + (select avg(p_size) + from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a + where r <= 2 + ) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p_name, p_size +from +part where part.p_size in + (select avg(p_size) + from (select p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a + where r <= 2 + ) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 3 <- Map 2 (SIMPLE_EDGE) +Map 1 <- Reducer 5 (BROADCAST_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_27] + compressed:true + Statistics:Num rows: 28 Data size: 3803 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Map Join Operator [MAPJOIN_33] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"Map 1":"_col2 (type: double)","Reducer 5":"_col0 (type: double)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 28 Data size: 3803 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [BROADCAST_EDGE] + | Reduce Output Operator [RS_24] + | key expressions:_col0 (type: double) + | Map-reduce partition columns:_col0 (type: double) + | sort order:+ + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Group By Operator [GBY_20] + | keys:_col0 (type: double) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + | Filter Operator [FIL_31] + | predicate:_col0 is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_17] + | | aggregations:["avg(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_16] + | sort order: + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | value expressions:_col0 (type: struct) + | Group By Operator [GBY_15] + | | aggregations:["avg(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_14] + | Map-reduce partition columns:rand() (type: double) + | sort order: + | Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: int) + | Select Operator [SEL_9] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_32] + | predicate:(_wcol0 <= 2) (type: boolean) + | Statistics:Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + | PTF Operator [PTF_8] + | Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"partition by:":"_col0","name:":"windowingtablefunction","order by:":"_col1"}] + | Statistics:Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_7] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int) + | Map-reduce partition columns:_col0 (type: string) + | sort order:++ + | Statistics:Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_4] + | alias:part + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + |<-Filter Operator [FIL_30] + predicate:_col2 is not null (type: boolean) + Statistics:Num rows: 26 Data size: 3458 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 26 Data size: 3458 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain + select count(1) FROM (select s1.key as key, s1.value as value from src s1 UNION + select s2.key as key, s2.value as value from src s2) unionsrc +PREHOOK: type: QUERY +POSTHOOK: query: explain + select count(1) FROM (select s1.key as key, s1.value as value from src s1 UNION + select s2.key as key, s2.value as value from src s2) unionsrc +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Map 1 <- Union 2 (CONTAINS) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Map 7 <- Union 2 (CONTAINS) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 6 + File Output Operator [FS_19] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_17] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_35] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col0 (type: bigint) + Group By Operator [OP_34] + | aggregations:["count(1)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_14] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator [SEL_11] + Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [GBY_10] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 500 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_33] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 1000 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator [OP_32] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1000 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + |<-Union 2 [SIMPLE_EDGE] + |<-Map 1 [CONTAINS] + | Reduce Output Operator [RS_7] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:rand() (type: double) + | sort order:++ + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | TableScan [TS_0] + | alias:s1 + |<-Map 7 [CONTAINS] + Reduce Output Operator [RS_7] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:rand() (type: double) + sort order:++ + Select Operator [SEL_3] + outputColumnNames:["_col0","_col1"] + TableScan [TS_2] + alias:s1 +PREHOOK: query: explain +select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR') +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Map 1 <- Map 2 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_29] + compressed:true + Statistics:Num rows: 55 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_27] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 55 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Map Join Operator [MAPJOIN_39] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"_col1 (type: int)","Reducer 5":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 55 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Reducer 5 [BROADCAST_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 50 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Group By Operator [GBY_13] + | | keys:KEY._col0 (type: int) + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 50 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | |<-Reducer 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_43] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 100 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Group By Operator [OP_42] + | | keys:KEY._col0 (type: int) + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 100 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:rand() (type: double) + | sort order:+ + | Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_8] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_37] + | predicate:l_partkey is not null (type: boolean) + | Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_7] + | alias:lineitem + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map Join Operator [MAPJOIN_38] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"Map 1":"_col0 (type: int)","Map 2":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_16] + | keys:_col0 (type: int) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_36] + | predicate:((l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean) + | Statistics:Num rows: 14 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:lineitem + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 16 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_35] + predicate:(((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) + Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:lineitem + Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: explain +select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select p.p_partkey, li.l_suppkey +from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey +where li.l_linenumber = 1 and + li.l_orderkey in (select l_orderkey from lineitem where l_shipmode = 'AIR' and l_linenumber = li.l_linenumber) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Map 1 <- Map 2 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_29] + compressed:true + Statistics:Num rows: 55 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_27] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 55 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Map Join Operator [MAPJOIN_39] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"_col1 (type: int)","Reducer 5":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 55 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Reducer 5 [BROADCAST_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 50 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Group By Operator [GBY_13] + | | keys:KEY._col0 (type: int) + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 50 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | |<-Reducer 4 [SIMPLE_EDGE] + | Reduce Output Operator [RS_43] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 100 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | Group By Operator [OP_42] + | | keys:KEY._col0 (type: int) + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 100 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE + | |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:rand() (type: double) + | sort order:+ + | Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_8] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_37] + | predicate:l_partkey is not null (type: boolean) + | Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_7] + | alias:lineitem + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map Join Operator [MAPJOIN_38] + | condition map:[{"":"Left Semi Join 0 to 1"}] + | keys:{"Map 1":"_col0 (type: int), _col3 (type: int)","Map 2":"_col0 (type: int), _col1 (type: int)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col0 (type: int), _col1 (type: int) + | Map-reduce partition columns:_col0 (type: int), _col1 (type: int) + | sort order:++ + | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_16] + | keys:_col0 (type: int), _col1 (type: int) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_36] + | predicate:(((l_shipmode = 'AIR') and l_orderkey is not null) and l_linenumber is not null) (type: boolean) + | Statistics:Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:lineitem + | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + |<-Select Operator [SEL_2] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_35] + predicate:(((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) + Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_0] + alias:lineitem + Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE +PREHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) +CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@bucket_small +POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) +CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@bucket_small +PREHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_small +POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_small +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_small@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_small@ds=2008-04-08 +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@bucket_big +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@bucket_big +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: explain select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 3 <- Map 2 (SIMPLE_EDGE) +Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_9] + | aggregations:["count()"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Map 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"key (type: string)","Map 2":"key (type: string)"} + | Statistics:Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [BROADCAST_EDGE] + | Reduce Output Operator [RS_3] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_16] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:a + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + |<-Filter Operator [FIL_17] + predicate:key is not null (type: boolean) + Statistics:Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_1] + alias:b + Statistics:Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_9] + | aggregations:["count()"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"key (type: string)","Map 4":"key (type: string)"} + | Statistics:Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_17] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + |<-Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:a + Statistics:Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +Map 1 <- Map 4 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 + File Output Operator [FS_13] + compressed:true + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_11] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_9] + | aggregations:["count()"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + Map-reduce partition columns:rand() (type: double) + sort order: + Statistics:Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_18] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"key (type: string)","Map 4":"key (type: string)"} + | Statistics:Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_5] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_17] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:b + | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + |<-Filter Operator [FIL_16] + predicate:key is not null (type: boolean) + Statistics:Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:a + Statistics:Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/explainuser_2.q.out b/ql/src/test/results/clientpositive/tez/explainuser_2.q.out new file mode 100644 index 0000000..e1094fc --- /dev/null +++ b/ql/src/test/results/clientpositive/tez/explainuser_2.q.out @@ -0,0 +1,2755 @@ +PREHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest_j1 +POSTHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest_j1 +PREHOOK: query: CREATE TABLE ss(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss +POSTHOOK: query: CREATE TABLE ss(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss +PREHOOK: query: CREATE TABLE sr(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@sr +POSTHOOK: query: CREATE TABLE sr(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@sr +PREHOOK: query: CREATE TABLE cs(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@cs +POSTHOOK: query: CREATE TABLE cs(k1 STRING,v1 STRING,k2 STRING,v2 STRING,k3 STRING,v3 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@cs +PREHOOK: query: INSERT OVERWRITE TABLE ss +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Output: default@ss +POSTHOOK: query: INSERT OVERWRITE TABLE ss +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Output: default@ss +POSTHOOK: Lineage: ss.k1 SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: ss.k2 SIMPLE [(src)y.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: ss.k3 EXPRESSION [(srcpart)z.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: ss.v1 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: ss.v2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: ss.v3 EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: INSERT OVERWRITE TABLE sr +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=12) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@sr +POSTHOOK: query: INSERT OVERWRITE TABLE sr +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=12) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@sr +POSTHOOK: Lineage: sr.k1 SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: sr.k2 SIMPLE [(src)y.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: sr.k3 EXPRESSION [(srcpart)z.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: sr.v1 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: sr.v2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: sr.v3 EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: INSERT OVERWRITE TABLE cs +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08') +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@cs +POSTHOOK: query: INSERT OVERWRITE TABLE cs +SELECT x.key,x.value,y.key,y.value,z.key,z.value +FROM src1 x +JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08') +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@cs +POSTHOOK: Lineage: cs.k1 SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: cs.k2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: cs.k3 SIMPLE [(srcpart)z.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: cs.v1 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: cs.v2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: cs.v3 SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss +POSTHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss +PREHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE ss COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +#### A masked pattern was here #### +PREHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS +PREHOOK: type: QUERY +PREHOOK: Input: default@sr +PREHOOK: Output: default@sr +POSTHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS +POSTHOOK: type: QUERY +POSTHOOK: Input: default@sr +POSTHOOK: Output: default@sr +PREHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 +PREHOOK: type: QUERY +PREHOOK: Input: default@sr +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE sr COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@sr +#### A masked pattern was here #### +PREHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS +PREHOOK: type: QUERY +PREHOOK: Input: default@cs +PREHOOK: Output: default@cs +POSTHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cs +POSTHOOK: Output: default@cs +PREHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 +PREHOOK: type: QUERY +PREHOOK: Input: default@cs +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE cs COMPUTE STATISTICS FOR COLUMNS k1,v1,k2,v2,k3,v3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cs +#### A masked pattern was here #### +PREHOOK: query: EXPLAIN +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_20] + compressed:false + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_14] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_26] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + key expressions:_col3 (type: string) + Map-reduce partition columns:_col3 (type: string) + sort order:+ + Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string) + Merge Join Operator [MERGEJOIN_29] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col3"] + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_4] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_27] + | predicate:value is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_2] + | alias:z + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_10] + key expressions:_col1 (type: string) + Map-reduce partition columns:_col1 (type: string) + sort order:+ + Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string) + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_28] + predicate:(value is not null and key is not null) (type: boolean) + Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_5] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: EXPLAIN +select +ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) +FROM +ss,sr,cs,src d1,src d2,src d3,src1,srcpart +where + ss.k1 = d1.key +and sr.k1 = d2.key +and cs.k1 = d3.key +and ss.k2 = sr.k2 +and ss.k3 = sr.k3 +and ss.v1 = src1.value +and ss.v2 = srcpart.value +and sr.v2 = cs.v2 +and sr.v3 = cs.v3 +and ss.v3='ssv3' +and sr.v1='srv1' +and src1.key = 'src1key' +and srcpart.key = 'srcpartkey' +and d1.value = 'd1value' +and d2.value in ('2000Q1','2000Q2','2000Q3') +and d3.value in ('2000Q1','2000Q2','2000Q3') +group by +ss.k1,sr.k2,cs.k3 +order by +ss.k1,sr.k2,cs.k3 +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +select +ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) +FROM +ss,sr,cs,src d1,src d2,src d3,src1,srcpart +where + ss.k1 = d1.key +and sr.k1 = d2.key +and cs.k1 = d3.key +and ss.k2 = sr.k2 +and ss.k3 = sr.k3 +and ss.v1 = src1.value +and ss.v2 = srcpart.value +and sr.v2 = cs.v2 +and sr.v3 = cs.v3 +and ss.v3='ssv3' +and sr.v1='srv1' +and src1.key = 'src1key' +and srcpart.key = 'srcpartkey' +and d1.value = 'd1value' +and d2.value in ('2000Q1','2000Q2','2000Q3') +and d3.value in ('2000Q1','2000Q2','2000Q3') +group by +ss.k1,sr.k2,cs.k3 +order by +ss.k1,sr.k2,cs.k3 +limit 100 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 9 <- Reducer 16 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 5 + File Output Operator [FS_72] + compressed:false + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_71] + Number of rows:100 + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_70] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_69] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_67] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_66] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_65] + aggregations:["count(_col3)","count(_col4)","count(_col5)"] + keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_62] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_114] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col15 (type: string), _col17 (type: string)","0":"_col1 (type: string), _col3 (type: string)"} + | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] + | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_58] + | key expressions:_col1 (type: string), _col3 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col2 (type: string) + | Merge Join Operator [MERGEJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 1 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_53] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_100] + | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_0] + | | alias:cs + | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE + | |<-Map 6 [SIMPLE_EDGE] + | Reduce Output Operator [RS_55] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_4] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_101] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_2] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_60] + key expressions:_col15 (type: string), _col17 (type: string) + Map-reduce partition columns:_col15 (type: string), _col17 (type: string) + sort order:++ + Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + value expressions:_col6 (type: string), _col7 (type: string), _col14 (type: string) + Select Operator [SEL_51] + outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_113] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col2 (type: string), _col4 (type: string)","0":"_col8 (type: string), _col10 (type: string)"} + | outputColumnNames:["_col6","_col7","_col14","_col15","_col17"] + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 16 [SIMPLE_EDGE] + | Reduce Output Operator [RS_49] + | key expressions:_col2 (type: string), _col4 (type: string) + | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: string), _col5 (type: string) + | Merge Join Operator [MERGEJOIN_112] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 15 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_36] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + | | Select Operator [SEL_31] + | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_106] + | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_29] + | | alias:sr + | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | |<-Map 17 [SIMPLE_EDGE] + | Reduce Output Operator [RS_38] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_34] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_107] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_32] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_47] + key expressions:_col8 (type: string), _col10 (type: string) + Map-reduce partition columns:_col8 (type: string), _col10 (type: string) + sort order:++ + Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + value expressions:_col6 (type: string), _col7 (type: string) + Merge Join Operator [MERGEJOIN_111] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col5 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col6","_col7","_col8","_col10"] + | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_42] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_7] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_102] + | predicate:((key = 'src1key') and value is not null) (type: boolean) + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_5] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 11 [SIMPLE_EDGE] + Reduce Output Operator [RS_44] + key expressions:_col5 (type: string) + Map-reduce partition columns:_col5 (type: string) + sort order:+ + Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: string), _col6 (type: string), _col8 (type: string) + Merge Join Operator [MERGEJOIN_110] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col2 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col4","_col5","_col6","_col8"] + | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_24] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_103] + | predicate:((value = 'd1value') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_8] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 13 [SIMPLE_EDGE] + Reduce Output Operator [RS_26] + key expressions:_col2 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:+ + Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) + Merge Join Operator [MERGEJOIN_109] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col3 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 12 [SIMPLE_EDGE] + | Reduce Output Operator [RS_18] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_13] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_104] + | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_11] + | alias:srcpart + | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + |<-Map 14 [SIMPLE_EDGE] + Reduce Output Operator [RS_20] + key expressions:_col3 (type: string) + Map-reduce partition columns:_col3 (type: string) + sort order:+ + Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + Select Operator [SEL_16] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_105] + predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) + Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_14] + alias:ss + Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 13 <- Union 12 (SIMPLE_EDGE) +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE), Union 5 (CONTAINS) +Map 11 <- Union 12 (CONTAINS) +Map 1 <- Union 2 (CONTAINS) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE), Union 5 (CONTAINS) +Map 7 <- Union 2 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE) +Reducer 9 <- Map 10 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 17 <- Map 16 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE) +Map 15 <- Union 12 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 6 + File Output Operator [FS_63] + compressed:false + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_61] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + |<-Union 5 [SIMPLE_EDGE] + |<-Reducer 14 [CONTAINS] + | Reduce Output Operator [RS_60] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_59] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_54] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_87] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col2 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col0","_col2"] + | |<-Reducer 13 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_50] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_38] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_37] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 12 [SIMPLE_EDGE] + | | |<-Map 11 [CONTAINS] + | | | Reduce Output Operator [RS_36] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_35] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_29] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_80] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_28] + | | | alias:x + | | |<-Map 15 [CONTAINS] + | | Reduce Output Operator [RS_36] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_35] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_31] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_81] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_30] + | | alias:y + | |<-Reducer 17 [SIMPLE_EDGE] + | Reduce Output Operator [RS_52] + | key expressions:_col2 (type: string) + | Map-reduce partition columns:_col2 (type: string) + | sort order:+ + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Merge Join Operator [MERGEJOIN_85] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2"] + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | |<-Map 16 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_44] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_40] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_82] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_39] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Map 18 [SIMPLE_EDGE] + | Reduce Output Operator [RS_46] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_42] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_83] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_41] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [CONTAINS] + Reduce Output Operator [RS_60] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_59] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_86] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col2 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col2"] + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | |<-Union 2 [SIMPLE_EDGE] + | |<-Map 1 [CONTAINS] + | | Reduce Output Operator [RS_8] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_7] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_76] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_0] + | | alias:x + | |<-Map 7 [CONTAINS] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_7] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_77] + | predicate:value is not null (type: boolean) + | TableScan [TS_2] + | alias:y + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_24] + key expressions:_col2 (type: string) + Map-reduce partition columns:_col2 (type: string) + sort order:+ + Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: string) + Merge Join Operator [MERGEJOIN_84] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2"] + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_18] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_14] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_79] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_13] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_12] + outputColumnNames:["_col0"] + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_78] + predicate:key is not null (type: boolean) + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_11] + alias:y + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 31 <- Reducer 30 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE), Union 7 (CONTAINS) +Reducer 22 <- Map 21 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE) +Map 24 <- Union 25 (CONTAINS) +Map 32 <- Union 25 (CONTAINS) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 30 <- Union 29 (SIMPLE_EDGE) +Map 13 <- Union 14 (CONTAINS) +Map 34 <- Union 29 (CONTAINS) +Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE) +Map 1 <- Union 2 (CONTAINS) +Map 20 <- Union 16 (CONTAINS) +Map 33 <- Union 27 (CONTAINS) +Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Map 19 <- Union 14 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) +Reducer 26 <- Union 25 (SIMPLE_EDGE), Union 27 (CONTAINS) +Reducer 17 <- Union 16 (SIMPLE_EDGE) +Reducer 8 <- Union 7 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE), Union 16 (CONTAINS) +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Map 9 <- Union 2 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 8 + File Output Operator [FS_125] + compressed:false + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_123] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + |<-Union 7 [SIMPLE_EDGE] + |<-Reducer 31 [CONTAINS] + | Reduce Output Operator [RS_122] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_121] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_116] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_167] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3"] + | |<-Reducer 30 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_112] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_100] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_99] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 29 [SIMPLE_EDGE] + | | |<-Map 34 [CONTAINS] + | | | Reduce Output Operator [RS_98] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_97] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_93] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_159] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_92] + | | | alias:y + | | |<-Reducer 28 [CONTAINS] + | | Reduce Output Operator [RS_98] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_97] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Group By Operator [GBY_90] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | |<-Union 27 [SIMPLE_EDGE] + | | |<-Map 33 [CONTAINS] + | | | Reduce Output Operator [RS_89] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_88] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_84] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_158] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_83] + | | | alias:y + | | |<-Reducer 26 [CONTAINS] + | | Reduce Output Operator [RS_89] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_88] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Group By Operator [GBY_81] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | |<-Union 25 [SIMPLE_EDGE] + | | |<-Map 24 [CONTAINS] + | | | Reduce Output Operator [RS_80] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_79] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_73] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_156] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_72] + | | | alias:x + | | |<-Map 32 [CONTAINS] + | | Reduce Output Operator [RS_80] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_79] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_75] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_157] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_74] + | | alias:y + | |<-Reducer 36 [SIMPLE_EDGE] + | Reduce Output Operator [RS_114] + | key expressions:_col3 (type: string) + | Map-reduce partition columns:_col3 (type: string) + | sort order:+ + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string), _col2 (type: string) + | Merge Join Operator [MERGEJOIN_164] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | |<-Map 35 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_106] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_102] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_160] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_101] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Map 37 [SIMPLE_EDGE] + | Reduce Output Operator [RS_108] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_104] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_161] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_103] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [CONTAINS] + Reduce Output Operator [RS_122] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_121] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Group By Operator [GBY_70] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + |<-Union 5 [SIMPLE_EDGE] + |<-Reducer 4 [CONTAINS] + | Reduce Output Operator [RS_69] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_68] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_26] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_165] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3"] + | |<-Reducer 11 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_24] + | | key expressions:_col3 (type: string) + | | Map-reduce partition columns:_col3 (type: string) + | | sort order:+ + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string), _col2 (type: string) + | | Merge Join Operator [MERGEJOIN_162] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | | outputColumnNames:["_col1","_col2","_col3"] + | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 10 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_16] + | | | key expressions:_col0 (type: string) + | | | Map-reduce partition columns:_col0 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:_col1 (type: string) + | | | Select Operator [SEL_12] + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_149] + | | | predicate:key is not null (type: boolean) + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_11] + | | | alias:y + | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 12 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_18] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_14] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_150] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_13] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | |<-Union 2 [SIMPLE_EDGE] + | |<-Map 1 [CONTAINS] + | | Reduce Output Operator [RS_8] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_7] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_147] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_0] + | | alias:x + | |<-Map 9 [CONTAINS] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_7] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_148] + | predicate:value is not null (type: boolean) + | TableScan [TS_2] + | alias:y + |<-Reducer 18 [CONTAINS] + Reduce Output Operator [RS_69] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_68] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_63] + outputColumnNames:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_166] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col2","_col3"] + |<-Reducer 17 [SIMPLE_EDGE] + | Reduce Output Operator [RS_59] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_47] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_46] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | |<-Union 16 [SIMPLE_EDGE] + | |<-Map 20 [CONTAINS] + | | Reduce Output Operator [RS_45] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_44] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_40] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_153] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_39] + | | alias:y + | |<-Reducer 15 [CONTAINS] + | Reduce Output Operator [RS_45] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_44] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Group By Operator [GBY_37] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | |<-Union 14 [SIMPLE_EDGE] + | |<-Map 13 [CONTAINS] + | | Reduce Output Operator [RS_36] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_35] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_29] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_151] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_28] + | | alias:x + | |<-Map 19 [CONTAINS] + | Reduce Output Operator [RS_36] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_35] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_31] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_152] + | predicate:value is not null (type: boolean) + | TableScan [TS_30] + | alias:y + |<-Reducer 22 [SIMPLE_EDGE] + Reduce Output Operator [RS_61] + key expressions:_col3 (type: string) + Map-reduce partition columns:_col3 (type: string) + sort order:+ + Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: string), _col2 (type: string) + Merge Join Operator [MERGEJOIN_163] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3"] + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + |<-Map 21 [SIMPLE_EDGE] + | Reduce Output Operator [RS_53] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_49] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_154] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_48] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map 23 [SIMPLE_EDGE] + Reduce Output Operator [RS_55] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: string) + Select Operator [SEL_51] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_155] + predicate:(key is not null and value is not null) (type: boolean) + Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_50] + alias:x + Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: EXPLAIN +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Map 2 <- Map 1 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 2 + File Output Operator [FS_20] + compressed:false + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_30] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col3 (type: string)"} + | outputColumnNames:["_col1","_col2","_col5"] + | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [BROADCAST_EDGE] + | Reduce Output Operator [RS_14] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_26] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map Join Operator [MAPJOIN_29] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 2":"_col0 (type: string)","Map 3":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col3"] + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string) + | Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_28] + | predicate:(value is not null and key is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_5] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_4] + outputColumnNames:["_col0"] + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_27] + predicate:value is not null (type: boolean) + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:z + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: EXPLAIN +select +ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) +FROM +ss,sr,cs,src d1,src d2,src d3,src1,srcpart +where + ss.k1 = d1.key +and sr.k1 = d2.key +and cs.k1 = d3.key +and ss.k2 = sr.k2 +and ss.k3 = sr.k3 +and ss.v1 = src1.value +and ss.v2 = srcpart.value +and sr.v2 = cs.v2 +and sr.v3 = cs.v3 +and ss.v3='ssv3' +and sr.v1='srv1' +and src1.key = 'src1key' +and srcpart.key = 'srcpartkey' +and d1.value = 'd1value' +and d2.value in ('2000Q1','2000Q2','2000Q3') +and d3.value in ('2000Q1','2000Q2','2000Q3') +group by +ss.k1,sr.k2,cs.k3 +order by +ss.k1,sr.k2,cs.k3 +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +select +ss.k1,sr.k2,cs.k3,count(ss.v1),count(sr.v2),count(cs.v3) +FROM +ss,sr,cs,src d1,src d2,src d3,src1,srcpart +where + ss.k1 = d1.key +and sr.k1 = d2.key +and cs.k1 = d3.key +and ss.k2 = sr.k2 +and ss.k3 = sr.k3 +and ss.v1 = src1.value +and ss.v2 = srcpart.value +and sr.v2 = cs.v2 +and sr.v3 = cs.v3 +and ss.v3='ssv3' +and sr.v1='srv1' +and src1.key = 'src1key' +and srcpart.key = 'srcpartkey' +and d1.value = 'd1value' +and d2.value in ('2000Q1','2000Q2','2000Q3') +and d3.value in ('2000Q1','2000Q2','2000Q3') +group by +ss.k1,sr.k2,cs.k3 +order by +ss.k1,sr.k2,cs.k3 +limit 100 +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Map 2 <- Map 1 (BROADCAST_EDGE) +Map 10 <- Map 9 (BROADCAST_EDGE) +Map 5 <- Map 10 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 7 + File Output Operator [FS_72] + compressed:false + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Limit [LIM_71] + Number of rows:100 + Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_70] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_69] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_67] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Map 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_66] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_65] + aggregations:["count(_col3)","count(_col4)","count(_col5)"] + keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_62] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_114] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 2":"_col1 (type: string), _col3 (type: string)","Map 5":"_col15 (type: string), _col17 (type: string)"} + | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] + | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_58] + | key expressions:_col1 (type: string), _col3 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col2 (type: string) + | Map Join Operator [MAPJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 1 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_53] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_100] + | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_0] + | | alias:cs + | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_4] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_101] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_2] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_51] + outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_113] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 10":"_col2 (type: string), _col4 (type: string)","Map 5":"_col8 (type: string), _col10 (type: string)"} + | outputColumnNames:["_col6","_col7","_col14","_col15","_col17"] + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [BROADCAST_EDGE] + | Reduce Output Operator [RS_49] + | key expressions:_col2 (type: string), _col4 (type: string) + | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: string), _col5 (type: string) + | Map Join Operator [MAPJOIN_112] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 10":"_col0 (type: string)","Map 9":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 9 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_36] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + | | Select Operator [SEL_31] + | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_106] + | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_29] + | | alias:sr + | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_34] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_107] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_32] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map Join Operator [MAPJOIN_111] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 3":"_col1 (type: string)","Map 5":"_col5 (type: string)"} + | outputColumnNames:["_col6","_col7","_col8","_col10"] + | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_42] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_7] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_102] + | predicate:((key = 'src1key') and value is not null) (type: boolean) + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_5] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Map Join Operator [MAPJOIN_110] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 5":"_col2 (type: string)","Map 4":"_col0 (type: string)"} + | outputColumnNames:["_col4","_col5","_col6","_col8"] + | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [BROADCAST_EDGE] + | Reduce Output Operator [RS_24] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_103] + | predicate:((value = 'd1value') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_8] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map Join Operator [MAPJOIN_109] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 5":"_col1 (type: string)","Map 8":"_col3 (type: string)"} + | outputColumnNames:["_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 8 [BROADCAST_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col3 (type: string) + | Map-reduce partition columns:_col3 (type: string) + | sort order:+ + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + | Select Operator [SEL_16] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_105] + | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_14] + | alias:ss + | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_13] + outputColumnNames:["_col1"] + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_104] + predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_11] + alias:srcpart + Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, z.value, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Map 12 <- Union 10 (CONTAINS) +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Reducer 11 <- Union 10 (SIMPLE_EDGE) +Map 13 <- Map 14 (BROADCAST_EDGE), Reducer 11 (BROADCAST_EDGE), Union 6 (CONTAINS) +Map 1 <- Union 2 (CONTAINS) +Map 5 <- Map 8 (BROADCAST_EDGE), Reducer 3 (BROADCAST_EDGE), Union 6 (CONTAINS) +Map 4 <- Union 2 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Map 9 <- Union 10 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 7 + File Output Operator [FS_63] + compressed:false + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_61] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + |<-Union 6 [SIMPLE_EDGE] + |<-Map 13 [CONTAINS] + | Reduce Output Operator [RS_60] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_59] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_54] + | outputColumnNames:["_col0","_col1"] + | Map Join Operator [MAPJOIN_87] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Reducer 11":"_col0 (type: string)","Map 13":"_col2 (type: string)"} + | | outputColumnNames:["_col0","_col2"] + | |<-Reducer 11 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_50] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_38] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_37] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 10 [SIMPLE_EDGE] + | | |<-Map 12 [CONTAINS] + | | | Reduce Output Operator [RS_36] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_35] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_31] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_81] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_30] + | | | alias:y + | | |<-Map 9 [CONTAINS] + | | Reduce Output Operator [RS_36] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_35] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_29] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_80] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_28] + | | alias:x + | |<-Map Join Operator [MAPJOIN_85] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 14":"_col0 (type: string)","Map 13":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2"] + | |<-Map 14 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_46] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_42] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_83] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_41] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_40] + | outputColumnNames:["_col0"] + | Filter Operator [FIL_82] + | predicate:key is not null (type: boolean) + | TableScan [TS_39] + | alias:y + |<-Map 5 [CONTAINS] + Reduce Output Operator [RS_60] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_59] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1"] + Map Join Operator [MAPJOIN_86] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Reducer 3":"_col0 (type: string)","Map 5":"_col2 (type: string)"} + | outputColumnNames:["_col0","_col2"] + |<-Reducer 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | |<-Union 2 [SIMPLE_EDGE] + | |<-Map 1 [CONTAINS] + | | Reduce Output Operator [RS_8] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_7] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_76] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_0] + | | alias:x + | |<-Map 4 [CONTAINS] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_7] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_77] + | predicate:value is not null (type: boolean) + | TableScan [TS_2] + | alias:y + |<-Map Join Operator [MAPJOIN_84] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 5":"_col0 (type: string)","Map 8":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2"] + |<-Map 8 [BROADCAST_EDGE] + | Reduce Output Operator [RS_18] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_14] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_79] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_13] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_12] + outputColumnNames:["_col0"] + Filter Operator [FIL_78] + predicate:key is not null (type: boolean) + TableScan [TS_11] + alias:y +PREHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 22 <- Union 21 (SIMPLE_EDGE), Union 23 (CONTAINS) +Reducer 13 <- Union 12 (SIMPLE_EDGE), Union 14 (CONTAINS) +Map 30 <- Map 31 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE), Union 8 (CONTAINS) +Map 11 <- Union 12 (CONTAINS) +Reducer 24 <- Union 23 (SIMPLE_EDGE), Union 25 (CONTAINS) +Map 1 <- Union 2 (CONTAINS) +Map 20 <- Union 21 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) +Reducer 9 <- Union 8 (SIMPLE_EDGE) +Reducer 26 <- Union 25 (SIMPLE_EDGE) +Map 16 <- Union 12 (CONTAINS) +Map 29 <- Union 25 (CONTAINS) +Map 28 <- Union 23 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE) +Map 18 <- Map 19 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Union 6 (CONTAINS) +Map 27 <- Union 21 (CONTAINS) +Map 17 <- Union 14 (CONTAINS) +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Map 5 <- Map 10 (BROADCAST_EDGE), Reducer 3 (BROADCAST_EDGE), Union 6 (CONTAINS) +Map 4 <- Union 2 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 9 + File Output Operator [FS_125] + compressed:false + Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_123] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + |<-Union 8 [SIMPLE_EDGE] + |<-Map 30 [CONTAINS] + | Reduce Output Operator [RS_122] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_121] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_116] + | outputColumnNames:["_col0","_col1"] + | Map Join Operator [MAPJOIN_167] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 30":"_col3 (type: string)","Reducer 26":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3"] + | |<-Reducer 26 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_112] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_100] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_99] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 25 [SIMPLE_EDGE] + | | |<-Reducer 24 [CONTAINS] + | | | Reduce Output Operator [RS_98] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_97] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Group By Operator [GBY_90] + | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | | outputColumnNames:["_col0","_col1"] + | | | |<-Union 23 [SIMPLE_EDGE] + | | | |<-Reducer 22 [CONTAINS] + | | | | Reduce Output Operator [RS_89] + | | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | | sort order:++ + | | | | Group By Operator [GBY_88] + | | | | keys:_col0 (type: string), _col1 (type: string) + | | | | outputColumnNames:["_col0","_col1"] + | | | | Group By Operator [GBY_81] + | | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | | | outputColumnNames:["_col0","_col1"] + | | | | |<-Union 21 [SIMPLE_EDGE] + | | | | |<-Map 20 [CONTAINS] + | | | | | Reduce Output Operator [RS_80] + | | | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | | | sort order:++ + | | | | | Group By Operator [GBY_79] + | | | | | keys:_col0 (type: string), _col1 (type: string) + | | | | | outputColumnNames:["_col0","_col1"] + | | | | | Select Operator [SEL_73] + | | | | | outputColumnNames:["_col0","_col1"] + | | | | | Filter Operator [FIL_156] + | | | | | predicate:value is not null (type: boolean) + | | | | | TableScan [TS_72] + | | | | | alias:x + | | | | |<-Map 27 [CONTAINS] + | | | | Reduce Output Operator [RS_80] + | | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | | sort order:++ + | | | | Group By Operator [GBY_79] + | | | | keys:_col0 (type: string), _col1 (type: string) + | | | | outputColumnNames:["_col0","_col1"] + | | | | Select Operator [SEL_75] + | | | | outputColumnNames:["_col0","_col1"] + | | | | Filter Operator [FIL_157] + | | | | predicate:value is not null (type: boolean) + | | | | TableScan [TS_74] + | | | | alias:y + | | | |<-Map 28 [CONTAINS] + | | | Reduce Output Operator [RS_89] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_88] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_84] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_158] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_83] + | | | alias:y + | | |<-Map 29 [CONTAINS] + | | Reduce Output Operator [RS_98] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_97] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_93] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_159] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_92] + | | alias:y + | |<-Map Join Operator [MAPJOIN_164] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 30":"_col0 (type: string)","Map 31":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | |<-Map 31 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_108] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_104] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_161] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_103] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_102] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_160] + | predicate:key is not null (type: boolean) + | TableScan [TS_101] + | alias:y + |<-Reducer 7 [CONTAINS] + Reduce Output Operator [RS_122] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_121] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Group By Operator [GBY_70] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + |<-Union 6 [SIMPLE_EDGE] + |<-Map 18 [CONTAINS] + | Reduce Output Operator [RS_69] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_68] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_63] + | outputColumnNames:["_col0","_col1"] + | Map Join Operator [MAPJOIN_166] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Reducer 15":"_col0 (type: string)","Map 18":"_col3 (type: string)"} + | | outputColumnNames:["_col2","_col3"] + | |<-Reducer 15 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_59] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_47] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_46] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 14 [SIMPLE_EDGE] + | | |<-Reducer 13 [CONTAINS] + | | | Reduce Output Operator [RS_45] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_44] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Group By Operator [GBY_37] + | | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | | outputColumnNames:["_col0","_col1"] + | | | |<-Union 12 [SIMPLE_EDGE] + | | | |<-Map 11 [CONTAINS] + | | | | Reduce Output Operator [RS_36] + | | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | | sort order:++ + | | | | Group By Operator [GBY_35] + | | | | keys:_col0 (type: string), _col1 (type: string) + | | | | outputColumnNames:["_col0","_col1"] + | | | | Select Operator [SEL_29] + | | | | outputColumnNames:["_col0","_col1"] + | | | | Filter Operator [FIL_151] + | | | | predicate:value is not null (type: boolean) + | | | | TableScan [TS_28] + | | | | alias:x + | | | |<-Map 16 [CONTAINS] + | | | Reduce Output Operator [RS_36] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_35] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_31] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_152] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_30] + | | | alias:y + | | |<-Map 17 [CONTAINS] + | | Reduce Output Operator [RS_45] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_44] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_40] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_153] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_39] + | | alias:y + | |<-Map Join Operator [MAPJOIN_163] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 19":"_col0 (type: string)","Map 18":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | |<-Map 19 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_55] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_51] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_155] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_50] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_49] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_154] + | predicate:key is not null (type: boolean) + | TableScan [TS_48] + | alias:y + |<-Map 5 [CONTAINS] + Reduce Output Operator [RS_69] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_68] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1"] + Map Join Operator [MAPJOIN_165] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Reducer 3":"_col0 (type: string)","Map 5":"_col3 (type: string)"} + | outputColumnNames:["_col2","_col3"] + |<-Reducer 3 [BROADCAST_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | |<-Union 2 [SIMPLE_EDGE] + | |<-Map 1 [CONTAINS] + | | Reduce Output Operator [RS_8] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_7] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_147] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_0] + | | alias:x + | |<-Map 4 [CONTAINS] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_7] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_148] + | predicate:value is not null (type: boolean) + | TableScan [TS_2] + | alias:y + |<-Map Join Operator [MAPJOIN_162] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 10":"_col0 (type: string)","Map 5":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3"] + |<-Map 10 [BROADCAST_EDGE] + | Reduce Output Operator [RS_18] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_14] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_150] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_13] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_12] + outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_149] + predicate:key is not null (type: boolean) + TableScan [TS_11] + alias:y +PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin +PREHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tab_part +POSTHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tab_part +PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin_part +PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin_part +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin_part +PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: Output: default@tab_part@ds=2008-04-08 +POSTHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin_part +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: Output: default@tab_part@ds=2008-04-08 +POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tab +POSTHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tab +PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: Output: default@tab@ds=2008-04-08 +POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +POSTHOOK: Output: default@tab@ds=2008-04-08 +POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: CREATE TABLE tab2(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tab2 +POSTHOOK: query: CREATE TABLE tab2(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tab2 +PREHOOK: query: insert overwrite table tab2 partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: Output: default@tab2@ds=2008-04-08 +POSTHOOK: query: insert overwrite table tab2 partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +POSTHOOK: Output: default@tab2@ds=2008-04-08 +POSTHOOK: Lineage: tab2 PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tab2 PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_13] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | + |<-Filter Operator [FIL_12] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:s3 + | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + |<-Filter Operator [FIL_11] + predicate:key is not null (type: boolean) + Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:s1 + Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 146 Data size: 1552 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_25] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"value (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 146 Data size: 1552 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: int) + | Merge Join Operator [MERGEJOIN_23] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"key (type: int)","0":"key (type: int)"} + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | | + | |<-Filter Operator [FIL_21] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_1] + | | alias:s3 + | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + | |<-Filter Operator [FIL_20] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 61 Data size: 646 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:s1 + | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:value (type: string) + Map-reduce partition columns:value (type: string) + sort order:+ + Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_22] + predicate:value is not null (type: boolean) + Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:s2 + Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Map 1 + File Output Operator [FS_8] + compressed:false + Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_13] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int)","0":"key (type: int)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | + |<-Filter Operator [FIL_12] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_1] + | alias:s3 + | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + |<-Filter Operator [FIL_11] + predicate:key is not null (type: boolean) + Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_0] + alias:s1 + Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key join tab2 s2 on s1.value=s2.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +select s1.key as key, s1.value as value from tab s1 join tab2 s3 on s1.key=s3.key join tab2 s2 on s1.value=s2.value +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 + File Output Operator [FS_14] + compressed:false + Statistics:Num rows: 146 Data size: 1552 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Merge Join Operator [MERGEJOIN_25] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"value (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 146 Data size: 1552 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_9] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: int) + | Merge Join Operator [MERGEJOIN_23] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"key (type: int)","0":"key (type: int)"} + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | | + | |<-Filter Operator [FIL_21] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_1] + | | alias:s3 + | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + | |<-Filter Operator [FIL_20] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 61 Data size: 646 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:s1 + | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + |<-Map 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_11] + key expressions:value (type: string) + Map-reduce partition columns:value (type: string) + sort order:+ + Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_22] + predicate:value is not null (type: boolean) + Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:s2 + Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE +PREHOOK: query: explain +select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key +UNION ALL +select s2.key as key, s2.value as value from tab s2 +) a join tab_part b on (a.key = b.key) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key +UNION ALL +select s2.key as key, s2.value as value from tab s2 +) a join tab_part b on (a.key = b.key) +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 3 <- Map 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) +Map 1 <- Union 2 (CONTAINS) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Map 6 <- Union 2 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 4 + File Output Operator [FS_22] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_20] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_18] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_35] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int)","0":"_col0 (type: int)"} + | Statistics:Num rows: 279 Data size: 2963 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_32] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_11] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Union 2 [SIMPLE_EDGE] + |<-Map 1 [CONTAINS] + | Reduce Output Operator [RS_13] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Merge Join Operator [MERGEJOIN_33] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"key (type: int)","0":"key (type: int)"} + | | outputColumnNames:["_col0"] + | | + | |<-Filter Operator [FIL_30] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_1] + | | alias:s3 + | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + | |<-Filter Operator [FIL_29] + | predicate:key is not null (type: boolean) + | TableScan [TS_0] + | alias:s1 + |<-Map 6 [CONTAINS] + Reduce Output Operator [RS_13] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Select Operator [SEL_9] + outputColumnNames:["_col0"] + Filter Operator [FIL_31] + predicate:key is not null (type: boolean) + TableScan [TS_8] + alias:s2 +PREHOOK: query: explain +select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value +UNION ALL +select s2.key as key, s2.value as value from tab s2 +) a join tab_part b on (a.key = b.key) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from (select s1.key as key, s1.value as value from tab s1 join tab s3 on s1.key=s3.key join tab s2 on s1.value=s2.value +UNION ALL +select s2.key as key, s2.value as value from tab s2 +) a join tab_part b on (a.key = b.key) +POSTHOOK: type: QUERY +CBO failed due to missing column stats (see previous errors), skipping CBO + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 9 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE) +Map 8 <- Union 3 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 5 + File Output Operator [FS_28] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_26] + | aggregations:["count(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_25] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_24] + aggregations:["count()"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_47] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: int)","0":"_col0 (type: int)"} + | Statistics:Num rows: 293 Data size: 3118 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:key (type: int) + | Map-reduce partition columns:key (type: int) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_43] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_17] + | alias:b + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Union 3 [SIMPLE_EDGE] + |<-Reducer 2 [CONTAINS] + | Reduce Output Operator [RS_19] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Merge Join Operator [MERGEJOIN_46] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"value (type: string)","0":"_col1 (type: string)"} + | | outputColumnNames:["_col0"] + | |<-Map 1 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_9] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: int) + | | Merge Join Operator [MERGEJOIN_44] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"key (type: int)","0":"key (type: int)"} + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE + | | | + | | |<-Filter Operator [FIL_40] + | | | predicate:key is not null (type: boolean) + | | | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_1] + | | | alias:s3 + | | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + | | |<-Filter Operator [FIL_39] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 61 Data size: 646 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_0] + | | alias:s1 + | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + | |<-Map 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_11] + | key expressions:value (type: string) + | Map-reduce partition columns:value (type: string) + | sort order:+ + | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_41] + | predicate:value is not null (type: boolean) + | Statistics:Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_2] + | alias:s2 + | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE + |<-Map 8 [CONTAINS] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Select Operator [SEL_15] + outputColumnNames:["_col0"] + Filter Operator [FIL_42] + predicate:key is not null (type: boolean) + TableScan [TS_14] + alias:s2 diff --git a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out new file mode 100644 index 0000000..323276d --- /dev/null +++ b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out @@ -0,0 +1,1744 @@ +PREHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 24 <- Map 23 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Union 14 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 13 <- Union 14 (CONTAINS) +Map 22 <- Union 18 (CONTAINS) +Map 21 <- Union 18 (CONTAINS) +Map 1 <- Union 2 (CONTAINS) +Map 20 <- Union 18 (CONTAINS) +Reducer 10 <- Map 12 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 19 <- Reducer 24 (SIMPLE_EDGE), Union 18 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 16 <- Union 14 (CONTAINS) +Map 15 <- Union 14 (CONTAINS) +Map 17 <- Union 18 (CONTAINS) +Reducer 3 <- Reducer 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 5 <- Union 2 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Union 4 + |<-Reducer 11 [CONTAINS] + | File Output Operator [FS_79] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Select Operator [SEL_46] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_120] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} + | | outputColumnNames:["_col0","_col3"] + | |<-Reducer 10 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_42] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: string), _col3 (type: string) + | | Merge Join Operator [MERGEJOIN_117] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | | outputColumnNames:["_col0","_col1","_col3"] + | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 12 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_39] + | | | key expressions:_col0 (type: string) + | | | Map-reduce partition columns:_col0 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:_col1 (type: string) + | | | Select Operator [SEL_26] + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_106] + | | | predicate:key is not null (type: boolean) + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_25] + | | | alias:y + | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 9 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_37] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_24] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_105] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_23] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Union 14 [SIMPLE_EDGE] + | |<-Map 13 [CONTAINS] + | | Reduce Output Operator [RS_44] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Select Operator [SEL_28] + | | outputColumnNames:["_col0"] + | | Filter Operator [FIL_107] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_27] + | | alias:x + | |<-Map 16 [CONTAINS] + | | Reduce Output Operator [RS_44] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Select Operator [SEL_34] + | | outputColumnNames:["_col0"] + | | Filter Operator [FIL_109] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_33] + | | alias:y + | |<-Map 15 [CONTAINS] + | Reduce Output Operator [RS_44] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Select Operator [SEL_30] + | outputColumnNames:["_col0"] + | Filter Operator [FIL_108] + | predicate:value is not null (type: boolean) + | TableScan [TS_29] + | alias:y + |<-Reducer 19 [CONTAINS] + | File Output Operator [FS_79] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Select Operator [SEL_76] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_121] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col4"] + | |<-Reducer 24 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_74] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: string), _col3 (type: string) + | | Merge Join Operator [MERGEJOIN_118] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | | outputColumnNames:["_col0","_col1","_col3"] + | | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 23 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_66] + | | | key expressions:_col0 (type: string) + | | | Map-reduce partition columns:_col0 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:_col1 (type: string) + | | | Select Operator [SEL_62] + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_114] + | | | predicate:(key is not null and value is not null) (type: boolean) + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_61] + | | | alias:x + | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 25 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_68] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_64] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_115] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_63] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Union 18 [SIMPLE_EDGE] + | |<-Map 22 [CONTAINS] + | | Reduce Output Operator [RS_72] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Select Operator [SEL_59] + | | outputColumnNames:["_col0"] + | | Filter Operator [FIL_113] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_58] + | | alias:y + | |<-Map 21 [CONTAINS] + | | Reduce Output Operator [RS_72] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Select Operator [SEL_56] + | | outputColumnNames:["_col0"] + | | Filter Operator [FIL_112] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_55] + | | alias:y + | |<-Map 20 [CONTAINS] + | | Reduce Output Operator [RS_72] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Select Operator [SEL_52] + | | outputColumnNames:["_col0"] + | | Filter Operator [FIL_111] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_51] + | | alias:y + | |<-Map 17 [CONTAINS] + | Reduce Output Operator [RS_72] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Select Operator [SEL_50] + | outputColumnNames:["_col0"] + | Filter Operator [FIL_110] + | predicate:value is not null (type: boolean) + | TableScan [TS_49] + | alias:x + |<-Reducer 3 [CONTAINS] + File Output Operator [FS_79] + compressed:false + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_119] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} + | outputColumnNames:["_col2","_col3"] + |<-Reducer 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | key expressions:_col3 (type: string) + | Map-reduce partition columns:_col3 (type: string) + | sort order:+ + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string), _col2 (type: string) + | Merge Join Operator [MERGEJOIN_116] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | |<-Map 6 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_11] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_7] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_103] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_6] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_9] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_104] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_8] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Union 2 [SIMPLE_EDGE] + |<-Map 1 [CONTAINS] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Select Operator [SEL_1] + | outputColumnNames:["_col0"] + | Filter Operator [FIL_101] + | predicate:value is not null (type: boolean) + | TableScan [TS_0] + | alias:x + |<-Map 5 [CONTAINS] + Reduce Output Operator [RS_17] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Select Operator [SEL_3] + outputColumnNames:["_col0"] + Filter Operator [FIL_102] + predicate:value is not null (type: boolean) + TableScan [TS_2] + alias:y +PREHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +PREHOOK: type: QUERY +POSTHOOK: query: explain +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +POSTHOOK: type: QUERY +CBO Succeeded + +Vertex dependency in root stage +Reducer 31 <- Reducer 30 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE), Union 7 (CONTAINS) +Map 24 <- Union 25 (CONTAINS) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Map 23 <- Union 20 (CONTAINS) +Map 32 <- Union 25 (CONTAINS) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 30 <- Union 29 (SIMPLE_EDGE) +Map 22 <- Union 18 (CONTAINS) +Map 34 <- Union 29 (CONTAINS) +Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE) +Map 1 <- Union 2 (CONTAINS) +Map 33 <- Union 27 (CONTAINS) +Reducer 21 <- Union 20 (SIMPLE_EDGE) +Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) +Reducer 26 <- Union 25 (SIMPLE_EDGE), Union 27 (CONTAINS) +Reducer 8 <- Union 7 (SIMPLE_EDGE) +Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE), Union 5 (CONTAINS) +Map 17 <- Union 18 (CONTAINS) +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Map 9 <- Union 2 (CONTAINS) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 8 + File Output Operator [FS_123] + compressed:false + Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_121] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + |<-Union 7 [SIMPLE_EDGE] + |<-Reducer 31 [CONTAINS] + | Reduce Output Operator [RS_120] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_119] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_114] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_165] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col1 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col4"] + | |<-Reducer 30 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_110] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_98] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_97] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 29 [SIMPLE_EDGE] + | | |<-Map 34 [CONTAINS] + | | | Reduce Output Operator [RS_96] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_95] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_91] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_157] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_90] + | | | alias:y + | | |<-Reducer 28 [CONTAINS] + | | Reduce Output Operator [RS_96] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_95] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Group By Operator [GBY_88] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | |<-Union 27 [SIMPLE_EDGE] + | | |<-Map 33 [CONTAINS] + | | | Reduce Output Operator [RS_87] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_86] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_82] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_156] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_81] + | | | alias:y + | | |<-Reducer 26 [CONTAINS] + | | Reduce Output Operator [RS_87] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_86] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Group By Operator [GBY_79] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | |<-Union 25 [SIMPLE_EDGE] + | | |<-Map 24 [CONTAINS] + | | | Reduce Output Operator [RS_78] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_77] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_71] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_154] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_70] + | | | alias:x + | | |<-Map 32 [CONTAINS] + | | Reduce Output Operator [RS_78] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_77] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_73] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_155] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_72] + | | alias:y + | |<-Reducer 36 [SIMPLE_EDGE] + | Reduce Output Operator [RS_112] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col3 (type: string) + | Merge Join Operator [MERGEJOIN_162] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col0","_col1","_col3"] + | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | |<-Map 35 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_104] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_100] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_158] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_99] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Map 37 [SIMPLE_EDGE] + | Reduce Output Operator [RS_106] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_102] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_159] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_101] + | alias:x + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [CONTAINS] + Reduce Output Operator [RS_120] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_119] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Group By Operator [GBY_68] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + |<-Union 5 [SIMPLE_EDGE] + |<-Reducer 4 [CONTAINS] + | Reduce Output Operator [RS_67] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_66] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_26] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_163] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col3 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3"] + | |<-Reducer 11 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_24] + | | key expressions:_col3 (type: string) + | | Map-reduce partition columns:_col3 (type: string) + | | sort order:+ + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string), _col2 (type: string) + | | Merge Join Operator [MERGEJOIN_160] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | | outputColumnNames:["_col1","_col2","_col3"] + | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 10 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_16] + | | | key expressions:_col0 (type: string) + | | | Map-reduce partition columns:_col0 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:_col1 (type: string) + | | | Select Operator [SEL_12] + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_147] + | | | predicate:key is not null (type: boolean) + | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_11] + | | | alias:y + | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 12 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_18] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_14] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_148] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_13] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_22] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | |<-Union 2 [SIMPLE_EDGE] + | |<-Map 1 [CONTAINS] + | | Reduce Output Operator [RS_8] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_7] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_145] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_0] + | | alias:x + | |<-Map 9 [CONTAINS] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_7] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_146] + | predicate:value is not null (type: boolean) + | TableScan [TS_2] + | alias:y + |<-Reducer 15 [CONTAINS] + Reduce Output Operator [RS_67] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_66] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_62] + outputColumnNames:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_164] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col0 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col3"] + |<-Reducer 14 [SIMPLE_EDGE] + | Reduce Output Operator [RS_58] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col3 (type: string) + | Merge Join Operator [MERGEJOIN_161] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col0 (type: string)","0":"_col0 (type: string)"} + | | outputColumnNames:["_col0","_col1","_col3"] + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | |<-Map 13 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_53] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_29] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_149] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_28] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Map 16 [SIMPLE_EDGE] + | Reduce Output Operator [RS_55] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_31] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_150] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_30] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 21 [SIMPLE_EDGE] + Reduce Output Operator [RS_60] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_51] + outputColumnNames:["_col0"] + Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_50] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + |<-Union 20 [SIMPLE_EDGE] + |<-Map 23 [CONTAINS] + | Reduce Output Operator [RS_49] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_48] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_44] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_153] + | predicate:value is not null (type: boolean) + | TableScan [TS_43] + | alias:y + |<-Reducer 19 [CONTAINS] + Reduce Output Operator [RS_49] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_48] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Group By Operator [GBY_41] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + |<-Union 18 [SIMPLE_EDGE] + |<-Map 22 [CONTAINS] + | Reduce Output Operator [RS_40] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_39] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_35] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_152] + | predicate:value is not null (type: boolean) + | TableScan [TS_34] + | alias:y + |<-Map 17 [CONTAINS] + Reduce Output Operator [RS_40] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_39] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_33] + outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_151] + predicate:value is not null (type: boolean) + TableScan [TS_32] + alias:x +PREHOOK: query: CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@a +POSTHOOK: query: CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@a +PREHOOK: query: CREATE TABLE b(key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@b +POSTHOOK: query: CREATE TABLE b(key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@b +PREHOOK: query: CREATE TABLE c(key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@c +POSTHOOK: query: CREATE TABLE c(key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@c +PREHOOK: query: explain +from +( +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +) tmp +INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +from +( +SELECT x.key, y.value +FROM src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union all select * from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +union all +SELECT x.key, y.value +FROM src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union all select key, value from src union all select key, value from src union all select key, value from src)z ON (x.value = z.value) +) tmp +INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value +POSTHOOK: type: QUERY +Not invoking CBO because the statement is not a query, CTAS, or insert + +Vertex dependency in root stage +Map 12 <- Union 10 (CONTAINS) +Reducer 24 <- Map 23 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE) +Reducer 11 <- Reducer 15 (SIMPLE_EDGE), Union 10 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 13 <- Union 10 (CONTAINS) +Map 22 <- Union 18 (CONTAINS) +Map 21 <- Union 18 (CONTAINS) +Map 1 <- Union 2 (CONTAINS) +Map 20 <- Union 18 (CONTAINS) +Reducer 7 <- Map 6 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 19 <- Reducer 24 (SIMPLE_EDGE), Union 18 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Map 17 <- Union 18 (CONTAINS) +Reducer 3 <- Reducer 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 5 <- Union 2 (CONTAINS) +Map 9 <- Union 10 (CONTAINS) + +Stage-7 + Stats-Aggr Operator + Stage-2 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-4 + Dependency Collection{} + Stage-3 + Union 4 + |<-Reducer 11 [CONTAINS] + | File Output Operator [FS_62] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Select Operator [SEL_37] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_107] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} + | | outputColumnNames:["_col0","_col6"] + | |<-Reducer 15 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_33] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_104] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"key (type: string)","0":"key (type: string)"} + | | | outputColumnNames:["_col0","_col1","_col6"] + | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 14 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_28] + | | | key expressions:key (type: string) + | | | Map-reduce partition columns:key (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:value (type: string) + | | | Filter Operator [FIL_95] + | | | predicate:(key is not null and value is not null) (type: boolean) + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_25] + | | | alias:x + | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 16 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_30] + | | key expressions:key (type: string) + | | Map-reduce partition columns:key (type: string) + | | sort order:+ + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | value expressions:value (type: string) + | | Filter Operator [FIL_96] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_26] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Union 10 [SIMPLE_EDGE] + | |<-Map 12 [CONTAINS] + | | Reduce Output Operator [RS_35] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Select Operator [SEL_21] + | | outputColumnNames:["_col1"] + | | Filter Operator [FIL_93] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_20] + | | alias:src + | |<-Map 13 [CONTAINS] + | | Reduce Output Operator [RS_35] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Select Operator [SEL_24] + | | outputColumnNames:["_col1"] + | | Filter Operator [FIL_94] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_23] + | | alias:src + | |<-Map 9 [CONTAINS] + | Reduce Output Operator [RS_35] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Select Operator [SEL_19] + | outputColumnNames:["_col1"] + | Filter Operator [FIL_92] + | predicate:value is not null (type: boolean) + | TableScan [TS_18] + | alias:src1 + | File Output Operator [FS_64] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Please refer to the previous Select Operator [SEL_37] + | File Output Operator [FS_66] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Please refer to the previous Select Operator [SEL_37] + |<-Reducer 19 [CONTAINS] + | File Output Operator [FS_62] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Select Operator [SEL_60] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} + | | outputColumnNames:["_col0","_col6"] + | |<-Reducer 24 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_56] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_105] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"key (type: string)","0":"key (type: string)"} + | | | outputColumnNames:["_col0","_col1","_col6"] + | | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 23 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_51] + | | | key expressions:key (type: string) + | | | Map-reduce partition columns:key (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:value (type: string) + | | | Filter Operator [FIL_101] + | | | predicate:(key is not null and value is not null) (type: boolean) + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_48] + | | | alias:x + | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 25 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_53] + | | key expressions:key (type: string) + | | Map-reduce partition columns:key (type: string) + | | sort order:+ + | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | | value expressions:value (type: string) + | | Filter Operator [FIL_102] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_49] + | | alias:y + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Union 18 [SIMPLE_EDGE] + | |<-Map 22 [CONTAINS] + | | Reduce Output Operator [RS_58] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Select Operator [SEL_47] + | | outputColumnNames:["_col1"] + | | Filter Operator [FIL_100] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_46] + | | alias:src + | |<-Map 21 [CONTAINS] + | | Reduce Output Operator [RS_58] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Select Operator [SEL_45] + | | outputColumnNames:["_col1"] + | | Filter Operator [FIL_99] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_44] + | | alias:src + | |<-Map 20 [CONTAINS] + | | Reduce Output Operator [RS_58] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Select Operator [SEL_42] + | | outputColumnNames:["_col1"] + | | Filter Operator [FIL_98] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_41] + | | alias:src + | |<-Map 17 [CONTAINS] + | Reduce Output Operator [RS_58] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Select Operator [SEL_40] + | outputColumnNames:["_col1"] + | Filter Operator [FIL_97] + | predicate:value is not null (type: boolean) + | TableScan [TS_39] + | alias:src1 + | File Output Operator [FS_64] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Please refer to the previous Select Operator [SEL_60] + | File Output Operator [FS_66] + | compressed:false + | table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + | Please refer to the previous Select Operator [SEL_60] + |<-Reducer 3 [CONTAINS] + File Output Operator [FS_62] + compressed:false + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_17] + outputColumnNames:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_106] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col6"] + |<-Reducer 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col6 (type: string) + | Merge Join Operator [MERGEJOIN_103] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"key (type: string)","0":"key (type: string)"} + | | outputColumnNames:["_col0","_col1","_col6"] + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | |<-Map 6 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_8] + | | key expressions:key (type: string) + | | Map-reduce partition columns:key (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:value (type: string) + | | Filter Operator [FIL_90] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_5] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: string) + | Filter Operator [FIL_91] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:y + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Union 2 [SIMPLE_EDGE] + |<-Map 1 [CONTAINS] + | Reduce Output Operator [RS_15] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Select Operator [SEL_1] + | outputColumnNames:["_col1"] + | Filter Operator [FIL_88] + | predicate:value is not null (type: boolean) + | TableScan [TS_0] + | alias:src1 + |<-Map 5 [CONTAINS] + Reduce Output Operator [RS_15] + key expressions:_col1 (type: string) + Map-reduce partition columns:_col1 (type: string) + sort order:+ + Select Operator [SEL_3] + outputColumnNames:["_col1"] + Filter Operator [FIL_89] + predicate:value is not null (type: boolean) + TableScan [TS_2] + alias:src + File Output Operator [FS_64] + compressed:false + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Select Operator [SEL_17] + File Output Operator [FS_66] + compressed:false + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Select Operator [SEL_17] +Stage-6 + Stats-Aggr Operator + Stage-1 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Stage-4 +Stage-5 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Stage-4 +PREHOOK: query: explain +FROM +( +SELECT x.key as key, y.value as value from src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key as key, y.value as value from src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key as key, y.value as value from src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +) tmp +INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +FROM +( +SELECT x.key as key, y.value as value from src1 x JOIN src y ON (x.key = y.key) +JOIN (select * from src1 union select * from src)z ON (x.value = z.value) +union +SELECT x.key as key, y.value as value from src x JOIN src y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src)z ON (x.value = z.value) +union +SELECT x.key as key, y.value as value from src1 x JOIN src1 y ON (x.key = y.key) +JOIN (select key, value from src1 union select key, value from src union select key, value from src union select key, value from src)z ON (x.value = z.value) +) tmp +INSERT OVERWRITE TABLE a SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE b SELECT tmp.key, tmp.value +INSERT OVERWRITE TABLE c SELECT tmp.key, tmp.value +POSTHOOK: type: QUERY +Not invoking CBO because the statement is not a query, CTAS, or insert + +Vertex dependency in root stage +Reducer 31 <- Reducer 30 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE), Union 7 (CONTAINS) +Reducer 22 <- Map 21 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE) +Map 24 <- Union 25 (CONTAINS) +Map 32 <- Union 25 (CONTAINS) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 30 <- Union 29 (SIMPLE_EDGE) +Map 13 <- Union 14 (CONTAINS) +Map 34 <- Union 29 (CONTAINS) +Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE) +Map 1 <- Union 2 (CONTAINS) +Map 20 <- Union 16 (CONTAINS) +Map 33 <- Union 27 (CONTAINS) +Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Map 19 <- Union 14 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) +Reducer 26 <- Union 25 (SIMPLE_EDGE), Union 27 (CONTAINS) +Reducer 17 <- Union 16 (SIMPLE_EDGE) +Reducer 8 <- Union 7 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE), Union 16 (CONTAINS) +Reducer 3 <- Union 2 (SIMPLE_EDGE) +Map 9 <- Union 2 (CONTAINS) + +Stage-7 + Stats-Aggr Operator + Stage-2 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-4 + Dependency Collection{} + Stage-3 + Reducer 8 + File Output Operator [FS_114] + compressed:false + Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_111] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + |<-Union 7 [SIMPLE_EDGE] + |<-Reducer 31 [CONTAINS] + | Reduce Output Operator [RS_110] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_109] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_105] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_160] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} + | | outputColumnNames:["_col0","_col6"] + | |<-Reducer 30 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_103] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_92] + | | outputColumnNames:["_col1"] + | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | Group By Operator [GBY_91] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Statistics:Num rows: 220 Data size: 2332 Basic stats: COMPLETE Column stats: NONE + | | |<-Union 29 [SIMPLE_EDGE] + | | |<-Map 34 [CONTAINS] + | | | Reduce Output Operator [RS_90] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_89] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_85] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_152] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_84] + | | | alias:src + | | |<-Reducer 28 [CONTAINS] + | | Reduce Output Operator [RS_90] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_89] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Group By Operator [GBY_82] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | |<-Union 27 [SIMPLE_EDGE] + | | |<-Map 33 [CONTAINS] + | | | Reduce Output Operator [RS_81] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_80] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_76] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_151] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_75] + | | | alias:src + | | |<-Reducer 26 [CONTAINS] + | | Reduce Output Operator [RS_81] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_80] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Group By Operator [GBY_73] + | | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | |<-Union 25 [SIMPLE_EDGE] + | | |<-Map 24 [CONTAINS] + | | | Reduce Output Operator [RS_72] + | | | key expressions:_col0 (type: string), _col1 (type: string) + | | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | | sort order:++ + | | | Group By Operator [GBY_71] + | | | keys:_col0 (type: string), _col1 (type: string) + | | | outputColumnNames:["_col0","_col1"] + | | | Select Operator [SEL_65] + | | | outputColumnNames:["_col0","_col1"] + | | | Filter Operator [FIL_149] + | | | predicate:value is not null (type: boolean) + | | | TableScan [TS_64] + | | | alias:src1 + | | |<-Map 32 [CONTAINS] + | | Reduce Output Operator [RS_72] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_71] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_67] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_150] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_66] + | | alias:src + | |<-Reducer 36 [SIMPLE_EDGE] + | Reduce Output Operator [RS_101] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col6 (type: string) + | Merge Join Operator [MERGEJOIN_157] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"key (type: string)","0":"key (type: string)"} + | | outputColumnNames:["_col0","_col1","_col6"] + | | Statistics:Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE + | |<-Map 35 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_96] + | | key expressions:key (type: string) + | | Map-reduce partition columns:key (type: string) + | | sort order:+ + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | value expressions:value (type: string) + | | Filter Operator [FIL_153] + | | predicate:(key is not null and value is not null) (type: boolean) + | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_93] + | | alias:x + | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | |<-Map 37 [SIMPLE_EDGE] + | Reduce Output Operator [RS_98] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: string) + | Filter Operator [FIL_154] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_94] + | alias:y + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [CONTAINS] + Reduce Output Operator [RS_110] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_109] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Group By Operator [GBY_62] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + |<-Union 5 [SIMPLE_EDGE] + |<-Reducer 4 [CONTAINS] + | Reduce Output Operator [RS_61] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_60] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_23] + | outputColumnNames:["_col0","_col1"] + | Merge Join Operator [MERGEJOIN_158] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} + | | outputColumnNames:["_col0","_col6"] + | |<-Reducer 11 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_19] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_155] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"1":"key (type: string)","0":"key (type: string)"} + | | | outputColumnNames:["_col0","_col1","_col6"] + | | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 10 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_14] + | | | key expressions:key (type: string) + | | | Map-reduce partition columns:key (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:value (type: string) + | | | Filter Operator [FIL_142] + | | | predicate:(key is not null and value is not null) (type: boolean) + | | | Statistics:Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_11] + | | | alias:x + | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 12 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_16] + | | key expressions:key (type: string) + | | Map-reduce partition columns:key (type: string) + | | sort order:+ + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | value expressions:value (type: string) + | | Filter Operator [FIL_143] + | | predicate:key is not null (type: boolean) + | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_12] + | | alias:y + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_10] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_9] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 131 Data size: 1372 Basic stats: COMPLETE Column stats: NONE + | |<-Union 2 [SIMPLE_EDGE] + | |<-Map 1 [CONTAINS] + | | Reduce Output Operator [RS_8] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_7] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_140] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_0] + | | alias:src1 + | |<-Map 9 [CONTAINS] + | Reduce Output Operator [RS_8] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_7] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_3] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_141] + | predicate:value is not null (type: boolean) + | TableScan [TS_2] + | alias:src + |<-Reducer 18 [CONTAINS] + Reduce Output Operator [RS_61] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Group By Operator [GBY_60] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_56] + outputColumnNames:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_159] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"_col1 (type: string)","0":"_col1 (type: string)"} + | outputColumnNames:["_col0","_col6"] + |<-Reducer 17 [SIMPLE_EDGE] + | Reduce Output Operator [RS_54] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) + | sort order:+ + | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_43] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_42] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 190 Data size: 2008 Basic stats: COMPLETE Column stats: NONE + | |<-Union 16 [SIMPLE_EDGE] + | |<-Map 20 [CONTAINS] + | | Reduce Output Operator [RS_41] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_40] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_36] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_146] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_35] + | | alias:src + | |<-Reducer 15 [CONTAINS] + | Reduce Output Operator [RS_41] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_40] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Group By Operator [GBY_33] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | |<-Union 14 [SIMPLE_EDGE] + | |<-Map 13 [CONTAINS] + | | Reduce Output Operator [RS_32] + | | key expressions:_col0 (type: string), _col1 (type: string) + | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | | sort order:++ + | | Group By Operator [GBY_31] + | | keys:_col0 (type: string), _col1 (type: string) + | | outputColumnNames:["_col0","_col1"] + | | Select Operator [SEL_25] + | | outputColumnNames:["_col0","_col1"] + | | Filter Operator [FIL_144] + | | predicate:value is not null (type: boolean) + | | TableScan [TS_24] + | | alias:src1 + | |<-Map 19 [CONTAINS] + | Reduce Output Operator [RS_32] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ + | Group By Operator [GBY_31] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_27] + | outputColumnNames:["_col0","_col1"] + | Filter Operator [FIL_145] + | predicate:value is not null (type: boolean) + | TableScan [TS_26] + | alias:src + |<-Reducer 22 [SIMPLE_EDGE] + Reduce Output Operator [RS_52] + key expressions:_col1 (type: string) + Map-reduce partition columns:_col1 (type: string) + sort order:+ + Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: string), _col6 (type: string) + Merge Join Operator [MERGEJOIN_156] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"1":"key (type: string)","0":"key (type: string)"} + | outputColumnNames:["_col0","_col1","_col6"] + | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + |<-Map 21 [SIMPLE_EDGE] + | Reduce Output Operator [RS_47] + | key expressions:key (type: string) + | Map-reduce partition columns:key (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | value expressions:value (type: string) + | Filter Operator [FIL_147] + | predicate:(key is not null and value is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_44] + | alias:x + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map 23 [SIMPLE_EDGE] + Reduce Output Operator [RS_49] + key expressions:key (type: string) + Map-reduce partition columns:key (type: string) + sort order:+ + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions:value (type: string) + Filter Operator [FIL_148] + predicate:key is not null (type: boolean) + Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_45] + alias:y + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator [FS_116] + compressed:false + Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Group By Operator [GBY_111] + File Output Operator [FS_118] + compressed:false + Statistics:Num rows: 272 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.c","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Group By Operator [GBY_111] +Stage-6 + Stats-Aggr Operator + Stage-1 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.b","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Stage-4 +Stage-5 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.a","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Stage-4 +PREHOOK: query: CREATE TABLE DEST1(key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST1 +POSTHOOK: query: CREATE TABLE DEST1(key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST1 +PREHOOK: query: CREATE TABLE DEST2(key STRING, val1 STRING, val2 STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST2 +POSTHOOK: query: CREATE TABLE DEST2(key STRING, val1 STRING, val2 STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST2 +PREHOOK: query: explain +FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1 + UNION DISTINCT + select s2.key as key, s2.value as value from src s2) unionsrc +INSERT OVERWRITE TABLE DEST1 SELECT unionsrc.key, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key +INSERT OVERWRITE TABLE DEST2 SELECT unionsrc.key, unionsrc.value, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key, unionsrc.value +PREHOOK: type: QUERY +POSTHOOK: query: explain +FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1 + UNION DISTINCT + select s2.key as key, s2.value as value from src s2) unionsrc +INSERT OVERWRITE TABLE DEST1 SELECT unionsrc.key, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key +INSERT OVERWRITE TABLE DEST2 SELECT unionsrc.key, unionsrc.value, COUNT(DISTINCT SUBSTR(unionsrc.value,5)) GROUP BY unionsrc.key, unionsrc.value +POSTHOOK: type: QUERY +Not invoking CBO because the statement is not a query, CTAS, or insert + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Union 3 (SIMPLE_EDGE) +Map 6 <- Union 3 (CONTAINS) + +Stage-5 + Stats-Aggr Operator + Stage-1 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest2","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Stage-3 + Dependency Collection{} + Stage-2 + Reducer 5 + File Output Operator [FS_20] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Group By Operator [GBY_18] + | aggregations:["count(DISTINCT KEY._col1:0._col0)"] + | keys:KEY._col0 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_17] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:++ + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + Group By Operator [GBY_16] + aggregations:["count(DISTINCT substr(_col1, 5))"] + keys:_col0 (type: string), substr(_col1, 5) (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + Group By Operator [GBY_13] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + |<-Union 3 [SIMPLE_EDGE] + |<-Reducer 2 [CONTAINS] + | Reduce Output Operator [RS_12] + | key expressions:_col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:+++ + | Group By Operator [GBY_11] + | keys:_col0 (type: string), _col1 (type: string) + | outputColumnNames:["_col0","_col1"] + | Select Operator [SEL_5] + | outputColumnNames:["_col0","_col1"] + | Group By Operator [GBY_4] + | | aggregations:["count(VALUE._col0)"] + | | outputColumnNames:["_col0"] + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_3] + | sort order: + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: bigint) + | Group By Operator [GBY_2] + | aggregations:["count(1)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_1] + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:s1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [CONTAINS] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:+++ + Group By Operator [GBY_11] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1"] + Select Operator [SEL_7] + outputColumnNames:["_col0","_col1"] + TableScan [TS_6] + alias:s2 + File Output Operator [FS_26] + compressed:false + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest2","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Select Operator [SEL_25] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + Group By Operator [GBY_24] + aggregations:["count(DISTINCT substr(_col1, 5))"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 0 Data size: 0 Basic stats: NONE Column stats: PARTIAL + Please refer to the previous Group By Operator [GBY_13] +Stage-4 + Stats-Aggr Operator + Stage-0 + Move Operator + table:{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","name:":"default.dest1","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"} + Please refer to the previous Stage-3