From 8f3a9fa32412a4cae9d565442d17fea06a67cb20 Mon Sep 17 00:00:00 2001 From: Nishant Date: Mon, 15 Jul 2019 19:52:51 +0530 Subject: [PATCH] [HIVE-20683] Add the Ability to push Dynamic Between and Bloom filters to Druid fix concurrent initialization change ex type --- .../druid_table_alltypesorc/load.hive.sql | 10 +- druid-handler/pom.xml | 5 + .../hive/druid/DruidStorageHandler.java | 38 + .../hive/druid/DruidStorageHandlerUtils.java | 299 +++ .../serde/DruidGroupByQueryRecordReader.java | 6 +- .../druid/serde/DruidQueryRecordReader.java | 199 +- .../serde/DruidScanQueryRecordReader.java | 6 +- .../serde/DruidSelectQueryRecordReader.java | 6 +- .../DruidTimeseriesQueryRecordReader.java | 6 +- .../serde/DruidTopNQueryRecordReader.java | 6 +- .../hive/druid/serde/TestDruidSerDe.java | 6 +- itests/qtest-druid/pom.xml | 5 + .../hive/ql/metadata/HiveStorageHandler.java | 14 + .../DynamicPartitionPruningOptimization.java | 4 +- .../hadoop/hive/ql/plan/TableScanDesc.java | 28 +- .../druidmini_semijoin_reduction_all_types.q | 144 ++ .../clientpositive/druidmini_test_cast.q | 128 ++ ...uidmini_semijoin_reduction_all_types.q.out | 1973 +++++++++++++++++ 18 files changed, 2776 insertions(+), 107 deletions(-) create mode 100644 ql/src/test/queries/clientpositive/druidmini_semijoin_reduction_all_types.q create mode 100644 ql/src/test/queries/clientpositive/druidmini_test_cast.q create mode 100644 ql/src/test/results/clientpositive/druid/druidmini_semijoin_reduction_all_types.q.out diff --git a/data/files/datasets/druid_table_alltypesorc/load.hive.sql b/data/files/datasets/druid_table_alltypesorc/load.hive.sql index 0641665eac..c322e3fd3f 100644 --- a/data/files/datasets/druid_table_alltypesorc/load.hive.sql +++ b/data/files/datasets/druid_table_alltypesorc/load.hive.sql @@ -10,7 +10,10 @@ CREATE TABLE alltypesorc1( ctimestamp1 TIMESTAMP, ctimestamp2 TIMESTAMP, cboolean1 BOOLEAN, - cboolean2 BOOLEAN) + cboolean2 BOOLEAN, + cintstring STRING, + cfloatstring STRING, + cdoublestring STRING) STORED AS ORC; LOAD DATA LOCAL INPATH "${hiveconf:test.data.dir}/alltypesorc" @@ -30,5 +33,8 @@ SELECT cast (`ctimestamp1` as timestamp with local time zone) as `__time`, cint, cbigint, cboolean1, - cboolean2 + cboolean2, + cast(cint as string) as cintstring, + cast(cfloat as string) as cfloatstring, + cast(cdouble as string) as cdoublestring FROM alltypesorc1 where ctimestamp1 IS NOT NULL; diff --git a/druid-handler/pom.xml b/druid-handler/pom.xml index 0454747ad8..ad27ac8a2c 100644 --- a/druid-handler/pom.xml +++ b/druid-handler/pom.xml @@ -170,6 +170,11 @@ postgresql-metadata-storage ${druid.version} + + org.apache.druid.extensions + druid-bloom-filter + ${druid.version} + org.apache.hadoop hadoop-common diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandler.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandler.java index a14837d60e..13963b0148 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandler.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandler.java @@ -26,6 +26,7 @@ import com.google.common.base.Throwables; import com.google.common.collect.ImmutableList; import com.google.common.collect.ImmutableSet; +import com.google.common.collect.Maps; import com.google.common.collect.Sets; import org.apache.druid.data.input.impl.DimensionSchema; import org.apache.druid.data.input.impl.DimensionsSpec; @@ -49,6 +50,8 @@ import org.apache.druid.metadata.storage.mysql.MySQLConnectorConfig; import org.apache.druid.metadata.storage.postgresql.PostgreSQLConnector; import org.apache.druid.metadata.storage.postgresql.PostgreSQLConnectorConfig; +import org.apache.druid.query.BaseQuery; +import org.apache.druid.query.Query; import org.apache.druid.query.aggregation.AggregatorFactory; import org.apache.druid.segment.IndexSpec; import org.apache.druid.segment.indexing.DataSchema; @@ -84,7 +87,10 @@ import org.apache.hadoop.hive.ql.hooks.WriteEntity; import org.apache.hadoop.hive.ql.metadata.HiveStorageHandler; import org.apache.hadoop.hive.ql.metadata.StorageHandlerInfo; +import org.apache.hadoop.hive.ql.plan.ExprNodeGenericFuncDesc; +import org.apache.hadoop.hive.ql.plan.OperatorDesc; import org.apache.hadoop.hive.ql.plan.TableDesc; +import org.apache.hadoop.hive.ql.plan.TableScanDesc; import org.apache.hadoop.hive.ql.security.authorization.DefaultHiveAuthorizationProvider; import org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider; import org.apache.hadoop.hive.ql.session.SessionState; @@ -964,4 +970,36 @@ private int getMaxRetryCount() { return null; } } + + @Override + public Map getOperatorDescProperties(OperatorDesc operatorDesc, + Map initialProps + ) { + if(operatorDesc instanceof TableScanDesc) { + TableScanDesc tableScanDesc = (TableScanDesc) operatorDesc; + ExprNodeGenericFuncDesc filterExpr = tableScanDesc.getFilterExpr(); + String druidQuery = initialProps.get(Constants.DRUID_QUERY_JSON); + + if(filterExpr != null && druidQuery != null) { + try { + Query query = DruidStorageHandlerUtils.JSON_MAPPER.readValue( + druidQuery, BaseQuery.class); + Query queryWithDynamicFilters = DruidStorageHandlerUtils + .addDynamicFilters(query, filterExpr, conf, false); + Map props = Maps.newHashMap(initialProps); + props.put(Constants.DRUID_QUERY_JSON, + DruidStorageHandlerUtils.JSON_MAPPER.writeValueAsString(queryWithDynamicFilters) + ); + return props; + } catch (IOException e) { + LOG.error( + "Exception while deserializing druid query. Explain plan may not have final druid query", + e + ); + } + } + } + // Case when we do not have any additional info to add. + return initialProps; + } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandlerUtils.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandlerUtils.java index 1fab1e006a..7255f30687 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandlerUtils.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/DruidStorageHandlerUtils.java @@ -25,13 +25,17 @@ import com.google.common.base.Throwables; import com.google.common.collect.ImmutableList; import com.google.common.collect.ImmutableMap; +import com.google.common.collect.ImmutableSet; import com.google.common.collect.Interner; import com.google.common.collect.Interners; import com.google.common.collect.Iterables; import com.google.common.collect.Lists; import com.google.common.collect.Ordering; +import org.apache.calcite.adapter.druid.DruidQuery; +import org.apache.calcite.sql.validate.SqlValidatorUtil; import org.apache.druid.data.input.impl.DimensionSchema; import org.apache.druid.data.input.impl.StringDimensionSchema; +import org.apache.druid.guice.BloomFilterSerializersModule; import org.apache.druid.jackson.DefaultObjectMapper; import org.apache.druid.java.util.common.JodaUtils; import org.apache.druid.java.util.common.MapUtils; @@ -50,6 +54,7 @@ import org.apache.druid.metadata.SQLMetadataConnector; import org.apache.druid.metadata.storage.mysql.MySQLConnector; import org.apache.druid.query.DruidProcessingConfig; +import org.apache.druid.query.Druids; import org.apache.druid.query.aggregation.AggregatorFactory; import org.apache.druid.query.aggregation.DoubleSumAggregatorFactory; import org.apache.druid.query.aggregation.FloatSumAggregatorFactory; @@ -63,12 +68,29 @@ import org.apache.druid.query.expression.TimestampParseExprMacro; import org.apache.druid.query.expression.TimestampShiftExprMacro; import org.apache.druid.query.expression.TrimExprMacro; +import org.apache.druid.query.filter.AndDimFilter; +import org.apache.druid.query.filter.BloomDimFilter; +import org.apache.druid.query.filter.BloomKFilter; +import org.apache.druid.query.filter.BloomKFilterHolder; +import org.apache.druid.query.filter.BoundDimFilter; +import org.apache.druid.query.filter.DimFilter; +import org.apache.druid.query.filter.OrDimFilter; +import org.apache.druid.query.groupby.GroupByQuery; +import org.apache.druid.query.ordering.StringComparator; +import org.apache.druid.query.ordering.StringComparators; import org.apache.druid.query.scan.ScanQuery; +import org.apache.druid.query.select.SelectQuery; import org.apache.druid.query.select.SelectQueryConfig; import org.apache.druid.query.spec.MultipleIntervalSegmentSpec; +import org.apache.druid.query.timeseries.TimeseriesQuery; +import org.apache.druid.query.topn.TopNQuery; +import org.apache.druid.query.topn.TopNQueryBuilder; import org.apache.druid.segment.IndexIO; import org.apache.druid.segment.IndexMergerV9; import org.apache.druid.segment.IndexSpec; +import org.apache.druid.segment.VirtualColumn; +import org.apache.druid.segment.VirtualColumns; +import org.apache.druid.segment.column.ValueType; import org.apache.druid.segment.data.BitmapSerdeFactory; import org.apache.druid.segment.data.ConciseBitmapSerdeFactory; import org.apache.druid.segment.data.RoaringBitmapSerdeFactory; @@ -76,6 +98,7 @@ import org.apache.druid.segment.indexing.granularity.UniformGranularitySpec; import org.apache.druid.segment.loading.DataSegmentPusher; import org.apache.druid.segment.realtime.appenderator.SegmentIdWithShardSpec; +import org.apache.druid.segment.virtual.ExpressionVirtualColumn; import org.apache.druid.segment.writeout.TmpFileSegmentWriteOutMediumFactory; import org.apache.druid.storage.hdfs.HdfsDataSegmentPusher; import org.apache.druid.storage.hdfs.HdfsDataSegmentPusherConfig; @@ -91,17 +114,37 @@ import org.apache.hadoop.fs.FileStatus; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.common.io.NonSyncByteArrayInputStream; import org.apache.hadoop.hive.conf.Constants; import org.apache.hadoop.hive.conf.HiveConf; import org.apache.hadoop.hive.druid.conf.DruidConstants; import org.apache.hadoop.hive.druid.json.AvroParseSpec; import org.apache.hadoop.hive.druid.json.AvroStreamInputRowParser; import org.apache.hadoop.hive.metastore.api.Table; +import org.apache.hadoop.hive.ql.exec.ExprNodeDynamicValueEvaluator; +import org.apache.hadoop.hive.ql.exec.ExprNodeEvaluator; +import org.apache.hadoop.hive.ql.exec.ExprNodeEvaluatorFactory; +import org.apache.hadoop.hive.ql.exec.FunctionRegistry; +import org.apache.hadoop.hive.ql.exec.UDF; import org.apache.hadoop.hive.ql.exec.Utilities; +import org.apache.hadoop.hive.ql.metadata.HiveException; +import org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc; +import org.apache.hadoop.hive.ql.plan.ExprNodeDesc; +import org.apache.hadoop.hive.ql.plan.ExprNodeGenericFuncDesc; +import org.apache.hadoop.hive.ql.udf.UDFToDouble; +import org.apache.hadoop.hive.ql.udf.UDFToFloat; +import org.apache.hadoop.hive.ql.udf.UDFToLong; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDF; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBetween; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFInBloomFilter; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFToString; import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector; import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorUtils; import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; +import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; +import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.retry.RetryPolicies; import org.apache.hadoop.io.retry.RetryProxy; import org.apache.hadoop.util.StringUtils; @@ -133,9 +176,11 @@ import java.net.UnknownHostException; import java.sql.SQLException; import java.util.ArrayList; +import java.util.Arrays; import java.util.Collection; import java.util.Collections; import java.util.HashSet; +import java.util.Iterator; import java.util.List; import java.util.Map; import java.util.Objects; @@ -209,6 +254,11 @@ private DruidStorageHandlerUtils() { SMILE_MAPPER.registerSubtypes(new NamedType(AvroParseSpec.class, "avro")); JSON_MAPPER.registerSubtypes(new NamedType(AvroStreamInputRowParser.class, "avro_stream")); SMILE_MAPPER.registerSubtypes(new NamedType(AvroStreamInputRowParser.class, "avro_stream")); + // Register Bloom Filter Serializers + BloomFilterSerializersModule bloomFilterSerializersModule = new BloomFilterSerializersModule(); + JSON_MAPPER.registerModule(bloomFilterSerializersModule); + SMILE_MAPPER.registerModule(bloomFilterSerializersModule); + // set the timezone of the object mapper // THIS IS NOT WORKING workaround is to set it as part of java opts -Duser.timezone="UTC" JSON_MAPPER.setTimeZone(TimeZone.getTimeZone("UTC")); @@ -894,4 +944,253 @@ public static IndexSpec getIndexSpec(Configuration jc) { ImmutableList aggregatorFactories = aggregatorFactoryBuilder.build(); return Pair.of(dimensions, aggregatorFactories.toArray(new AggregatorFactory[0])); } + + // Druid only supports String,Long,Float,Double selectors + private static Set DRUID_SUPPORTED_TYPE_INFOS = ImmutableSet.of( + TypeInfoFactory.stringTypeInfo, TypeInfoFactory.charTypeInfo, + TypeInfoFactory.varcharTypeInfo, TypeInfoFactory.byteTypeInfo, + TypeInfoFactory.intTypeInfo, TypeInfoFactory.longTypeInfo, + TypeInfoFactory.shortTypeInfo, TypeInfoFactory.doubleTypeInfo + ); + + private static Set STRING_TYPE_INFOS = ImmutableSet.of( + TypeInfoFactory.stringTypeInfo, + TypeInfoFactory.charTypeInfo, TypeInfoFactory.varcharTypeInfo + ); + + + public static org.apache.druid.query.Query addDynamicFilters(org.apache.druid.query.Query query, + ExprNodeGenericFuncDesc filterExpr, Configuration conf, boolean resolveDynamicValues + ) { + List virtualColumns = Arrays + .asList(getVirtualColumns(query).getVirtualColumns()); + org.apache.druid.query.Query rv = query; + DimFilter joinReductionFilter = toDruidFilter(filterExpr, conf, virtualColumns, + resolveDynamicValues + ); + if(joinReductionFilter != null) { + String type = query.getType(); + DimFilter filter = new AndDimFilter(joinReductionFilter, query.getFilter()); + switch (type) { + case org.apache.druid.query.Query.TIMESERIES: + rv = Druids.TimeseriesQueryBuilder.copy((TimeseriesQuery) query) + .filters(filter) + .virtualColumns(VirtualColumns.create(virtualColumns)) + .build(); + break; + case org.apache.druid.query.Query.TOPN: + rv = new TopNQueryBuilder((TopNQuery) query) + .filters(filter) + .virtualColumns(VirtualColumns.create(virtualColumns)) + .build(); + break; + case org.apache.druid.query.Query.GROUP_BY: + rv = new GroupByQuery.Builder((GroupByQuery) query) + .setDimFilter(filter) + .setVirtualColumns(VirtualColumns.create(virtualColumns)) + .build(); + break; + case org.apache.druid.query.Query.SCAN: + rv = ScanQuery.ScanQueryBuilder.copy((ScanQuery) query) + .filters(filter) + .virtualColumns(VirtualColumns.create(virtualColumns)) + .build(); + break; + case org.apache.druid.query.Query.SELECT: + rv = Druids.SelectQueryBuilder.copy((SelectQuery) query) + .filters(filter) + .virtualColumns(VirtualColumns.create(virtualColumns)) + .build(); + } + } + return rv; + } + + private static DimFilter toDruidFilter(ExprNodeDesc filterExpr, Configuration configuration, + List virtualColumns, boolean resolveDynamicValues + ) { + if(filterExpr == null) { + return null; + } + Class genericUDFClass = getGenericUDFClassFromExprDesc(filterExpr); + if(FunctionRegistry.isOpAnd(filterExpr)) { + Iterator iterator = filterExpr.getChildren().iterator(); + List delegates = Lists.newArrayList(); + while (iterator.hasNext()) { + DimFilter filter = toDruidFilter(iterator.next(), configuration, virtualColumns, + resolveDynamicValues + ); + if(filter != null) { + delegates.add(filter); + } + } + if(delegates != null && !delegates.isEmpty()) { + return new AndDimFilter(delegates); + } + } + if(FunctionRegistry.isOpOr(filterExpr)) { + Iterator iterator = filterExpr.getChildren().iterator(); + List delegates = Lists.newArrayList(); + while (iterator.hasNext()) { + DimFilter filter = toDruidFilter(iterator.next(), configuration, virtualColumns, + resolveDynamicValues + ); + if(filter != null) { + delegates.add(filter); + } + } + if(delegates != null) { + return new OrDimFilter(delegates); + } + } else if(GenericUDFBetween.class == genericUDFClass) { + List child = filterExpr.getChildren(); + String col = extractColName(child.get(1), virtualColumns); + if(col != null) { + try { + StringComparator comparator = STRING_TYPE_INFOS.contains(child.get(1).getTypeInfo()) + ? StringComparators.LEXICOGRAPHIC + : StringComparators.NUMERIC; + String lower = evaluate(child.get(2), configuration, resolveDynamicValues); + String upper = evaluate(child.get(3), configuration, resolveDynamicValues); + return new BoundDimFilter(col, lower, upper, false, false, null, null, + StringComparator.fromString("numeric") + ); + + } catch (HiveException e) { + throw new RuntimeException(e); + } + } + } else if(GenericUDFInBloomFilter.class == genericUDFClass) { + List child = filterExpr.getChildren(); + String col = extractColName(child.get(0), virtualColumns); + if(col != null) { + try { + BloomKFilter bloomFilter = evaluateBloomFilter(child.get(1), configuration, + resolveDynamicValues + ); + return new BloomDimFilter(col, BloomKFilterHolder.fromBloomKFilter(bloomFilter), null); + } catch (HiveException e) { + throw new RuntimeException(e); + } catch (IOException e) { + throw new RuntimeException(e); + } + } + } + return null; + } + + private static String evaluate(ExprNodeDesc desc, Configuration configuration, + boolean resolveDynamicValue + ) throws HiveException { + ExprNodeEvaluator exprNodeEvaluator = ExprNodeEvaluatorFactory.get(desc, configuration); + if(exprNodeEvaluator instanceof ExprNodeDynamicValueEvaluator && !resolveDynamicValue) { + return desc.getExprStringForExplain(); + } else { + return exprNodeEvaluator.evaluate(null).toString(); + } + } + + private static BloomKFilter evaluateBloomFilter(ExprNodeDesc desc, Configuration configuration, + boolean resolveDynamicValue + ) + throws HiveException, IOException { + if(!resolveDynamicValue) { + // return a dummy bloom filter for explain + return new BloomKFilter(1); + } else { + BytesWritable bw = (BytesWritable) ExprNodeEvaluatorFactory.get(desc, configuration) + .evaluate(null); + byte[] bytes = new byte[bw.getLength()]; + System.arraycopy(bw.getBytes(), 0, bytes, 0, bw.getLength()); + InputStream in = new NonSyncByteArrayInputStream(bytes); + return BloomKFilter.deserialize(in); + } + } + + public static String extractColName(ExprNodeDesc expr, List virtualColumns) { + if(!DRUID_SUPPORTED_TYPE_INFOS.contains(expr.getTypeInfo())) { + // This column type is currently not supported in druid.(e.g boolean) + // We cannot pass the bloom filter to druid since bloom filter tests for exact object bytes. + return null; + } + if(expr instanceof ExprNodeColumnDesc) { + return ((ExprNodeColumnDesc) expr).getColumn(); + } + + ExprNodeGenericFuncDesc funcDesc = null; + if(expr instanceof ExprNodeGenericFuncDesc) { + funcDesc = (ExprNodeGenericFuncDesc) expr; + } + if(null == funcDesc) { + return null; + } + GenericUDF udf = funcDesc.getGenericUDF(); + // bail out if its not a simple cast expression. + if(funcDesc.getChildren().size() == 1 && funcDesc.getChildren() + .get(0) instanceof ExprNodeColumnDesc) { + return null; + } + String columnName = ((ExprNodeColumnDesc) (funcDesc.getChildren() + .get(0))).getColumn(); + ValueType targetType = null; + if(udf instanceof GenericUDFBridge) { + Class udfClass = ((GenericUDFBridge) udf).getUdfClass(); + if(udfClass.equals(UDFToDouble.class)) { + targetType = ValueType.DOUBLE; + } else if(udfClass.equals(UDFToFloat.class)) { + targetType = ValueType.FLOAT; + } else if(udfClass.equals(UDFToLong.class)) { + targetType = ValueType.LONG; + } else if(udfClass.equals(GenericUDFToString.class)) { + targetType = ValueType.STRING; + } + } + + if(targetType == null) { + return null; + } + String virtualColumnExpr = DruidQuery + .format("CAST(%s, '%s')", columnName, targetType.toString()); + for(VirtualColumn column : virtualColumns) { + if(column instanceof ExpressionVirtualColumn && ((ExpressionVirtualColumn) column) + .getExpression().equals(virtualColumnExpr)) { + // Found an existing virtual column with same expression, no need to add another virtual column + return column.getOutputName(); + } + } + Set usedColumnNames = virtualColumns.stream().map(col -> col.getOutputName()) + .collect(Collectors.toSet()); + final String name = SqlValidatorUtil + .uniquify("vc", usedColumnNames, SqlValidatorUtil.EXPR_SUGGESTER); + ExpressionVirtualColumn expressionVirtualColumn = new ExpressionVirtualColumn(name, + virtualColumnExpr, targetType, null + ); + virtualColumns.add(expressionVirtualColumn); + return name; + } + + public static VirtualColumns getVirtualColumns(org.apache.druid.query.Query query) { + String type = query.getType(); + switch (type) { + case org.apache.druid.query.Query.TIMESERIES: + return ((TimeseriesQuery) query).getVirtualColumns(); + case org.apache.druid.query.Query.TOPN: + return ((TopNQuery) query).getVirtualColumns(); + case org.apache.druid.query.Query.GROUP_BY: + return ((GroupByQuery) query).getVirtualColumns(); + case org.apache.druid.query.Query.SCAN: + return ((ScanQuery) query).getVirtualColumns(); + case org.apache.druid.query.Query.SELECT: + return ((SelectQuery) query).getVirtualColumns(); + } + throw new UnsupportedOperationException("Unsupported Query type" + query); + } + + private static Class getGenericUDFClassFromExprDesc(ExprNodeDesc desc) { + if(!(desc instanceof ExprNodeGenericFuncDesc)) { + return null; + } + ExprNodeGenericFuncDesc genericFuncDesc = (ExprNodeGenericFuncDesc) desc; + return genericFuncDesc.getGenericUDF().getClass(); + } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidGroupByQueryRecordReader.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidGroupByQueryRecordReader.java index 038b1f63b0..4def3864c7 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidGroupByQueryRecordReader.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidGroupByQueryRecordReader.java @@ -45,8 +45,8 @@ @Override public boolean nextKeyValue() { // Results - if (queryResultsIterator.hasNext()) { - final Row row = queryResultsIterator.next(); + if (getQueryResultsIterator().hasNext()) { + final Row row = getQueryResultsIterator().next(); // currently druid supports only MapBasedRow as Jackson SerDe so it should safe to cast without check currentRow = (MapBasedRow) row; currentEvent = currentRow.getEvent(); @@ -87,7 +87,7 @@ } @Override public float getProgress() throws IOException { - return queryResultsIterator.hasNext() ? 0 : 1; + return getQueryResultsIterator().hasNext() ? 0 : 1; } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidQueryRecordReader.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidQueryRecordReader.java index edbea22c54..68ab7aca29 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidQueryRecordReader.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidQueryRecordReader.java @@ -36,6 +36,9 @@ import org.apache.hadoop.hive.druid.DruidStorageHandler; import org.apache.hadoop.hive.druid.DruidStorageHandlerUtils; import org.apache.hadoop.hive.druid.io.HiveDruidSplit; +import org.apache.hadoop.hive.ql.exec.SerializationUtilities; +import org.apache.hadoop.hive.ql.plan.ExprNodeGenericFuncDesc; +import org.apache.hadoop.hive.ql.plan.TableScanDesc; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.mapreduce.InputSplit; import org.apache.hadoop.mapreduce.RecordReader; @@ -51,6 +54,7 @@ import java.util.Objects; import java.util.concurrent.ExecutionException; import java.util.concurrent.Future; +import java.util.concurrent.atomic.AtomicReference; /** * Base record reader for given a Druid query. This class contains the logic to @@ -65,7 +69,12 @@ implements org.apache.hadoop.mapred.RecordReader { private static final Logger LOG = LoggerFactory.getLogger(DruidQueryRecordReader.class); - + private final Object initLock = new Object(); + // Smile mapper is used to read query results that are serialized as binary instead of json + private ObjectMapper smileMapper; + private Configuration conf; + private String[] locations; + private HttpClient httpClient; /** * Query that Druid executes. */ @@ -74,83 +83,108 @@ /** * Query results as a streaming iterator. */ - JsonParserIterator queryResultsIterator = null; + private volatile JsonParserIterator queryResultsIterator = null; + + public JsonParserIterator getQueryResultsIterator() { + if(this.queryResultsIterator==null) + { + synchronized(initLock) + { + if(this.queryResultsIterator==null) + this.queryResultsIterator = createQueryResultsIterator(); + } + } + return this.queryResultsIterator; + } + + public JsonParserIterator createQueryResultsIterator(){ + { + JsonParserIterator iterator = null; + String filterExprSerialized = conf.get(TableScanDesc.FILTER_EXPR_CONF_STR); + if (filterExprSerialized != null) { + ExprNodeGenericFuncDesc filterExpr = SerializationUtilities + .deserializeExpression(filterExprSerialized); + query = DruidStorageHandlerUtils.addDynamicFilters(query, filterExpr, conf, true); + } + + // Result type definition used to read the rows, this is query dependent. + JavaType resultsType = getResultTypeDef(); + boolean initialized = false; + int currentLocationIndex = 0; + Exception ex = null; + while (!initialized && currentLocationIndex < locations.length) { + String address = locations[currentLocationIndex++]; + if (Strings.isNullOrEmpty(address)) { + throw new RE("can not fetch results from empty or null host value"); + } + // Execute query + LOG.debug("Retrieving data from druid location[{}] using query:[{}] ", address, query); + try { + Request request = DruidStorageHandlerUtils.createSmileRequest(address, query); + Future inputStreamFuture = httpClient.go(request, new InputStreamResponseHandler()); + //noinspection unchecked + iterator = + new JsonParserIterator(smileMapper, + resultsType, + inputStreamFuture, + request.getUrl().toString(), + query); + iterator.init(); + initialized = true; + } catch (Exception e) { + if (iterator != null) { + // We got exception while querying results from this host. + CloseQuietly.close(iterator); + } + LOG.error("Failure getting results for query[{}] from host[{}] because of [{}]", + query, + address, + e.getMessage()); + if (ex == null) { + ex = e; + } else { + ex.addSuppressed(e); + } + } + } + + if (!initialized) { + throw new RE(ex, + "Failure getting results for query[%s] from locations[%s] because of [%s]", + query, + locations, + Objects.requireNonNull(ex).getMessage()); + } + return iterator; + } + } @Override public void initialize(InputSplit split, TaskAttemptContext context) throws IOException { initialize(split, context.getConfiguration()); } - public void initialize(InputSplit split, ObjectMapper mapper, ObjectMapper smileMapper, HttpClient httpClient) + public void initialize(InputSplit split, ObjectMapper mapper, ObjectMapper smileMapper, HttpClient httpClient,Configuration conf) throws IOException { + this.conf = conf; HiveDruidSplit hiveDruidSplit = (HiveDruidSplit) split; Preconditions.checkNotNull(hiveDruidSplit, "input split is null ???"); Preconditions.checkNotNull(httpClient, "need Http Client can not be null"); - ObjectMapper objectMapper = Preconditions.checkNotNull(mapper, "object Mapper can not be null"); - // Smile mapper is used to read query results that are serialized as binary instead of json // Smile mapper is used to read query results that are serialized as binary instead of json - ObjectMapper smileObjectMapper = Preconditions.checkNotNull(smileMapper, "Smile Mapper can not be null"); + this.smileMapper = Preconditions.checkNotNull(smileMapper, "Smile Mapper can not be null"); // Create query - this.query = objectMapper.readValue(Preconditions.checkNotNull(hiveDruidSplit.getDruidQuery()), Query.class); + this.query = mapper.readValue(Preconditions.checkNotNull(hiveDruidSplit.getDruidQuery()), Query.class); Preconditions.checkNotNull(query); - /* - Result type definition used to read the rows, this is query dependent. - */ - JavaType resultsType = getResultTypeDef(); - - final String[] locations = hiveDruidSplit.getLocations(); - boolean initialized = false; - int currentLocationIndex = 0; - Exception ex = null; - while (!initialized && currentLocationIndex < locations.length) { - String address = locations[currentLocationIndex++]; - if (Strings.isNullOrEmpty(address)) { - throw new IOException("can not fetch results from empty or null host value"); - } - // Execute query - LOG.debug("Retrieving data from druid location[{}] using query:[{}] ", address, query); - try { - Request request = DruidStorageHandlerUtils.createSmileRequest(address, query); - Future inputStreamFuture = httpClient.go(request, new InputStreamResponseHandler()); - //noinspection unchecked - queryResultsIterator = - new JsonParserIterator(smileObjectMapper, - resultsType, - inputStreamFuture, - request.getUrl().toString(), - query); - queryResultsIterator.init(); - initialized = true; - } catch (IOException | ExecutionException | InterruptedException e) { - if (queryResultsIterator != null) { - // We got exception while querying results from this host. - queryResultsIterator.close(); - } - LOG.error("Failure getting results for query[{}] from host[{}] because of [{}]", - query, - address, - e.getMessage()); - if (ex == null) { - ex = e; - } else { - ex.addSuppressed(e); - } - } - } - if (!initialized) { - throw new RE(ex, - "Failure getting results for query[%s] from locations[%s] because of [%s]", - query, - locations, - Objects.requireNonNull(ex).getMessage()); - } + this.locations = hiveDruidSplit.getLocations(); + this.httpClient = httpClient; } public void initialize(InputSplit split, Configuration conf) throws IOException { initialize(split, DruidStorageHandlerUtils.JSON_MAPPER, DruidStorageHandlerUtils.SMILE_MAPPER, - DruidStorageHandler.getHttpClient()); + DruidStorageHandler.getHttpClient(), + conf); } protected abstract JavaType getResultTypeDef(); @@ -181,7 +215,9 @@ public void initialize(InputSplit split, Configuration conf) throws IOException @Override public abstract float getProgress() throws IOException; @Override public void close() { - CloseQuietly.close(queryResultsIterator); + if(queryResultsIterator != null) { + CloseQuietly.close(queryResultsIterator); + } } /** @@ -246,23 +282,34 @@ public void initialize(InputSplit split, Configuration conf) throws IOException throw new UnsupportedOperationException(); } - private void init() throws IOException, ExecutionException, InterruptedException { + private void init() { if (jp == null) { - InputStream is = future.get(); - if (is == null) { - throw new IOException(String.format("query[%s] url[%s] timed out", query, url)); - } else { - jp = mapper.getFactory().createParser(is).configure(JsonParser.Feature.AUTO_CLOSE_SOURCE, true); - } - final JsonToken nextToken = jp.nextToken(); - if (nextToken == JsonToken.START_OBJECT) { - QueryInterruptedException cause = jp.getCodec().readValue(jp, QueryInterruptedException.class); - throw new QueryInterruptedException(cause); - } else if (nextToken != JsonToken.START_ARRAY) { - throw new IAE("Next token wasn't a START_ARRAY, was[%s] from url [%s]", jp.getCurrentToken(), url); - } else { - jp.nextToken(); - objectCodec = jp.getCodec(); + try { + InputStream is = future.get(); + if (is == null) { + throw new IOException(String.format("query[%s] url[%s] timed out", query, url)); + } else { + jp = mapper.getFactory().createParser(is).configure(JsonParser.Feature.AUTO_CLOSE_SOURCE, true); + } + final JsonToken nextToken = jp.nextToken(); + if (nextToken == JsonToken.START_OBJECT) { + QueryInterruptedException cause = jp.getCodec().readValue(jp, QueryInterruptedException.class); + throw new QueryInterruptedException(cause); + } else if (nextToken != JsonToken.START_ARRAY) { + throw new IAE("Next token wasn't a START_ARRAY, was[%s] from url [%s]", jp.getCurrentToken(), url); + } else { + jp.nextToken(); + objectCodec = jp.getCodec(); + } + + } catch (IOException | InterruptedException | ExecutionException e) { + throw new RE( + e, + "Failure getting results for query[%s] url[%s] because of [%s]", + query, + url, + e.getMessage() + ); } } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidScanQueryRecordReader.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidScanQueryRecordReader.java index 6a843aaf16..9afb76a12f 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidScanQueryRecordReader.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidScanQueryRecordReader.java @@ -48,8 +48,8 @@ if (compactedValues.hasNext()) { return true; } - if (queryResultsIterator.hasNext()) { - ScanResultValue current = queryResultsIterator.next(); + if (getQueryResultsIterator().hasNext()) { + ScanResultValue current = getQueryResultsIterator().next(); //noinspection unchecked compactedValues = ((List>) current.getEvents()).iterator(); return nextKeyValue(); @@ -82,7 +82,7 @@ } @Override public float getProgress() { - return queryResultsIterator.hasNext() || compactedValues.hasNext() ? 0 : 1; + return getQueryResultsIterator().hasNext() || compactedValues.hasNext() ? 0 : 1; } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidSelectQueryRecordReader.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidSelectQueryRecordReader.java index 0b88fe2588..907558fe48 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidSelectQueryRecordReader.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidSelectQueryRecordReader.java @@ -52,8 +52,8 @@ if (values.hasNext()) { return true; } - if (queryResultsIterator.hasNext()) { - Result current = queryResultsIterator.next(); + if (getQueryResultsIterator().hasNext()) { + Result current = getQueryResultsIterator().next(); values = current.getValue().getEvents().iterator(); return nextKeyValue(); } @@ -86,7 +86,7 @@ } @Override public float getProgress() { - return queryResultsIterator.hasNext() || values.hasNext() ? 0 : 1; + return getQueryResultsIterator().hasNext() || values.hasNext() ? 0 : 1; } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTimeseriesQueryRecordReader.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTimeseriesQueryRecordReader.java index d8d261bfd3..95af15d2fa 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTimeseriesQueryRecordReader.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTimeseriesQueryRecordReader.java @@ -44,8 +44,8 @@ protected JavaType getResultTypeDef() { @Override public boolean nextKeyValue() { - if (queryResultsIterator.hasNext()) { - current = queryResultsIterator.next(); + if (getQueryResultsIterator().hasNext()) { + current = getQueryResultsIterator().next(); return true; } return false; @@ -83,7 +83,7 @@ public boolean next(NullWritable key, DruidWritable value) { @Override public float getProgress() throws IOException { - return queryResultsIterator.hasNext() ? 0 : 1; + return getQueryResultsIterator().hasNext() ? 0 : 1; } } diff --git a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTopNQueryRecordReader.java b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTopNQueryRecordReader.java index 743858b692..57c8b0ef14 100644 --- a/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTopNQueryRecordReader.java +++ b/druid-handler/src/java/org/apache/hadoop/hive/druid/serde/DruidTopNQueryRecordReader.java @@ -53,8 +53,8 @@ if (values.hasNext()) { return true; } - if (queryResultsIterator.hasNext()) { - current = queryResultsIterator.next(); + if (getQueryResultsIterator().hasNext()) { + current = getQueryResultsIterator().next(); values = current.getValue().getValue().iterator(); return nextKeyValue(); } @@ -90,7 +90,7 @@ } @Override public float getProgress() { - return queryResultsIterator.hasNext() || values.hasNext() ? 0 : 1; + return getQueryResultsIterator().hasNext() || values.hasNext() ? 0 : 1; } } diff --git a/druid-handler/src/test/org/apache/hadoop/hive/druid/serde/TestDruidSerDe.java b/druid-handler/src/test/org/apache/hadoop/hive/druid/serde/TestDruidSerDe.java index 546eac6964..123112c740 100644 --- a/druid-handler/src/test/org/apache/hadoop/hive/druid/serde/TestDruidSerDe.java +++ b/druid-handler/src/test/org/apache/hadoop/hive/druid/serde/TestDruidSerDe.java @@ -808,8 +808,8 @@ private static Properties createPropertiesQuery(String dataSource, DruidQueryRecordReader reader = DruidQueryBasedInputFormat.getDruidQueryReader(queryType); final HiveDruidSplit split = new HiveDruidSplit(jsonQuery, new Path("empty"), new String[]{"testing_host"}); - - reader.initialize(split, DruidStorageHandlerUtils.JSON_MAPPER, DruidStorageHandlerUtils.SMILE_MAPPER, httpClient); + Configuration conf = new Configuration(); + reader.initialize(split, DruidStorageHandlerUtils.JSON_MAPPER, DruidStorageHandlerUtils.SMILE_MAPPER, httpClient, conf); StructObjectInspector oi = (StructObjectInspector) serDe.getObjectInspector(); List fieldRefs = oi.getAllStructFieldRefs(); @@ -834,7 +834,7 @@ private static Properties createPropertiesQuery(String dataSource, futureResult.set(new ByteArrayInputStream(resultString)); when(httpClient.go(anyObject(), any(HttpResponseHandler.class))).thenReturn(futureResult); reader = DruidQueryBasedInputFormat.getDruidQueryReader(queryType); - reader.initialize(split, DruidStorageHandlerUtils.JSON_MAPPER, DruidStorageHandlerUtils.SMILE_MAPPER, httpClient); + reader.initialize(split, DruidStorageHandlerUtils.JSON_MAPPER, DruidStorageHandlerUtils.SMILE_MAPPER, httpClient, conf); pos = 0; while (reader.nextKeyValue()) { diff --git a/itests/qtest-druid/pom.xml b/itests/qtest-druid/pom.xml index 3b9c5c3ef7..e693283c0c 100644 --- a/itests/qtest-druid/pom.xml +++ b/itests/qtest-druid/pom.xml @@ -104,6 +104,11 @@ + + org.apache.druid.extensions + druid-bloom-filter + ${druid.version} + org.apache.druid.extensions druid-kafka-indexing-service diff --git a/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java b/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java index c010b18b61..8017c88c62 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/metadata/HiveStorageHandler.java @@ -27,6 +27,7 @@ import org.apache.hadoop.hive.metastore.api.Table; import org.apache.hadoop.hive.ql.hooks.WriteEntity; import org.apache.hadoop.hive.ql.plan.ExprNodeDesc; +import org.apache.hadoop.hive.ql.plan.OperatorDesc; import org.apache.hadoop.hive.ql.plan.TableDesc; import org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider; import org.apache.hadoop.hive.serde2.AbstractSerDe; @@ -184,4 +185,17 @@ default LockType getLockType(WriteEntity writeEntity){ default boolean addDynamicSplitPruningEdge(ExprNodeDesc syntheticFilterPredicate) { return false; } + + /** + * Used to add additional operator specific information from storage handler during DESCRIBE EXTENDED statement + * + * @param operatorDesc operatorDesc + * @param initialProps Map containing initial operator properties + * @return Map containing additional operator specific information from storage handler + * OR `initialProps` if the storage handler choose to not provide any such information. + */ + public default Map getOperatorDescProperties(OperatorDesc operatorDesc, Map initialProps) + { + return initialProps; + } } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java index 374004f309..0f95d7788c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java @@ -286,8 +286,10 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, Obje andArgs.add(desc.getPredicate()); andArgs.addAll(newBetweenNodes); andArgs.addAll(newBloomFilterNodes); - ExprNodeDesc andExpr = ExprNodeGenericFuncDesc.newInstance( + ExprNodeGenericFuncDesc andExpr = ExprNodeGenericFuncDesc.newInstance( FunctionRegistry.getFunctionInfo("and").getGenericUDF(), andArgs); + // Also pass in filter as tableScan filterExpr + ts.getConf().setFilterExpr(andExpr); desc.setPredicate(andExpr); } } 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 192c04c661..d8083f4120 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 @@ -18,16 +18,9 @@ package org.apache.hadoop.hive.ql.plan; -import java.io.Serializable; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.BitSet; -import java.util.List; -import java.util.Map; -import java.util.Objects; - import org.apache.hadoop.hive.common.type.DataTypePhysicalVariation; import org.apache.hadoop.hive.ql.io.AcidUtils; +import org.apache.hadoop.hive.ql.metadata.HiveStorageHandler; import org.apache.hadoop.hive.ql.metadata.Table; import org.apache.hadoop.hive.ql.metadata.VirtualColumn; import org.apache.hadoop.hive.ql.optimizer.signature.Signature; @@ -38,6 +31,14 @@ import org.apache.hadoop.hive.serde.serdeConstants; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.BitSet; +import java.util.List; +import java.util.Map; +import java.util.Objects; + /** * 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 @@ -471,9 +472,16 @@ public boolean isNeedSkipHeaderFooters() { } @Override - @Explain(displayName = "properties", explainLevels = { Level.DEFAULT, Level.USER, Level.EXTENDED }) public Map getOpProps() { - return opProps; + return opProps; + } + + @Explain(displayName = "properties", explainLevels = { Level.DEFAULT, Level.USER, Level.EXTENDED }) + public Map getOpPropsWithStorageHandlerProps() { + HiveStorageHandler storageHandler = tableMetadata.getStorageHandler(); + return storageHandler == null + ? opProps + : storageHandler.getOperatorDescProperties(this, opProps); } public class TableScanOperatorExplainVectorization extends OperatorExplainVectorization { diff --git a/ql/src/test/queries/clientpositive/druidmini_semijoin_reduction_all_types.q b/ql/src/test/queries/clientpositive/druidmini_semijoin_reduction_all_types.q new file mode 100644 index 0000000000..370d887bd2 --- /dev/null +++ b/ql/src/test/queries/clientpositive/druidmini_semijoin_reduction_all_types.q @@ -0,0 +1,144 @@ +--! qt:dataset:srcpart +--! qt:dataset:druid_table_alltypesorc +--! qt:dataset:alltypesorc + +set hive.compute.query.using.stats=false; +set hive.mapred.mode=nonstrict; +set hive.explain.user=false; +set hive.optimize.ppd=true; +set hive.ppd.remove.duplicatefilters=true; +set hive.tez.dynamic.partition.pruning=true; +set hive.tez.dynamic.semijoin.reduction=true; +set hive.optimize.metadataonly=false; +set hive.optimize.index.filter=true; +set hive.stats.autogather=true; +set hive.tez.bigtable.minsize.semijoin.reduction=1; +set hive.tez.min.bloom.filter.entries=1; +set hive.stats.fetch.column.stats=true; +set hive.disable.unsafe.external.table.operations=false; +set hive.tez.dynamic.semijoin.reduction.for.mapjoin=true; + +DROP TABLE IF EXISTS alltypesorc_small; +CREATE TABLE alltypesorc_small( + ctinyint TINYINT, + csmallint SMALLINT, + cint INT, + cbigint BIGINT, + cfloat FLOAT, + cdouble DOUBLE, + cstring1 STRING, + cstring2 STRING, + ctimestamp1 TIMESTAMP, + cboolean1 BOOLEAN, + cboolean2 BOOLEAN) + STORED AS ORC; +Insert into table alltypesorc_small +Select ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, cast(`__time` as timestamp), cboolean1, cboolean2 from druid_table_alltypesorc where cstring2 like '%a%' and cstring1 like '%a%'; +Select count(*) from alltypesorc_small; +Select count(*) from druid_table_alltypesorc; + +DESCRIBE druid_table_alltypesorc; +DESCRIBE alltypesorc_small; + +-- Test Joins on all column types one by one +-- String +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1); + +-- tinyint +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint); + +-- smallint +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint); + +-- int +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint); + +-- bigint +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint); + +-- float +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat); + +-- double +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble); +set hive.disable.unsafe.external.table.operations=true; + +-- timestamp +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = druid_table_alltypesorc.`__time`); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)); + +-- boolean +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1); + + +-- Test Casts + +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring); + + +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring); + + +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring); + + + + + + + + + + + + + + + diff --git a/ql/src/test/queries/clientpositive/druidmini_test_cast.q b/ql/src/test/queries/clientpositive/druidmini_test_cast.q new file mode 100644 index 0000000000..c9b470d3d3 --- /dev/null +++ b/ql/src/test/queries/clientpositive/druidmini_test_cast.q @@ -0,0 +1,128 @@ +--! qt:dataset:srcpart +--! qt:dataset:druid_table_alltypesorc +--! qt:dataset:alltypesorc + +DROP TABLE IF EXISTS alltypesorc_small; +CREATE TABLE alltypesorc_small( + ctinyint TINYINT, + csmallint SMALLINT, + cint INT, + cbigint BIGINT, + cfloat FLOAT, + cdouble DOUBLE, + cstring1 STRING, + cstring2 STRING, + ctimestamp1 TIMESTAMP, + cboolean1 BOOLEAN, + cboolean2 BOOLEAN) + STORED AS ORC; +Insert into table alltypesorc_small +Select ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, cast(`__time` as timestamp), cboolean1, cboolean2 from druid_table_alltypesorc where cstring2 like '%a%' and cstring1 like '%a%'; +Select count(*) from alltypesorc_small; +Select count(*) from druid_table_alltypesorc; + +DESCRIBE druid_table_alltypesorc; +DESCRIBE alltypesorc_small; + +-- Test Joins on all column types one by one +-- String +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1); + +-- tinyint +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint); + +-- smallint +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint); + +-- int +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint); + +-- bigint +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint); + +-- float +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat); + +-- double +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble); +set hive.disable.unsafe.external.table.operations=true; + +-- timestamp +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = druid_table_alltypesorc.`__time`); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)); + +-- boolean +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1); + + +-- Test Casts + +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cintstring); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cintstring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cintstring); + + +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdoublestring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdoublestring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdoublestring); + + +set hive.disable.unsafe.external.table.operations=false; +EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloatstring); +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloatstring); +set hive.disable.unsafe.external.table.operations=true; +select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloatstring); + + + + + + + + + + + + + + + diff --git a/ql/src/test/results/clientpositive/druid/druidmini_semijoin_reduction_all_types.q.out b/ql/src/test/results/clientpositive/druid/druidmini_semijoin_reduction_all_types.q.out new file mode 100644 index 0000000000..dddf0b9d64 --- /dev/null +++ b/ql/src/test/results/clientpositive/druid/druidmini_semijoin_reduction_all_types.q.out @@ -0,0 +1,1973 @@ +PREHOOK: query: DROP TABLE IF EXISTS alltypesorc_small +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS alltypesorc_small +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE alltypesorc_small( + ctinyint TINYINT, + csmallint SMALLINT, + cint INT, + cbigint BIGINT, + cfloat FLOAT, + cdouble DOUBLE, + cstring1 STRING, + cstring2 STRING, + ctimestamp1 TIMESTAMP, + cboolean1 BOOLEAN, + cboolean2 BOOLEAN) + STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alltypesorc_small +POSTHOOK: query: CREATE TABLE alltypesorc_small( + ctinyint TINYINT, + csmallint SMALLINT, + cint INT, + cbigint BIGINT, + cfloat FLOAT, + cdouble DOUBLE, + cstring1 STRING, + cstring2 STRING, + ctimestamp1 TIMESTAMP, + cboolean1 BOOLEAN, + cboolean2 BOOLEAN) + STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alltypesorc_small +PREHOOK: query: Insert into table alltypesorc_small +Select ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, cast(`__time` as timestamp), cboolean1, cboolean2 from druid_table_alltypesorc where cstring2 like '%a%' and cstring1 like '%a%' +PREHOOK: type: QUERY +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: default@alltypesorc_small +POSTHOOK: query: Insert into table alltypesorc_small +Select ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, cast(`__time` as timestamp), cboolean1, cboolean2 from druid_table_alltypesorc where cstring2 like '%a%' and cstring1 like '%a%' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: default@alltypesorc_small +POSTHOOK: Lineage: alltypesorc_small.cbigint SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cboolean1 SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cboolean2 SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cdouble SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cdouble, type:double, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cfloat SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cfloat, type:float, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cint SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cint, type:int, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.csmallint SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cstring1 SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cstring1, type:string, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.cstring2 SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:cstring2, type:string, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.ctimestamp1 SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:vc, type:timestamp, comment:from deserializer), ] +POSTHOOK: Lineage: alltypesorc_small.ctinyint SIMPLE [(druid_table_alltypesorc)druid_table_alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:from deserializer), ] +PREHOOK: query: Select count(*) from alltypesorc_small +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: Select count(*) from alltypesorc_small +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: Select count(*) from druid_table_alltypesorc +PREHOOK: type: QUERY +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: Select count(*) from druid_table_alltypesorc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +9173 +PREHOOK: query: DESCRIBE druid_table_alltypesorc +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: query: DESCRIBE druid_table_alltypesorc +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@druid_table_alltypesorc +__time timestamp with local time zone from deserializer +cstring1 string from deserializer +cstring2 string from deserializer +cdouble double from deserializer +cfloat float from deserializer +ctinyint tinyint from deserializer +csmallint smallint from deserializer +cint int from deserializer +cbigint bigint from deserializer +cboolean1 boolean from deserializer +cboolean2 boolean from deserializer +cintstring string from deserializer +cfloatstring string from deserializer +cdoublestring string from deserializer +PREHOOK: query: DESCRIBE alltypesorc_small +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@alltypesorc_small +POSTHOOK: query: DESCRIBE alltypesorc_small +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@alltypesorc_small +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +cboolean1 boolean +cboolean2 boolean +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: cstring1 is not null (type: boolean) + Statistics: Num rows: 69 Data size: 6969 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cstring1 is not null (type: boolean) + Statistics: Num rows: 69 Data size: 6969 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 6969 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: 69 Data size: 6969 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 6969 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=69) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cstring1 BETWEEN DynamicValue(RS_4_alltypesorc_small_cstring1_min) AND DynamicValue(RS_4_alltypesorc_small_cstring1_max) and in_bloom_filter(cstring1, DynamicValue(RS_4_alltypesorc_small_cstring1_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cstring1 + druid.fieldTypes string + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cstring1","lower":"DynamicValue(RS_4_alltypesorc_small_cstring1_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cstring1_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cstring1","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cstring1","value":null,"extractionFn":null}}]},"columns":["cstring1"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cstring1 BETWEEN DynamicValue(RS_4_alltypesorc_small_cstring1_min) AND DynamicValue(RS_4_alltypesorc_small_cstring1_max) and in_bloom_filter(cstring1, DynamicValue(RS_4_alltypesorc_small_cstring1_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cstring1 (type: string) + sort order: + + Map-reduce partition columns: cstring1 (type: string) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 cstring1 (type: string) + Statistics: Num rows: 10090 Data size: 1764118 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=69) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cstring1 = druid_table_alltypesorc.cstring1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: ctinyint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ctinyint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=3) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: tinyint), _col1 (type: tinyint), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (ctinyint BETWEEN DynamicValue(RS_4_alltypesorc_small_ctinyint_min) AND DynamicValue(RS_4_alltypesorc_small_ctinyint_max) and in_bloom_filter(ctinyint, DynamicValue(RS_4_alltypesorc_small_ctinyint_bloom_filter))) (type: boolean) + properties: + druid.fieldNames ctinyint + druid.fieldTypes tinyint + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"ctinyint","lower":"DynamicValue(RS_4_alltypesorc_small_ctinyint_min)","upper":"DynamicValue(RS_4_alltypesorc_small_ctinyint_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"ctinyint","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"ctinyint","value":null,"extractionFn":null}}]},"columns":["ctinyint"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ctinyint BETWEEN DynamicValue(RS_4_alltypesorc_small_ctinyint_min) AND DynamicValue(RS_4_alltypesorc_small_ctinyint_max) and in_bloom_filter(ctinyint, DynamicValue(RS_4_alltypesorc_small_ctinyint_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: ctinyint (type: tinyint) + sort order: + + Map-reduce partition columns: ctinyint (type: tinyint) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: tinyint) + 1 ctinyint (type: tinyint) + Statistics: Num rows: 10090 Data size: 38350 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=3) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: tinyint), _col1 (type: tinyint), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +73895 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctinyint = druid_table_alltypesorc.ctinyint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +73895 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: csmallint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: csmallint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: csmallint (type: smallint) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: smallint) + sort order: + + Map-reduce partition columns: _col0 (type: smallint) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: smallint) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: smallint), _col1 (type: smallint), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (csmallint BETWEEN DynamicValue(RS_4_alltypesorc_small_csmallint_min) AND DynamicValue(RS_4_alltypesorc_small_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_4_alltypesorc_small_csmallint_bloom_filter))) (type: boolean) + properties: + druid.fieldNames csmallint + druid.fieldTypes smallint + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"csmallint","lower":"DynamicValue(RS_4_alltypesorc_small_csmallint_min)","upper":"DynamicValue(RS_4_alltypesorc_small_csmallint_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"csmallint","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"csmallint","value":null,"extractionFn":null}}]},"columns":["csmallint"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (csmallint BETWEEN DynamicValue(RS_4_alltypesorc_small_csmallint_min) AND DynamicValue(RS_4_alltypesorc_small_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_4_alltypesorc_small_csmallint_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: csmallint (type: smallint) + sort order: + + Map-reduce partition columns: csmallint (type: smallint) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: smallint) + 1 csmallint (type: smallint) + Statistics: Num rows: 10090 Data size: 38350 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: smallint), _col1 (type: smallint), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +211968 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.csmallint = druid_table_alltypesorc.csmallint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +211968 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: cint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=69) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cint BETWEEN DynamicValue(RS_4_alltypesorc_small_cint_min) AND DynamicValue(RS_4_alltypesorc_small_cint_max) and in_bloom_filter(cint, DynamicValue(RS_4_alltypesorc_small_cint_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cint + druid.fieldTypes int + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cint","lower":"DynamicValue(RS_4_alltypesorc_small_cint_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cint_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cint","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cint","value":null,"extractionFn":null}}]},"columns":["cint"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cint BETWEEN DynamicValue(RS_4_alltypesorc_small_cint_min) AND DynamicValue(RS_4_alltypesorc_small_cint_max) and in_bloom_filter(cint, DynamicValue(RS_4_alltypesorc_small_cint_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cint (type: int) + sort order: + + Map-reduce partition columns: cint (type: int) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 cint (type: int) + Statistics: Num rows: 10090 Data size: 38350 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=69) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cint = druid_table_alltypesorc.cint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: cbigint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cbigint is not null (type: boolean) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: bigint) + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=69) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + 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: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cbigint BETWEEN DynamicValue(RS_4_alltypesorc_small_cbigint_min) AND DynamicValue(RS_4_alltypesorc_small_cbigint_max) and in_bloom_filter(cbigint, DynamicValue(RS_4_alltypesorc_small_cbigint_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cbigint + druid.fieldTypes bigint + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cbigint","lower":"DynamicValue(RS_4_alltypesorc_small_cbigint_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cbigint_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cbigint","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cbigint","value":null,"extractionFn":null}}]},"columns":["cbigint"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 69728 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cbigint BETWEEN DynamicValue(RS_4_alltypesorc_small_cbigint_min) AND DynamicValue(RS_4_alltypesorc_small_cbigint_max) and in_bloom_filter(cbigint, DynamicValue(RS_4_alltypesorc_small_cbigint_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 69728 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cbigint (type: bigint) + sort order: + + Map-reduce partition columns: cbigint (type: bigint) + Statistics: Num rows: 9173 Data size: 69728 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: bigint) + 1 cbigint (type: bigint) + Statistics: Num rows: 10090 Data size: 76700 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=69) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + 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: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cbigint = druid_table_alltypesorc.cbigint) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: cfloat is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cfloat is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cfloat (type: float) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: float) + sort order: + + Map-reduce partition columns: _col0 (type: float) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: float) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=3) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cfloat BETWEEN DynamicValue(RS_4_alltypesorc_small_cfloat_min) AND DynamicValue(RS_4_alltypesorc_small_cfloat_max) and in_bloom_filter(cfloat, DynamicValue(RS_4_alltypesorc_small_cfloat_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cfloat + druid.fieldTypes float + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"not","field":{"type":"selector","dimension":"cfloat","value":null,"extractionFn":null}},"columns":["cfloat"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cfloat BETWEEN DynamicValue(RS_4_alltypesorc_small_cfloat_min) AND DynamicValue(RS_4_alltypesorc_small_cfloat_max) and in_bloom_filter(cfloat, DynamicValue(RS_4_alltypesorc_small_cfloat_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cfloat (type: float) + sort order: + + Map-reduce partition columns: cfloat (type: float) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: float) + 1 cfloat (type: float) + Statistics: Num rows: 10090 Data size: 38350 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=3) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +73895 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cfloat = druid_table_alltypesorc.cfloat) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +73895 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: cdouble is not null (type: boolean) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cdouble is not null (type: boolean) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cdouble (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cdouble BETWEEN DynamicValue(RS_4_alltypesorc_small_cdouble_min) AND DynamicValue(RS_4_alltypesorc_small_cdouble_max) and in_bloom_filter(cdouble, DynamicValue(RS_4_alltypesorc_small_cdouble_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cdouble + druid.fieldTypes double + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cdouble","lower":"DynamicValue(RS_4_alltypesorc_small_cdouble_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cdouble_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cdouble","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cdouble","value":null,"extractionFn":null}}]},"columns":["cdouble"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 69728 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cdouble BETWEEN DynamicValue(RS_4_alltypesorc_small_cdouble_min) AND DynamicValue(RS_4_alltypesorc_small_cdouble_max) and in_bloom_filter(cdouble, DynamicValue(RS_4_alltypesorc_small_cdouble_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 69728 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cdouble (type: double) + sort order: + + Map-reduce partition columns: cdouble (type: double) + Statistics: Num rows: 9173 Data size: 69728 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: double) + 1 cdouble (type: double) + Statistics: Num rows: 10090 Data size: 76700 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cdouble = druid_table_alltypesorc.cdouble) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +211968 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = druid_table_alltypesorc.`__time`) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = druid_table_alltypesorc.`__time`) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: CAST( ctimestamp1 AS timestamp with local time zone) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: CAST( ctimestamp1 AS timestamp with local time zone) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( ctimestamp1 AS timestamp with local time zone) (type: timestamp with local time zone) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp with local time zone) + sort order: + + Map-reduce partition columns: _col0 (type: timestamp with local time zone) + Statistics: Num rows: 69 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: timestamp with local time zone) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=69) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: timestamp with local time zone), _col1 (type: timestamp with local time zone), _col2 (type: binary) + Execution mode: llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (vc BETWEEN DynamicValue(RS_4_alltypesorc_small_ctimestamp1_min) AND DynamicValue(RS_4_alltypesorc_small_ctimestamp1_max) and in_bloom_filter(vc, DynamicValue(RS_4_alltypesorc_small_ctimestamp1_bloom_filter))) (type: boolean) + properties: + druid.fieldNames vc + druid.fieldTypes timestamp with local time zone + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":null,"columns":["vc"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (vc BETWEEN DynamicValue(RS_4_alltypesorc_small_ctimestamp1_min) AND DynamicValue(RS_4_alltypesorc_small_ctimestamp1_max) and in_bloom_filter(vc, DynamicValue(RS_4_alltypesorc_small_ctimestamp1_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: vc (type: timestamp with local time zone) + sort order: + + Map-reduce partition columns: vc (type: timestamp with local time zone) + Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: timestamp with local time zone) + 1 vc (type: timestamp with local time zone) + Statistics: Num rows: 10090 Data size: 383504 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=69) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: timestamp with local time zone), _col1 (type: timestamp with local time zone), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +434493 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.ctimestamp1 = cast(druid_table_alltypesorc.`__time` as timestamp)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +434493 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: cboolean1 is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cboolean1 is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cboolean1 (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean) + sort order: + + Map-reduce partition columns: _col0 (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean), _col1 (type: boolean), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cboolean1 BETWEEN DynamicValue(RS_4_alltypesorc_small_cboolean1_min) AND DynamicValue(RS_4_alltypesorc_small_cboolean1_max) and in_bloom_filter(cboolean1, DynamicValue(RS_4_alltypesorc_small_cboolean1_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cboolean1 + druid.fieldTypes boolean + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"not","field":{"type":"selector","dimension":"cboolean1","value":null,"extractionFn":null}},"columns":["cboolean1"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cboolean1 BETWEEN DynamicValue(RS_4_alltypesorc_small_cboolean1_min) AND DynamicValue(RS_4_alltypesorc_small_cboolean1_max) and in_bloom_filter(cboolean1, DynamicValue(RS_4_alltypesorc_small_cboolean1_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cboolean1 (type: boolean) + sort order: + + Map-reduce partition columns: cboolean1 (type: boolean) + Statistics: Num rows: 9173 Data size: 34864 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: boolean) + 1 cboolean1 (type: boolean) + Statistics: Num rows: 10090 Data size: 38350 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean), _col1 (type: boolean), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +418071 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (alltypesorc_small.cboolean1 = druid_table_alltypesorc.cboolean1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +418071 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: CAST( cint AS STRING) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: CAST( cint AS STRING) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( cint AS STRING) (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 12696 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: 69 Data size: 12696 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 12696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=69) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cintstring BETWEEN DynamicValue(RS_4_alltypesorc_small_cint_min) AND DynamicValue(RS_4_alltypesorc_small_cint_max) and in_bloom_filter(cintstring, DynamicValue(RS_4_alltypesorc_small_cint_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cintstring + druid.fieldTypes string + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cintstring","lower":"DynamicValue(RS_4_alltypesorc_small_cint_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cint_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cintstring","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cintstring","value":null,"extractionFn":null}}]},"columns":["cintstring"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cintstring BETWEEN DynamicValue(RS_4_alltypesorc_small_cint_min) AND DynamicValue(RS_4_alltypesorc_small_cint_max) and in_bloom_filter(cintstring, DynamicValue(RS_4_alltypesorc_small_cint_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cintstring (type: string) + sort order: + + Map-reduce partition columns: cintstring (type: string) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 cintstring (type: string) + Statistics: Num rows: 10090 Data size: 1764118 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=69) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +32 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cint as string) = druid_table_alltypesorc.cintstring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +69 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: CAST( cdouble AS STRING) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: CAST( cdouble AS STRING) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( cdouble AS STRING) (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 12696 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: 69 Data size: 12696 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 12696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cdoublestring BETWEEN DynamicValue(RS_4_alltypesorc_small_cdouble_min) AND DynamicValue(RS_4_alltypesorc_small_cdouble_max) and in_bloom_filter(cdoublestring, DynamicValue(RS_4_alltypesorc_small_cdouble_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cdoublestring + druid.fieldTypes string + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cdoublestring","lower":"DynamicValue(RS_4_alltypesorc_small_cdouble_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cdouble_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cdoublestring","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cdoublestring","value":null,"extractionFn":null}}]},"columns":["cdoublestring"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cdoublestring BETWEEN DynamicValue(RS_4_alltypesorc_small_cdouble_min) AND DynamicValue(RS_4_alltypesorc_small_cdouble_max) and in_bloom_filter(cdoublestring, DynamicValue(RS_4_alltypesorc_small_cdouble_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cdoublestring (type: string) + sort order: + + Map-reduce partition columns: cdoublestring (type: string) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 cdoublestring (type: string) + Statistics: Num rows: 10090 Data size: 1764118 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +0 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cdouble as string) = druid_table_alltypesorc.cdoublestring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +0 +PREHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: EXPLAIN select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Reducer 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc_small + filterExpr: CAST( cfloat AS STRING) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: CAST( cfloat AS STRING) is not null (type: boolean) + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( cfloat AS STRING) (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 12696 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: 69 Data size: 12696 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 12696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=3) + minReductionHashAggr: 0.98550725 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: druid_table_alltypesorc + filterExpr: (cfloatstring BETWEEN DynamicValue(RS_4_alltypesorc_small_cfloat_min) AND DynamicValue(RS_4_alltypesorc_small_cfloat_max) and in_bloom_filter(cfloatstring, DynamicValue(RS_4_alltypesorc_small_cfloat_bloom_filter))) (type: boolean) + properties: + druid.fieldNames cfloatstring + druid.fieldTypes string + druid.query.json {"queryType":"scan","dataSource":{"type":"table","name":"default.druid_table_alltypesorc"},"intervals":{"type":"LegacySegmentSpec","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]},"virtualColumns":[],"resultFormat":"compactedList","batchSize":20480,"limit":9223372036854775807,"filter":{"type":"and","fields":[{"type":"and","fields":[{"type":"bound","dimension":"cfloatstring","lower":"DynamicValue(RS_4_alltypesorc_small_cfloat_min)","upper":"DynamicValue(RS_4_alltypesorc_small_cfloat_max)","lowerStrict":false,"upperStrict":false,"extractionFn":null,"ordering":{"type":"numeric"}},{"type":"bloom","dimension":"cfloatstring","bloomKFilter":"BAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA","extractionFn":null}]},{"type":"not","field":{"type":"selector","dimension":"cfloatstring","value":null,"extractionFn":null}}]},"columns":["cfloatstring"],"legacy":null,"context":null,"descending":false,"granularity":{"type":"all"}} + druid.query.type scan + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cfloatstring BETWEEN DynamicValue(RS_4_alltypesorc_small_cfloat_min) AND DynamicValue(RS_4_alltypesorc_small_cfloat_max) and in_bloom_filter(cfloatstring, DynamicValue(RS_4_alltypesorc_small_cfloat_bloom_filter))) (type: boolean) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: cfloatstring (type: string) + sort order: + + Map-reduce partition columns: cfloatstring (type: string) + Statistics: Num rows: 9173 Data size: 1603744 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 cfloatstring (type: string) + Statistics: Num rows: 10090 Data size: 1764118 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=3) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +44951 +PREHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc_small +PREHOOK: Input: default@druid_table_alltypesorc +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: select count(*) from alltypesorc_small join druid_table_alltypesorc on (cast(alltypesorc_small.cfloat as string) = druid_table_alltypesorc.cfloatstring) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc_small +POSTHOOK: Input: default@druid_table_alltypesorc +POSTHOOK: Output: hdfs://### HDFS PATH ### +73895 -- 2.20.1 (Apple Git-117)