diff --git common/src/java/org/apache/hadoop/hive/conf/HiveConf.java common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index b0cb98b..3fe67b2 100644 --- common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -1044,7 +1044,7 @@ "That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small, it can make very slow, single MR.\n" + "The optimization will be automatically disabled if number of reducers would be less than specified value."), - HIVEOPTSORTDYNAMICPARTITION("hive.optimize.sort.dynamic.partition", true, + HIVEOPTSORTDYNAMICPARTITION("hive.optimize.sort.dynamic.partition", false, "When enabled dynamic partitioning column will be globally sorted.\n" + "This way we can keep only one record writer open for each partition value\n" + "in the reducer thereby reducing the memory pressure on reducers."), diff --git data/files/dynpart_test.txt data/files/dynpart_test.txt new file mode 100644 index 0000000..ab6cd4a --- /dev/null +++ data/files/dynpart_test.txt @@ -0,0 +1,24 @@ +24526172.99-11.32 +245261710022.633952.8 +24526172.1-2026.3 +2452617552.96-1363.84 +24526171765.07-4648.8 +2452617879.07-2185.76 +24526177412.832071.68 +245261785.825.61 +2452617565.92196.48 +24526175362.01-600.28 +24526173423.95-3164.07 +24526384133.98-775.72 +245263810171.1660.48 +2452638317.87-3775.38 +2452638156.67-4626.56 +24526381327.0857.97 +24526381971.35-488.25 +2452638181.03-207.24 +2452638267.01-3266.36 +24526380.15-241.22 +24526381524.33494.37 +2452638150.39-162.12 +24526381413.19178.08 +24526384329.49-4000.51 diff --git itests/src/test/resources/testconfiguration.properties itests/src/test/resources/testconfiguration.properties index e525798..b7de49a 100644 --- itests/src/test/resources/testconfiguration.properties +++ itests/src/test/resources/testconfiguration.properties @@ -75,6 +75,7 @@ minitez.query.files.shared=alter_merge_2_orc.q,\ disable_merge_for_bucketing.q,\ dynpart_sort_opt_vectorization.q,\ dynpart_sort_optimization.q,\ + dynpart_sort_optimization2.q,\ enforce_order.q,\ filter_join_breaktask.q,\ filter_join_breaktask2.q,\ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java index 3ff0782..e02071c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/FileSinkOperator.java @@ -29,6 +29,8 @@ import java.util.Map; import java.util.Set; +import org.apache.commons.logging.Log; +import org.apache.commons.logging.LogFactory; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileStatus; import org.apache.hadoop.fs.FileSystem; @@ -38,13 +40,13 @@ import org.apache.hadoop.hive.conf.HiveConf; import org.apache.hadoop.hive.ql.ErrorMsg; import org.apache.hadoop.hive.ql.io.AcidUtils; -import org.apache.hadoop.hive.ql.io.RecordUpdater; -import org.apache.hadoop.hive.ql.io.StatsProvidingRecordWriter; import org.apache.hadoop.hive.ql.io.HiveFileFormatUtils; import org.apache.hadoop.hive.ql.io.HiveKey; import org.apache.hadoop.hive.ql.io.HiveOutputFormat; import org.apache.hadoop.hive.ql.io.HivePartitioner; import org.apache.hadoop.hive.ql.io.HivePassThroughOutputFormat; +import org.apache.hadoop.hive.ql.io.RecordUpdater; +import org.apache.hadoop.hive.ql.io.StatsProvidingRecordWriter; import org.apache.hadoop.hive.ql.metadata.HiveException; import org.apache.hadoop.hive.ql.metadata.HiveFatalException; import org.apache.hadoop.hive.ql.plan.DynamicPartitionCtx; @@ -72,14 +74,16 @@ import org.apache.hadoop.mapred.JobConf; import org.apache.hadoop.util.ReflectionUtils; -import com.google.common.collect.Lists; - /** * File Sink operator implementation. **/ public class FileSinkOperator extends TerminalOperator implements Serializable { + public static final Log LOG = LogFactory.getLog(FileSinkOperator.class); + private static final boolean isInfoEnabled = LOG.isInfoEnabled(); + private static final boolean isDebugEnabled = LOG.isDebugEnabled(); + protected transient HashMap valToPaths; protected transient int numDynParts; protected transient List dpColNames; @@ -101,10 +105,6 @@ protected transient boolean isCollectRWStats; private transient FSPaths prevFsp; private transient FSPaths fpaths; - private transient ObjectInspector keyOI; - private transient List keyWritables; - private transient List keys; - private transient int numKeyColToRead; private StructField recIdField; // field to find record identifier in private StructField bucketField; // field bucket is in in record id private StructObjectInspector recIdInspector; // OI for inspecting record id @@ -131,9 +131,6 @@ int acidLastBucket = -1; int acidFileOffset = -1; - public FSPaths() { - } - public FSPaths(Path specPath) { tmpPath = Utilities.toTempPath(specPath); taskOutputTempPath = Utilities.toTaskTempPath(specPath); @@ -141,7 +138,9 @@ public FSPaths(Path specPath) { finalPaths = new Path[numFiles]; outWriters = new RecordWriter[numFiles]; updaters = new RecordUpdater[numFiles]; - LOG.debug("Created slots for " + numFiles); + if (isDebugEnabled) { + LOG.debug("Created slots for " + numFiles); + } stat = new Stat(); } @@ -326,7 +325,6 @@ protected void initializeOp(Configuration hconf) throws HiveException { parent = Utilities.toTempPath(conf.getDirName()); statsCollectRawDataSize = conf.isStatsCollectRawDataSize(); statsFromRecordWriter = new boolean[numFiles]; - serializer = (Serializer) conf.getTableInfo().getDeserializerClass().newInstance(); serializer.initialize(null, conf.getTableInfo().getProperties()); outputClass = serializer.getSerializedClass(); @@ -363,20 +361,6 @@ protected void initializeOp(Configuration hconf) throws HiveException { lbSetup(); } - int numPart = 0; - int numBuck = 0; - if (conf.getPartitionCols() != null && !conf.getPartitionCols().isEmpty()) { - numPart = conf.getPartitionCols().size(); - } - - // bucket number will exists only in PARTITION_BUCKET_SORTED mode - if (conf.getDpSortState().equals(DPSortState.PARTITION_BUCKET_SORTED)) { - numBuck = 1; - } - numKeyColToRead = numPart + numBuck; - keys = Lists.newArrayListWithCapacity(numKeyColToRead); - keyWritables = Lists.newArrayListWithCapacity(numKeyColToRead); - if (!bDynParts) { fsp = new FSPaths(specPath); @@ -423,7 +407,8 @@ private void dpSetup() { this.dpColNames = dpCtx.getDPColNames(); this.maxPartitions = dpCtx.getMaxPartitionsPerNode(); - assert numDynParts == dpColNames.size() : "number of dynamic paritions should be the same as the size of DP mapping"; + assert numDynParts == dpColNames.size() + : "number of dynamic paritions should be the same as the size of DP mapping"; if (dpColNames != null && dpColNames.size() > 0) { this.bDynParts = true; @@ -441,6 +426,9 @@ private void dpSetup() { newFieldsOI.add(sf.getFieldObjectInspector()); newFieldsName.add(sf.getFieldName()); this.dpStartCol++; + } else { + // once we found the start column for partition column we are done + break; } } assert newFieldsOI.size() > 0 : "new Fields ObjectInspector is empty"; @@ -457,11 +445,15 @@ protected void createBucketFiles(FSPaths fsp) throws HiveException { Set seenBuckets = new HashSet(); for (int idx = 0; idx < totalFiles; idx++) { if (this.getExecContext() != null && this.getExecContext().getFileId() != null) { - LOG.info("replace taskId from execContext "); + if (isInfoEnabled) { + LOG.info("replace taskId from execContext "); + } taskId = Utilities.replaceTaskIdFromFilename(taskId, this.getExecContext().getFileId()); - LOG.info("new taskId: FS " + taskId); + if (isInfoEnabled) { + LOG.info("new taskId: FS " + taskId); + } assert !multiFileSpray; assert totalFiles == 1; @@ -515,9 +507,13 @@ protected void createBucketForFileIdx(FSPaths fsp, int filesIdx) try { if (isNativeTable) { fsp.finalPaths[filesIdx] = fsp.getFinalPath(taskId, fsp.tmpPath, null); - LOG.info("Final Path: FS " + fsp.finalPaths[filesIdx]); + if (isInfoEnabled) { + LOG.info("Final Path: FS " + fsp.finalPaths[filesIdx]); + } fsp.outPaths[filesIdx] = fsp.getTaskOutPath(taskId); - LOG.info("Writing to temp file: FS " + fsp.outPaths[filesIdx]); + if (isInfoEnabled) { + LOG.info("Writing to temp file: FS " + fsp.outPaths[filesIdx]); + } } else { fsp.finalPaths[filesIdx] = fsp.outPaths[filesIdx] = specPath; } @@ -532,7 +528,9 @@ protected void createBucketForFileIdx(FSPaths fsp, int filesIdx) fsp.finalPaths[filesIdx] = fsp.getFinalPath(taskId, fsp.tmpPath, extension); } - LOG.info("New Final Path: FS " + fsp.finalPaths[filesIdx]); + if (isInfoEnabled) { + LOG.info("New Final Path: FS " + fsp.finalPaths[filesIdx]); + } if (isNativeTable) { // in recent hadoop versions, use deleteOnExit to clean tmp files. @@ -604,14 +602,22 @@ public void processOp(Object row, int tag) throws HiveException { updateProgress(); // if DP is enabled, get the final output writers and prepare the real output row - assert inputObjInspectors[0].getCategory() == ObjectInspector.Category.STRUCT : "input object inspector is not struct"; + assert inputObjInspectors[0].getCategory() == ObjectInspector.Category.STRUCT + : "input object inspector is not struct"; if (bDynParts) { + + // we need to read bucket number which is the last column in value (after partition columns) + if (conf.getDpSortState().equals(DPSortState.PARTITION_BUCKET_SORTED)) { + numDynParts += 1; + } + // copy the DP column values from the input row to dpVals dpVals.clear(); dpWritables.clear(); - ObjectInspectorUtils.partialCopyToStandardObject(dpWritables, row, dpStartCol, numDynParts, - (StructObjectInspector) inputObjInspectors[0], ObjectInspectorCopyOption.WRITABLE); + ObjectInspectorUtils.partialCopyToStandardObject(dpWritables, row, dpStartCol,numDynParts, + (StructObjectInspector) inputObjInspectors[0],ObjectInspectorCopyOption.WRITABLE); + // get a set of RecordWriter based on the DP column values // pass the null value along to the escaping process to determine what the dir should be for (Object o : dpWritables) { @@ -621,16 +627,11 @@ public void processOp(Object row, int tag) throws HiveException { dpVals.add(o.toString()); } } - // use SubStructObjectInspector to serialize the non-partitioning columns in the input row - recordValue = serializer.serialize(row, subSetOI); - // when dynamic partition sorting is not used, the DPSortState will be NONE - // in which we will fall back to old method of file system path creation - // i.e, having as many record writers as distinct values in partition column - if (conf.getDpSortState().equals(DPSortState.NONE)) { - fpaths = getDynOutPaths(dpVals, lbDirName); - } + fpaths = getDynOutPaths(dpVals, lbDirName); + // use SubStructObjectInspector to serialize the non-partitioning columns in the input row + recordValue = serializer.serialize(row, subSetOI); } else { if (lbDirName != null) { fpaths = lookupListBucketingPaths(lbDirName); @@ -686,8 +687,10 @@ public void processOp(Object row, int tag) throws HiveException { fpaths.updaters[++fpaths.acidFileOffset] = HiveFileFormatUtils.getAcidRecordUpdater( jc, conf.getTableInfo(), bucketNum, conf, fpaths.outPaths[fpaths.acidFileOffset], rowInspector, reporter, 0); - LOG.debug("Created updater for bucket number " + bucketNum + " using file " + - fpaths.outPaths[fpaths.acidFileOffset]); + if (isDebugEnabled) { + LOG.debug("Created updater for bucket number " + bucketNum + " using file " + + fpaths.outPaths[fpaths.acidFileOffset]); + } } if (conf.getWriteType() == AcidUtils.Operation.UPDATE) { @@ -834,10 +837,8 @@ protected FSPaths getDynOutPaths(List row, String lbDirName) throws Hive if (dpDir != null) { dpDir = appendToSource(lbDirName, dpDir); pathKey = dpDir; - int numericBucketNum = 0; if(conf.getDpSortState().equals(DPSortState.PARTITION_BUCKET_SORTED)) { String buckNum = row.get(row.size() - 1); - numericBucketNum = Integer.valueOf(buckNum); taskId = Utilities.replaceTaskIdFromFilename(Utilities.getTaskId(hconf), buckNum); pathKey = appendToSource(taskId, dpDir); } @@ -918,26 +919,6 @@ private String getDynPartDirectory(List row, List dpColNames) { } @Override - public void startGroup() throws HiveException { - if (!conf.getDpSortState().equals(DPSortState.NONE)) { - keyOI = getGroupKeyObjectInspector(); - keys.clear(); - keyWritables.clear(); - ObjectInspectorUtils.partialCopyToStandardObject(keyWritables, getGroupKeyObject(), 0, - numKeyColToRead, (StructObjectInspector) keyOI, ObjectInspectorCopyOption.WRITABLE); - - for (Object o : keyWritables) { - if (o == null || o.toString().length() == 0) { - keys.add(dpCtx.getDefaultPartitionName()); - } else { - keys.add(o.toString()); - } - } - fpaths = getDynOutPaths(keys, null); - } - } - - @Override public void closeOp(boolean abort) throws HiveException { if (!bDynParts && !filesCreated) { diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java index 62b6402..4632f08 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/GroupByOperator.java @@ -18,7 +18,22 @@ package org.apache.hadoop.hive.ql.exec; +import java.io.Serializable; +import java.lang.management.ManagementFactory; +import java.lang.management.MemoryMXBean; +import java.lang.reflect.Field; +import java.sql.Timestamp; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.HashMap; +import java.util.HashSet; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.Set; + import javolution.util.FastBitSet; + import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.hadoop.conf.Configuration; @@ -54,20 +69,6 @@ import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.Text; -import java.io.Serializable; -import java.lang.management.ManagementFactory; -import java.lang.management.MemoryMXBean; -import java.lang.reflect.Field; -import java.sql.Timestamp; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.HashMap; -import java.util.HashSet; -import java.util.Iterator; -import java.util.List; -import java.util.Map; -import java.util.Set; - /** * GroupBy operator implementation. */ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java index a066f98..3dc7c76 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java @@ -498,8 +498,6 @@ protected final void defaultStartGroup() throws HiveException { LOG.debug("Starting group for children:"); for (Operator op : childOperators) { - op.setGroupKeyObjectInspector(groupKeyOI); - op.setGroupKeyObject(groupKeyObject); op.startGroup(); } @@ -970,7 +968,6 @@ protected static StructObjectInspector initEvaluatorsAndReturnStruct( } protected transient Object groupKeyObject; - protected transient ObjectInspector groupKeyOI; public String getOperatorId() { return operatorId; @@ -1287,14 +1284,6 @@ public void setStatistics(Statistics stats) { } } - public void setGroupKeyObjectInspector(ObjectInspector keyObjectInspector) { - this.groupKeyOI = keyObjectInspector; - } - - public ObjectInspector getGroupKeyObjectInspector() { - return groupKeyOI; - } - public static Operator createDummy() { return new DummyOperator(); } diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/ReduceSinkOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/ReduceSinkOperator.java index 9bbc4ec..d8698da 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/ReduceSinkOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/ReduceSinkOperator.java @@ -50,7 +50,6 @@ import org.apache.hadoop.hive.serde2.objectinspector.primitive.IntObjectInspector; import org.apache.hadoop.io.BinaryComparable; import org.apache.hadoop.io.BytesWritable; -import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Writable; import org.apache.hadoop.mapred.OutputCollector; @@ -67,6 +66,9 @@ } private static final Log LOG = LogFactory.getLog(ReduceSinkOperator.class.getName()); + private static final boolean isInfoEnabled = LOG.isInfoEnabled(); + private static final boolean isDebugEnabled = LOG.isDebugEnabled(); + private static final boolean isTraceEnabled = LOG.isTraceEnabled(); private static final long serialVersionUID = 1L; private static final MurmurHash hash = (MurmurHash) MurmurHash.getInstance(); @@ -117,6 +119,8 @@ protected transient Object[] cachedValues; protected transient List> distinctColIndices; protected transient Random random; + protected transient int bucketNumber; + /** * This two dimensional array holds key data and a corresponding Union object * which contains the tag identifying the aggregate expression for distinct columns. @@ -144,8 +148,14 @@ protected void initializeOp(Configuration hconf) throws HiveException { try { List keys = conf.getKeyCols(); - LOG.debug("keys size is " + keys.size()); - for (ExprNodeDesc k : keys) LOG.debug("Key exprNodeDesc " + k.getExprString()); + + if (isDebugEnabled) { + LOG.debug("keys size is " + keys.size()); + for (ExprNodeDesc k : keys) { + LOG.debug("Key exprNodeDesc " + k.getExprString()); + } + } + keyEval = new ExprNodeEvaluator[keys.size()]; int i = 0; for (ExprNodeDesc e : keys) { @@ -184,7 +194,9 @@ protected void initializeOp(Configuration hconf) throws HiveException { tag = conf.getTag(); tagByte[0] = (byte) tag; skipTag = conf.getSkipTag(); - LOG.info("Using tag = " + tag); + if (isInfoEnabled) { + LOG.info("Using tag = " + tag); + } TableDesc keyTableDesc = conf.getKeySerializeInfo(); keySerializer = (Serializer) keyTableDesc.getDeserializerClass() @@ -284,7 +296,10 @@ public void processOp(Object row, int tag) throws HiveException { bucketInspector = (IntObjectInspector)bucketField.getFieldObjectInspector(); } - LOG.info("keys are " + conf.getOutputKeyColumnNames() + " num distributions: " + conf.getNumDistributionKeys()); + if (isInfoEnabled) { + LOG.info("keys are " + conf.getOutputKeyColumnNames() + " num distributions: " + + conf.getNumDistributionKeys()); + } keyObjectInspector = initEvaluatorsAndReturnStruct(keyEval, distinctColIndices, conf.getOutputKeyColumnNames(), numDistributionKeys, rowInspector); @@ -304,15 +319,14 @@ public void processOp(Object row, int tag) throws HiveException { populateCachedDistributionKeys(row, 0); // replace bucketing columns with hashcode % numBuckets - int buckNum = -1; if (bucketEval != null) { - buckNum = computeBucketNumber(row, conf.getNumBuckets()); - cachedKeys[0][buckColIdxInKey] = new IntWritable(buckNum); + bucketNumber = computeBucketNumber(row, conf.getNumBuckets()); + cachedKeys[0][buckColIdxInKey] = new Text(String.valueOf(bucketNumber)); } else if (conf.getWriteType() == AcidUtils.Operation.UPDATE || conf.getWriteType() == AcidUtils.Operation.DELETE) { // In the non-partitioned case we still want to compute the bucket number for updates and // deletes. - buckNum = computeBucketNumber(row, conf.getNumBuckets()); + bucketNumber = computeBucketNumber(row, conf.getNumBuckets()); } HiveKey firstKey = toHiveKey(cachedKeys[0], tag, null); @@ -328,7 +342,7 @@ public void processOp(Object row, int tag) throws HiveException { if (autoParallel && partitionEval.length > 0) { hashCode = computeMurmurHash(firstKey); } else { - hashCode = computeHashCode(row, buckNum); + hashCode = computeHashCode(row); } firstKey.setHashCode(hashCode); @@ -377,7 +391,9 @@ private int computeBucketNumber(Object row, int numBuckets) throws HiveException // column directly. Object recIdValue = acidRowInspector.getStructFieldData(row, recIdField); buckNum = bucketInspector.get(recIdInspector.getStructFieldData(recIdValue, bucketField)); - LOG.debug("Acid choosing bucket number " + buckNum); + if (isTraceEnabled) { + LOG.trace("Acid choosing bucket number " + buckNum); + } } else { for (int i = 0; i < bucketEval.length; i++) { Object o = bucketEval[i].evaluate(row); @@ -422,7 +438,7 @@ protected final int computeMurmurHash(HiveKey firstKey) { return hash.hash(firstKey.getBytes(), firstKey.getDistKeyLength(), 0); } - private int computeHashCode(Object row, int buckNum) throws HiveException { + private int computeHashCode(Object row) throws HiveException { // Evaluate the HashCode int keyHashCode = 0; if (partitionEval.length == 0) { @@ -446,8 +462,10 @@ private int computeHashCode(Object row, int buckNum) throws HiveException { + ObjectInspectorUtils.hashCode(o, partitionObjectInspectors[i]); } } - LOG.debug("Going to return hash code " + (keyHashCode * 31 + buckNum)); - return buckNum < 0 ? keyHashCode : keyHashCode * 31 + buckNum; + if (isTraceEnabled) { + LOG.trace("Going to return hash code " + (keyHashCode * 31 + bucketNumber)); + } + return bucketNumber < 0 ? keyHashCode : keyHashCode * 31 + bucketNumber; } private boolean partitionKeysAreNull(Object row) throws HiveException { @@ -493,10 +511,19 @@ protected void collect(BytesWritable keyWritable, Writable valueWritable) throws } private BytesWritable makeValueWritable(Object row) throws Exception { + int length = valueEval.length; + + // in case of bucketed table, insert the bucket number as the last column in value + if (bucketEval != null) { + length -= 1; + cachedValues[length] = new Text(String.valueOf(bucketNumber)); + } + // Evaluate the value - for (int i = 0; i < valueEval.length; i++) { + for (int i = 0; i < length; i++) { cachedValues[i] = valueEval[i].evaluate(row); } + // Serialize the value return (BytesWritable) valueSerializer.serialize(cachedValues, valueObjectInspector); } diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/mr/ExecReducer.java ql/src/java/org/apache/hadoop/hive/ql/exec/mr/ExecReducer.java index c9e469c..9cd8b56 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/mr/ExecReducer.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/mr/ExecReducer.java @@ -66,6 +66,8 @@ public class ExecReducer extends MapReduceBase implements Reducer { private static final Log LOG = LogFactory.getLog("ExecReducer"); + private static final boolean isInfoEnabled = LOG.isInfoEnabled(); + private static final boolean isTraceEnabled = LOG.isTraceEnabled(); private static final String PLAN_KEY = "__REDUCE_PLAN__"; // used to log memory usage periodically @@ -75,7 +77,6 @@ private final Deserializer[] inputValueDeserializer = new Deserializer[Byte.MAX_VALUE]; private final Object[] valueObject = new Object[Byte.MAX_VALUE]; private final List row = new ArrayList(Utilities.reduceFieldNameList.size()); - private final boolean isLogInfoEnabled = LOG.isInfoEnabled(); // TODO: move to DynamicSerDe when it's ready private Deserializer inputKeyDeserializer; @@ -101,16 +102,18 @@ public void configure(JobConf job) { ObjectInspector[] valueObjectInspector = new ObjectInspector[Byte.MAX_VALUE]; ObjectInspector keyObjectInspector; - LOG.info("maximum memory = " + memoryMXBean.getHeapMemoryUsage().getMax()); + if (isInfoEnabled) { + LOG.info("maximum memory = " + memoryMXBean.getHeapMemoryUsage().getMax()); - try { - LOG.info("conf classpath = " - + Arrays.asList(((URLClassLoader) job.getClassLoader()).getURLs())); - LOG.info("thread classpath = " - + Arrays.asList(((URLClassLoader) Thread.currentThread() - .getContextClassLoader()).getURLs())); - } catch (Exception e) { - LOG.info("cannot get classpath: " + e.getMessage()); + try { + LOG.info("conf classpath = " + + Arrays.asList(((URLClassLoader) job.getClassLoader()).getURLs())); + LOG.info("thread classpath = " + + Arrays.asList(((URLClassLoader) Thread.currentThread() + .getContextClassLoader()).getURLs())); + } catch (Exception e) { + LOG.info("cannot get classpath: " + e.getMessage()); + } } jc = job; @@ -147,7 +150,6 @@ public void configure(JobConf job) { ArrayList ois = new ArrayList(); ois.add(keyObjectInspector); ois.add(valueObjectInspector[tag]); - reducer.setGroupKeyObjectInspector(keyObjectInspector); rowObjectInspector[tag] = ObjectInspectorFactory .getStandardStructObjectInspector(Utilities.reduceFieldNameList, ois); } @@ -202,7 +204,9 @@ public void reduce(Object key, Iterator values, OutputCollector output, groupKey = new BytesWritable(); } else { // If a operator wants to do some work at the end of a group - LOG.trace("End Group"); + if (isTraceEnabled) { + LOG.trace("End Group"); + } reducer.endGroup(); } @@ -217,9 +221,11 @@ public void reduce(Object key, Iterator values, OutputCollector output, } groupKey.set(keyWritable.get(), 0, keyWritable.getSize()); - LOG.trace("Start Group"); - reducer.setGroupKeyObject(keyObject); + if (isTraceEnabled) { + LOG.trace("Start Group"); + } reducer.startGroup(); + reducer.setGroupKeyObject(keyObject); } // System.err.print(keyObject.toString()); while (values.hasNext()) { @@ -239,12 +245,14 @@ public void reduce(Object key, Iterator values, OutputCollector output, row.clear(); row.add(keyObject); row.add(valueObject[tag]); - if (isLogInfoEnabled) { + if (isInfoEnabled) { cntr++; if (cntr == nextCntr) { long used_memory = memoryMXBean.getHeapMemoryUsage().getUsed(); - LOG.info("ExecReducer: processing " + cntr - + " rows: used memory = " + used_memory); + if (isInfoEnabled) { + LOG.info("ExecReducer: processing " + cntr + + " rows: used memory = " + used_memory); + } nextCntr = getNextCntr(cntr); } } @@ -290,17 +298,19 @@ private long getNextCntr(long cntr) { public void close() { // No row was processed - if (oc == null) { + if (oc == null && isTraceEnabled) { LOG.trace("Close called without any rows processed"); } try { if (groupKey != null) { // If a operator wants to do some work at the end of a group - LOG.trace("End Group"); + if (isTraceEnabled) { + LOG.trace("End Group"); + } reducer.endGroup(); } - if (isLogInfoEnabled) { + if (isInfoEnabled) { LOG.info("ExecReducer: processed " + cntr + " rows: used memory = " + memoryMXBean.getHeapMemoryUsage().getUsed()); } diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ReduceRecordSource.java ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ReduceRecordSource.java index 8a54433..72e2fe5 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ReduceRecordSource.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ReduceRecordSource.java @@ -131,7 +131,6 @@ void init(JobConf jconf, Operator reducer, boolean vectorized, TableDesc keyT .getDeserializerClass(), null); SerDeUtils.initializeSerDe(inputKeyDeserializer, null, keyTableDesc.getProperties(), null); keyObjectInspector = inputKeyDeserializer.getObjectInspector(); - reducer.setGroupKeyObjectInspector(keyObjectInspector); if(vectorized) { keyStructInspector = (StructObjectInspector) keyObjectInspector; @@ -240,8 +239,8 @@ public boolean pushRecord() throws HiveException { } groupKey.set(keyWritable.getBytes(), 0, keyWritable.getLength()); - reducer.setGroupKeyObject(keyObject); reducer.startGroup(); + reducer.setGroupKeyObject(keyObject); } /* this.keyObject passed via reference */ diff --git ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorReduceSinkOperator.java ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorReduceSinkOperator.java index c096414..6c9d8e1 100644 --- ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorReduceSinkOperator.java +++ ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorReduceSinkOperator.java @@ -41,7 +41,6 @@ import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils; import org.apache.hadoop.hive.serde2.objectinspector.StandardUnionObjectInspector.StandardUnion; import org.apache.hadoop.io.BytesWritable; -import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; // import org.apache.hadoop.util.StringUtils; @@ -270,10 +269,9 @@ public void processOp(Object row, int tag) throws HiveException { populatedCachedDistributionKeys(vrg, rowIndex, 0); // replace bucketing columns with hashcode % numBuckets - int buckNum = -1; if (bucketEval != null) { - buckNum = computeBucketNumber(vrg, rowIndex, conf.getNumBuckets()); - cachedKeys[0][buckColIdxInKey] = new IntWritable(buckNum); + bucketNumber = computeBucketNumber(vrg, rowIndex, conf.getNumBuckets()); + cachedKeys[0][buckColIdxInKey] = new Text(String.valueOf(bucketNumber)); } HiveKey firstKey = toHiveKey(cachedKeys[0], tag, null); int distKeyLength = firstKey.getDistKeyLength(); @@ -289,7 +287,7 @@ public void processOp(Object row, int tag) throws HiveException { if (autoParallel && partitionEval.length > 0) { hashCode = computeMurmurHash(firstKey); } else { - hashCode = computeHashCode(vrg, rowIndex, buckNum); + hashCode = computeHashCode(vrg, rowIndex); } firstKey.setHashCode(hashCode); @@ -417,7 +415,15 @@ private void populateCachedDistinctKeys( private BytesWritable makeValueWritable(VectorizedRowBatch vrg, int rowIndex) throws HiveException, SerDeException { - for (int i = 0; i < valueEval.length; i++) { + int length = valueEval.length; + + // in case of bucketed table, insert the bucket number as the last column in value + if (bucketEval != null) { + length -= 1; + cachedValues[length] = new Text(String.valueOf(bucketNumber)); + } + + for (int i = 0; i < length; i++) { int batchColumn = valueEval[i].getOutputColumn(); ColumnVector vectorColumn = vrg.cols[batchColumn]; cachedValues[i] = valueWriters[i].writeValue(vectorColumn, rowIndex); @@ -426,7 +432,7 @@ private BytesWritable makeValueWritable(VectorizedRowBatch vrg, int rowIndex) return (BytesWritable)valueSerializer.serialize(cachedValues, valueObjectInspector); } - private int computeHashCode(VectorizedRowBatch vrg, int rowIndex, int buckNum) throws HiveException { + private int computeHashCode(VectorizedRowBatch vrg, int rowIndex) throws HiveException { // Evaluate the HashCode int keyHashCode = 0; if (partitionEval.length == 0) { @@ -449,7 +455,7 @@ private int computeHashCode(VectorizedRowBatch vrg, int rowIndex, int buckNum) t partitionWriters[p].getObjectInspector()); } } - return buckNum < 0 ? keyHashCode : keyHashCode * 31 + buckNum; + return bucketNumber < 0 ? keyHashCode : keyHashCode * 31 + bucketNumber; } private boolean partitionKeysAreNull(VectorizedRowBatch vrg, int rowIndex) diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java index e3313e9..d79879c 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java @@ -71,7 +71,6 @@ import org.apache.hadoop.hive.ql.plan.ReduceSinkDesc; import org.apache.hadoop.hive.ql.plan.TableDesc; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; -import org.apache.hadoop.io.IntWritable; import com.google.common.collect.Lists; import com.google.common.collect.Maps; @@ -85,6 +84,7 @@ */ public class SortedDynPartitionOptimizer implements Transform { + private static final String BUCKET_NUMBER_COL_NAME = "_bucket_number"; @Override public ParseContext transform(ParseContext pCtx) throws SemanticException { @@ -216,6 +216,13 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, ReduceSinkDesc rsConf = getReduceSinkDesc(partitionPositions, sortPositions, sortOrder, newValueCols, bucketColumns, numBuckets, fsParent, fsOp.getConf().getWriteType()); + if (!bucketColumns.isEmpty()) { + String tableAlias = outRR.getColumnInfos().get(0).getTabAlias(); + ColumnInfo ci = new ColumnInfo(BUCKET_NUMBER_COL_NAME, TypeInfoFactory.stringTypeInfo, + tableAlias, true, true); + outRR.put(tableAlias, BUCKET_NUMBER_COL_NAME, ci); + } + // Create ReduceSink operator ReduceSinkOperator rsOp = (ReduceSinkOperator) putOpInsertMap( OperatorFactory.getAndMakeChild(rsConf, new RowSchema(outRR.getColumnInfos()), fsParent), @@ -380,8 +387,11 @@ public ReduceSinkDesc getReduceSinkDesc(List partitionPositions, // corresponding with bucket number and hence their OIs for (Integer idx : keyColsPosInVal) { if (idx < 0) { - newKeyCols.add(new ExprNodeConstantDesc(TypeInfoFactory - .getPrimitiveTypeInfoFromPrimitiveWritable(IntWritable.class), -1)); + // add bucket number column to both key and value + ExprNodeConstantDesc encd = new ExprNodeConstantDesc(TypeInfoFactory.stringTypeInfo, + BUCKET_NUMBER_COL_NAME); + newKeyCols.add(encd); + newValueCols.add(encd); } else { newKeyCols.add(newValueCols.get(idx).clone()); } @@ -418,6 +428,9 @@ public ReduceSinkDesc getReduceSinkDesc(List partitionPositions, List outCols = Utilities.getInternalColumnNamesFromSignature(parent.getSchema() .getSignature()); ArrayList outValColNames = Lists.newArrayList(outCols); + if (!bucketColumns.isEmpty()) { + outValColNames.add(BUCKET_NUMBER_COL_NAME); + } List valFields = PlanUtils.getFieldSchemasFromColumnList(newValueCols, outValColNames, 0, ""); TableDesc valueTable = PlanUtils.getReduceValueTableDesc(valFields); diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index cdfbeb1..ac77041 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -6457,6 +6457,7 @@ Operator genConversionSelectOperator(String dest, QB qb, Operator input, int columnNumber = tableFields.size(); ArrayList expressions = new ArrayList( columnNumber); + // MetadataTypedColumnsetSerDe does not need type conversions because it // does the conversion to String by itself. boolean isMetaDataSerDe = table_desc.getDeserializerClass().equals( @@ -6524,17 +6525,19 @@ Operator genConversionSelectOperator(String dest, QB qb, Operator input, if (converted) { // add the select operator RowResolver rowResolver = new RowResolver(); - ArrayList colName = new ArrayList(); + ArrayList colNames = new ArrayList(); + Map colExprMap = new HashMap(); for (int i = 0; i < expressions.size(); i++) { String name = getColumnInternalName(i); rowResolver.put("", name, new ColumnInfo(name, expressions.get(i) .getTypeInfo(), "", false)); - colName.add(name); + colNames.add(name); + colExprMap.put(name, expressions.get(i)); } Operator output = putOpInsertMap(OperatorFactory.getAndMakeChild( - new SelectDesc(expressions, colName), new RowSchema(rowResolver + new SelectDesc(expressions, colNames), new RowSchema(rowResolver .getColumnInfos()), input), rowResolver); - + output.setColumnExprMap(colExprMap); return output; } else { // not converted diff --git ql/src/test/queries/clientpositive/alter_partition_change_col.q ql/src/test/queries/clientpositive/alter_partition_change_col.q index 64aafd1..baabb9f 100644 --- ql/src/test/queries/clientpositive/alter_partition_change_col.q +++ ql/src/test/queries/clientpositive/alter_partition_change_col.q @@ -1,6 +1,8 @@ SET hive.exec.dynamic.partition = true; SET hive.exec.dynamic.partition.mode = nonstrict; +-- SORT_QUERY_RESULTS + create table alter_partition_change_col0 (c1 string, c2 string); load data local inpath '../../data/files/dec.txt' overwrite into table alter_partition_change_col0; diff --git ql/src/test/queries/clientpositive/dynpart_sort_optimization2.q ql/src/test/queries/clientpositive/dynpart_sort_optimization2.q new file mode 100644 index 0000000..70c795d --- /dev/null +++ ql/src/test/queries/clientpositive/dynpart_sort_optimization2.q @@ -0,0 +1,246 @@ +set hive.optimize.sort.dynamic.partition=true; +set hive.exec.dynamic.partition=true; +set hive.exec.max.dynamic.partitions=1000; +set hive.exec.max.dynamic.partitions.pernode=1000; +set hive.exec.dynamic.partition.mode=nonstrict; +set hive.enforce.bucketing=false; +set hive.enforce.sorting=false; +set hive.exec.submitviachild=true; +set hive.exec.submit.local.task.via.child=true; + +drop table ss; +drop table ss_orc; +drop table ss_part; +drop table ss_part_orc; + +create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float); + +create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int); + +load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss; + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +set hive.optimize.sort.dynamic.partition=false; +-- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +desc formatted ss_part partition(ss_sold_date_sk=2452617); +select * from ss_part where ss_sold_date_sk=2452617; + +desc formatted ss_part partition(ss_sold_date_sk=2452638); +select * from ss_part where ss_sold_date_sk=2452638; + +set hive.vectorized.execution.enabled=true; +-- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc; + +create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc; + +insert overwrite table ss_orc select * from ss; + +drop table ss; +drop table ss_part; + +explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452617); +select * from ss_part_orc where ss_sold_date_sk=2452617; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452638); +select * from ss_part_orc where ss_sold_date_sk=2452638; + +explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452617); +select * from ss_part_orc where ss_sold_date_sk=2452617; + +desc formatted ss_part_orc partition(ss_sold_date_sk=2452638); +select * from ss_part_orc where ss_sold_date_sk=2452638; + +drop table ss_orc; +drop table ss_part_orc; + +drop table if exists hive13_dp1; +create table if not exists hive13_dp1 ( + k1 int, + k2 int +) +PARTITIONED BY(`day` string) +STORED AS ORC; + +set hive.optimize.sort.dynamic.partition=false; +explain insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key; + +insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key; +select * from hive13_dp1 limit 5; + +set hive.optimize.sort.dynamic.partition=true; +explain insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key; + +insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key; +select * from hive13_dp1 limit 5; + +drop table hive13_dp1; diff --git ql/src/test/results/clientpositive/alter_partition_change_col.q.out ql/src/test/results/clientpositive/alter_partition_change_col.q.out index e48464c..7123e40 100644 --- ql/src/test/results/clientpositive/alter_partition_change_col.q.out +++ ql/src/test/results/clientpositive/alter_partition_change_col.q.out @@ -1,8 +1,12 @@ -PREHOOK: query: create table alter_partition_change_col0 (c1 string, c2 string) +PREHOOK: query: -- SORT_QUERY_RESULTS + +create table alter_partition_change_col0 (c1 string, c2 string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@alter_partition_change_col0 -POSTHOOK: query: create table alter_partition_change_col0 (c1 string, c2 string) +POSTHOOK: query: -- SORT_QUERY_RESULTS + +create table alter_partition_change_col0 (c1 string, c2 string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@alter_partition_change_col0 @@ -61,26 +65,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 234.79 __HIVE_DEFAULT_PARTITION__ -Cluck 5.96 __HIVE_DEFAULT_PARTITION__ -Tom 19.00 __HIVE_DEFAULT_PARTITION__ -Mary 4.329 __HIVE_DEFAULT_PARTITION__ Beck 0.0 __HIVE_DEFAULT_PARTITION__ -Snow 55.71 __HIVE_DEFAULT_PARTITION__ -Mary 33.33 __HIVE_DEFAULT_PARTITION__ +Beck 0.0 abc Beck 77.341 __HIVE_DEFAULT_PARTITION__ +Beck 77.341 abc Beck 79.9 __HIVE_DEFAULT_PARTITION__ -Tom -12.25 __HIVE_DEFAULT_PARTITION__ Beck 79.9 abc -Beck 0.0 abc -Tom 19.00 abc +Cluck 5.96 __HIVE_DEFAULT_PARTITION__ +Cluck 5.96 abc +Mary 33.33 __HIVE_DEFAULT_PARTITION__ Mary 33.33 abc -Tom -12.25 abc +Mary 4.329 __HIVE_DEFAULT_PARTITION__ Mary 4.329 abc +Snow 55.71 __HIVE_DEFAULT_PARTITION__ Snow 55.71 abc -Beck 77.341 abc +Tom -12.25 __HIVE_DEFAULT_PARTITION__ +Tom -12.25 abc +Tom 19.00 __HIVE_DEFAULT_PARTITION__ +Tom 19.00 abc +Tom 234.79 __HIVE_DEFAULT_PARTITION__ Tom 234.79 abc -Cluck 5.96 abc PREHOOK: query: -- Change c2 to decimal(10,0) alter table alter_partition_change_col1 change c2 c2 decimal(10,0) PREHOOK: type: ALTERTABLE_RENAMECOL @@ -121,26 +125,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 235 __HIVE_DEFAULT_PARTITION__ -Cluck 6 __HIVE_DEFAULT_PARTITION__ -Tom 19 __HIVE_DEFAULT_PARTITION__ -Mary 4 __HIVE_DEFAULT_PARTITION__ Beck 0 __HIVE_DEFAULT_PARTITION__ -Snow 56 __HIVE_DEFAULT_PARTITION__ -Mary 33 __HIVE_DEFAULT_PARTITION__ +Beck 0 abc Beck 77 __HIVE_DEFAULT_PARTITION__ +Beck 77 abc Beck 80 __HIVE_DEFAULT_PARTITION__ -Tom -12 __HIVE_DEFAULT_PARTITION__ Beck 80 abc -Beck 0 abc -Tom 19 abc +Cluck 6 __HIVE_DEFAULT_PARTITION__ +Cluck 6 abc +Mary 33 __HIVE_DEFAULT_PARTITION__ Mary 33 abc -Tom -12 abc +Mary 4 __HIVE_DEFAULT_PARTITION__ Mary 4 abc +Snow 56 __HIVE_DEFAULT_PARTITION__ Snow 56 abc -Beck 77 abc +Tom -12 __HIVE_DEFAULT_PARTITION__ +Tom -12 abc +Tom 19 __HIVE_DEFAULT_PARTITION__ +Tom 19 abc +Tom 235 __HIVE_DEFAULT_PARTITION__ Tom 235 abc -Cluck 6 abc PREHOOK: query: -- Change the column type at the table level. Table-level describe shows the new type, but the existing partition does not. alter table alter_partition_change_col1 change c2 c2 decimal(14,4) PREHOOK: type: ALTERTABLE_RENAMECOL @@ -191,26 +195,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 235 __HIVE_DEFAULT_PARTITION__ -Cluck 6 __HIVE_DEFAULT_PARTITION__ -Tom 19 __HIVE_DEFAULT_PARTITION__ -Mary 4 __HIVE_DEFAULT_PARTITION__ Beck 0 __HIVE_DEFAULT_PARTITION__ -Snow 56 __HIVE_DEFAULT_PARTITION__ -Mary 33 __HIVE_DEFAULT_PARTITION__ +Beck 0 abc Beck 77 __HIVE_DEFAULT_PARTITION__ +Beck 77 abc Beck 80 __HIVE_DEFAULT_PARTITION__ -Tom -12 __HIVE_DEFAULT_PARTITION__ Beck 80 abc -Beck 0 abc -Tom 19 abc +Cluck 6 __HIVE_DEFAULT_PARTITION__ +Cluck 6 abc +Mary 33 __HIVE_DEFAULT_PARTITION__ Mary 33 abc -Tom -12 abc +Mary 4 __HIVE_DEFAULT_PARTITION__ Mary 4 abc +Snow 56 __HIVE_DEFAULT_PARTITION__ Snow 56 abc -Beck 77 abc +Tom -12 __HIVE_DEFAULT_PARTITION__ +Tom -12 abc +Tom 19 __HIVE_DEFAULT_PARTITION__ +Tom 19 abc +Tom 235 __HIVE_DEFAULT_PARTITION__ Tom 235 abc -Cluck 6 abc PREHOOK: query: -- now change the column type of the existing partition alter table alter_partition_change_col1 partition (p1='abc') change c2 c2 decimal(14,4) PREHOOK: type: ALTERTABLE_RENAMECOL @@ -248,26 +252,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 235 __HIVE_DEFAULT_PARTITION__ -Cluck 6 __HIVE_DEFAULT_PARTITION__ -Tom 19 __HIVE_DEFAULT_PARTITION__ -Mary 4 __HIVE_DEFAULT_PARTITION__ Beck 0 __HIVE_DEFAULT_PARTITION__ -Snow 56 __HIVE_DEFAULT_PARTITION__ -Mary 33 __HIVE_DEFAULT_PARTITION__ +Beck 0.0 abc Beck 77 __HIVE_DEFAULT_PARTITION__ -Beck 80 __HIVE_DEFAULT_PARTITION__ -Tom -12 __HIVE_DEFAULT_PARTITION__ +Beck 77.341 abc Beck 79.9 abc -Beck 0.0 abc -Tom 19.00 abc +Beck 80 __HIVE_DEFAULT_PARTITION__ +Cluck 5.96 abc +Cluck 6 __HIVE_DEFAULT_PARTITION__ +Mary 33 __HIVE_DEFAULT_PARTITION__ Mary 33.33 abc -Tom -12.25 abc +Mary 4 __HIVE_DEFAULT_PARTITION__ Mary 4.329 abc Snow 55.71 abc -Beck 77.341 abc +Snow 56 __HIVE_DEFAULT_PARTITION__ +Tom -12 __HIVE_DEFAULT_PARTITION__ +Tom -12.25 abc +Tom 19 __HIVE_DEFAULT_PARTITION__ +Tom 19.00 abc Tom 234.79 abc -Cluck 5.96 abc +Tom 235 __HIVE_DEFAULT_PARTITION__ PREHOOK: query: -- change column for default partition value alter table alter_partition_change_col1 partition (p1='__HIVE_DEFAULT_PARTITION__') change c2 c2 decimal(14,4) PREHOOK: type: ALTERTABLE_RENAMECOL @@ -305,26 +309,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 234.79 __HIVE_DEFAULT_PARTITION__ -Cluck 5.96 __HIVE_DEFAULT_PARTITION__ -Tom 19.00 __HIVE_DEFAULT_PARTITION__ -Mary 4.329 __HIVE_DEFAULT_PARTITION__ Beck 0.0 __HIVE_DEFAULT_PARTITION__ -Snow 55.71 __HIVE_DEFAULT_PARTITION__ -Mary 33.33 __HIVE_DEFAULT_PARTITION__ +Beck 0.0 abc Beck 77.341 __HIVE_DEFAULT_PARTITION__ +Beck 77.341 abc Beck 79.9 __HIVE_DEFAULT_PARTITION__ -Tom -12.25 __HIVE_DEFAULT_PARTITION__ Beck 79.9 abc -Beck 0.0 abc -Tom 19.00 abc +Cluck 5.96 __HIVE_DEFAULT_PARTITION__ +Cluck 5.96 abc +Mary 33.33 __HIVE_DEFAULT_PARTITION__ Mary 33.33 abc -Tom -12.25 abc +Mary 4.329 __HIVE_DEFAULT_PARTITION__ Mary 4.329 abc +Snow 55.71 __HIVE_DEFAULT_PARTITION__ Snow 55.71 abc -Beck 77.341 abc +Tom -12.25 __HIVE_DEFAULT_PARTITION__ +Tom -12.25 abc +Tom 19.00 __HIVE_DEFAULT_PARTITION__ +Tom 19.00 abc +Tom 234.79 __HIVE_DEFAULT_PARTITION__ Tom 234.79 abc -Cluck 5.96 abc PREHOOK: query: -- Try out replace columns alter table alter_partition_change_col1 partition (p1='abc') replace columns (c1 string) PREHOOK: type: ALTERTABLE_REPLACECOLS @@ -375,26 +379,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 234.79 __HIVE_DEFAULT_PARTITION__ -Cluck 5.96 __HIVE_DEFAULT_PARTITION__ -Tom 19.00 __HIVE_DEFAULT_PARTITION__ -Mary 4.329 __HIVE_DEFAULT_PARTITION__ Beck 0.0 __HIVE_DEFAULT_PARTITION__ -Snow 55.71 __HIVE_DEFAULT_PARTITION__ -Mary 33.33 __HIVE_DEFAULT_PARTITION__ Beck 77.341 __HIVE_DEFAULT_PARTITION__ Beck 79.9 __HIVE_DEFAULT_PARTITION__ -Tom -12.25 __HIVE_DEFAULT_PARTITION__ Beck NULL abc Beck NULL abc -Tom NULL abc +Beck NULL abc +Cluck 5.96 __HIVE_DEFAULT_PARTITION__ +Cluck NULL abc +Mary 33.33 __HIVE_DEFAULT_PARTITION__ +Mary 4.329 __HIVE_DEFAULT_PARTITION__ Mary NULL abc -Tom NULL abc Mary NULL abc +Snow 55.71 __HIVE_DEFAULT_PARTITION__ Snow NULL abc -Beck NULL abc +Tom -12.25 __HIVE_DEFAULT_PARTITION__ +Tom 19.00 __HIVE_DEFAULT_PARTITION__ +Tom 234.79 __HIVE_DEFAULT_PARTITION__ +Tom NULL abc +Tom NULL abc Tom NULL abc -Cluck NULL abc PREHOOK: query: alter table alter_partition_change_col1 replace columns (c1 string) PREHOOK: type: ALTERTABLE_REPLACECOLS PREHOOK: Input: default@alter_partition_change_col1 @@ -428,26 +432,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom __HIVE_DEFAULT_PARTITION__ -Cluck __HIVE_DEFAULT_PARTITION__ -Tom __HIVE_DEFAULT_PARTITION__ -Mary __HIVE_DEFAULT_PARTITION__ Beck __HIVE_DEFAULT_PARTITION__ -Snow __HIVE_DEFAULT_PARTITION__ -Mary __HIVE_DEFAULT_PARTITION__ Beck __HIVE_DEFAULT_PARTITION__ Beck __HIVE_DEFAULT_PARTITION__ -Tom __HIVE_DEFAULT_PARTITION__ Beck abc Beck abc -Tom abc +Beck abc +Cluck __HIVE_DEFAULT_PARTITION__ +Cluck abc +Mary __HIVE_DEFAULT_PARTITION__ +Mary __HIVE_DEFAULT_PARTITION__ Mary abc -Tom abc Mary abc +Snow __HIVE_DEFAULT_PARTITION__ Snow abc -Beck abc +Tom __HIVE_DEFAULT_PARTITION__ +Tom __HIVE_DEFAULT_PARTITION__ +Tom __HIVE_DEFAULT_PARTITION__ +Tom abc +Tom abc Tom abc -Cluck abc PREHOOK: query: -- Try add columns alter table alter_partition_change_col1 add columns (c2 decimal(14,4)) PREHOOK: type: ALTERTABLE_ADDCOLS @@ -497,26 +501,26 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 234.79 __HIVE_DEFAULT_PARTITION__ -Cluck 5.96 __HIVE_DEFAULT_PARTITION__ -Tom 19.00 __HIVE_DEFAULT_PARTITION__ -Mary 4.329 __HIVE_DEFAULT_PARTITION__ Beck 0.0 __HIVE_DEFAULT_PARTITION__ -Snow 55.71 __HIVE_DEFAULT_PARTITION__ -Mary 33.33 __HIVE_DEFAULT_PARTITION__ Beck 77.341 __HIVE_DEFAULT_PARTITION__ Beck 79.9 __HIVE_DEFAULT_PARTITION__ -Tom -12.25 __HIVE_DEFAULT_PARTITION__ Beck NULL abc Beck NULL abc -Tom NULL abc +Beck NULL abc +Cluck 5.96 __HIVE_DEFAULT_PARTITION__ +Cluck NULL abc +Mary 33.33 __HIVE_DEFAULT_PARTITION__ +Mary 4.329 __HIVE_DEFAULT_PARTITION__ Mary NULL abc -Tom NULL abc Mary NULL abc +Snow 55.71 __HIVE_DEFAULT_PARTITION__ Snow NULL abc -Beck NULL abc +Tom -12.25 __HIVE_DEFAULT_PARTITION__ +Tom 19.00 __HIVE_DEFAULT_PARTITION__ +Tom 234.79 __HIVE_DEFAULT_PARTITION__ +Tom NULL abc +Tom NULL abc Tom NULL abc -Cluck NULL abc PREHOOK: query: alter table alter_partition_change_col1 partition (p1='abc') add columns (c2 decimal(14,4)) PREHOOK: type: ALTERTABLE_ADDCOLS PREHOOK: Input: default@alter_partition_change_col1 @@ -552,23 +556,23 @@ POSTHOOK: Input: default@alter_partition_change_col1 POSTHOOK: Input: default@alter_partition_change_col1@p1=__HIVE_DEFAULT_PARTITION__ POSTHOOK: Input: default@alter_partition_change_col1@p1=abc #### A masked pattern was here #### -Tom 234.79 __HIVE_DEFAULT_PARTITION__ -Cluck 5.96 __HIVE_DEFAULT_PARTITION__ -Tom 19.00 __HIVE_DEFAULT_PARTITION__ -Mary 4.329 __HIVE_DEFAULT_PARTITION__ Beck 0.0 __HIVE_DEFAULT_PARTITION__ -Snow 55.71 __HIVE_DEFAULT_PARTITION__ -Mary 33.33 __HIVE_DEFAULT_PARTITION__ +Beck 0.0 abc Beck 77.341 __HIVE_DEFAULT_PARTITION__ +Beck 77.341 abc Beck 79.9 __HIVE_DEFAULT_PARTITION__ -Tom -12.25 __HIVE_DEFAULT_PARTITION__ Beck 79.9 abc -Beck 0.0 abc -Tom 19.00 abc +Cluck 5.96 __HIVE_DEFAULT_PARTITION__ +Cluck 5.96 abc +Mary 33.33 __HIVE_DEFAULT_PARTITION__ Mary 33.33 abc -Tom -12.25 abc +Mary 4.329 __HIVE_DEFAULT_PARTITION__ Mary 4.329 abc +Snow 55.71 __HIVE_DEFAULT_PARTITION__ Snow 55.71 abc -Beck 77.341 abc +Tom -12.25 __HIVE_DEFAULT_PARTITION__ +Tom -12.25 abc +Tom 19.00 __HIVE_DEFAULT_PARTITION__ +Tom 19.00 abc +Tom 234.79 __HIVE_DEFAULT_PARTITION__ Tom 234.79 abc -Cluck 5.96 abc diff --git ql/src/test/results/clientpositive/annotate_stats_part.q.out ql/src/test/results/clientpositive/annotate_stats_part.q.out index d2e9ed1..b952fa6 100644 --- ql/src/test/results/clientpositive/annotate_stats_part.q.out +++ ql/src/test/results/clientpositive/annotate_stats_part.q.out @@ -98,11 +98,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 5 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- partition level analyze statistics for specific parition @@ -158,11 +158,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 9 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 9 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE @@ -181,11 +181,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 399 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 7 Data size: 400 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 7 Data size: 399 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 7 Data size: 400 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- partition level analyze statistics for all partitions @@ -245,11 +245,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE @@ -268,11 +268,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- both partitions will be pruned @@ -331,11 +331,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: zip (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL @@ -354,7 +354,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string) outputColumnNames: _col0 @@ -377,7 +377,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: string) outputColumnNames: _col0 @@ -402,7 +402,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 @@ -425,7 +425,7 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 399 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int) outputColumnNames: _col0, _col1 @@ -471,11 +471,11 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 722 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 8 Data size: 723 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: -- This is to test filter expression evaluation on partition column @@ -496,7 +496,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 399 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -532,7 +532,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 399 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE @@ -568,7 +568,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: loc_orc - Statistics: Num rows: 7 Data size: 399 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 0) (type: boolean) Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/auto_sortmerge_join_16.q.out ql/src/test/results/clientpositive/auto_sortmerge_join_16.q.out index 03507dd..b32ac06 100644 --- ql/src/test/results/clientpositive/auto_sortmerge_join_16.q.out +++ ql/src/test/results/clientpositive/auto_sortmerge_join_16.q.out @@ -232,6 +232,16 @@ POSTHOOK: Input: default@bucket_small@pri=2 0 val_0 val_0 day1 1 0 val_0 val_0 day1 1 0 val_0 val_0 day1 1 +103 val_103 val_103 day1 1 +103 val_103 val_103 day1 1 +103 val_103 val_103 day1 1 +103 val_103 val_103 day1 1 +374 val_374 val_374 day1 1 +374 val_374 val_374 day1 1 +172 val_172 val_172 day1 1 +172 val_172 val_172 day1 1 +172 val_172 val_172 day1 1 +172 val_172 val_172 day1 1 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 @@ -240,13 +250,3 @@ POSTHOOK: Input: default@bucket_small@pri=2 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 -374 val_374 val_374 day1 1 -374 val_374 val_374 day1 1 -172 val_172 val_172 day1 1 -172 val_172 val_172 day1 1 -172 val_172 val_172 day1 1 -172 val_172 val_172 day1 1 -103 val_103 val_103 day1 1 -103 val_103 val_103 day1 1 -103 val_103 val_103 day1 1 -103 val_103 val_103 day1 1 diff --git ql/src/test/results/clientpositive/combine2.q.out ql/src/test/results/clientpositive/combine2.q.out index 9da953c..921dd90 100644 --- ql/src/test/results/clientpositive/combine2.q.out +++ ql/src/test/results/clientpositive/combine2.q.out @@ -263,7 +263,7 @@ STAGE PLANS: columns.types string #### A masked pattern was here #### name default.combine2 - numFiles 1 + numFiles 3 numRows 3 partition_columns value partition_columns.types string @@ -398,7 +398,7 @@ STAGE PLANS: columns.types string #### A masked pattern was here #### name default.combine2 - numFiles 1 + numFiles 3 numRows 3 partition_columns value partition_columns.types string diff --git ql/src/test/results/clientpositive/constprog_dp.q.out ql/src/test/results/clientpositive/constprog_dp.q.out index e876467..98af017 100644 --- ql/src/test/results/clientpositive/constprog_dp.q.out +++ ql/src/test/results/clientpositive/constprog_dp.q.out @@ -16,8 +16,13 @@ insert overwrite table dest partition (ds) select key, value, ds where ds='2008- POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -30,23 +35,23 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -63,6 +68,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: from srcpart insert overwrite table dest partition (ds) select key, value, ds where ds='2008-04-08' PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/delete_all_partitioned.q.out ql/src/test/results/clientpositive/delete_all_partitioned.q.out index 4486323..12efe78 100644 --- ql/src/test/results/clientpositive/delete_all_partitioned.q.out +++ ql/src/test/results/clientpositive/delete_all_partitioned.q.out @@ -84,3 +84,5 @@ POSTHOOK: Input: default@acid_dap POSTHOOK: Input: default@acid_dap@ds=today POSTHOOK: Input: default@acid_dap@ds=tomorrow #### A masked pattern was here #### +-1071480828 aw724t8c5558x2xneC624 today +-1072076362 2uLyD28144vklju213J1mr today diff --git ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out index f2c42ae..df8ad44 100644 --- ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out +++ ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out @@ -342,11 +342,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reduce Operator Tree: Extract @@ -399,11 +399,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reduce Operator Tree: Extract @@ -691,11 +691,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reduce Operator Tree: Extract @@ -748,11 +748,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reduce Operator Tree: Extract @@ -2063,11 +2063,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reduce Operator Tree: Extract diff --git ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out index 549169f..8794884 100644 --- ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out +++ ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out @@ -275,11 +275,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE @@ -331,11 +331,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE @@ -598,11 +598,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE @@ -654,11 +654,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE @@ -1962,11 +1962,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reduce Operator Tree: Extract Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out new file mode 100644 index 0000000..9b57bbb --- /dev/null +++ ql/src/test/results/clientpositive/dynpart_sort_optimization2.q.out @@ -0,0 +1,1782 @@ +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss +POSTHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss +PREHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part +POSTHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part +PREHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ss +POSTHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ss +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_orc +POSTHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_orc +PREHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part_orc +PREHOOK: query: insert overwrite table ss_orc select * from ss +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_orc +POSTHOOK: query: insert overwrite table ss_orc select * from ss +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_orc +POSTHOOK: Lineage: ss_orc.ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_sold_date_sk SIMPLE [(ss)ss.FieldSchema(name:ss_sold_date_sk, type:int, comment:null), ] +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part +PREHOOK: Output: default@ss_part +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part +POSTHOOK: Output: default@ss_part +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Execution mode: vectorized + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_orc +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_orc +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Output: default@ss_part_orc +PREHOOK: query: drop table if exists hive13_dp1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists hive13_dp1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table if not exists hive13_dp1 ( + k1 int, + k2 int +) +PARTITIONED BY(`day` string) +STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@hive13_dp1 +POSTHOOK: query: create table if not exists hive13_dp1 ( + k1 int, + k2 int +) +PARTITIONED BY(`day` string) +STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@hive13_dp1 +PREHOOK: query: explain insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(value) + keys: 'day' (type: string), key (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.hive13_dp1 + + Stage: Stage-0 + Move Operator + tables: + partition: + day + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.hive13_dp1 + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@hive13_dp1 +POSTHOOK: query: insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@hive13_dp1@day=day +POSTHOOK: Lineage: hive13_dp1 PARTITION(day=day).k1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: hive13_dp1 PARTITION(day=day).k2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from hive13_dp1 limit 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@hive13_dp1 +PREHOOK: Input: default@hive13_dp1@day=day +#### A masked pattern was here #### +POSTHOOK: query: select * from hive13_dp1 limit 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@hive13_dp1 +POSTHOOK: Input: default@hive13_dp1@day=day +#### A masked pattern was here #### +0 3 day +10 1 day +100 2 day +103 2 day +104 2 day +PREHOOK: query: explain insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(value) + keys: 'day' (type: string), key (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.hive13_dp1 + + Stage: Stage-0 + Move Operator + tables: + partition: + day + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.hive13_dp1 + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@hive13_dp1 +POSTHOOK: query: insert overwrite table `hive13_dp1` partition(`day`) +select + key k1, + count(value) k2, + "day" `day` +from src +group by "day", key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@hive13_dp1@day=day +POSTHOOK: Lineage: hive13_dp1 PARTITION(day=day).k1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: hive13_dp1 PARTITION(day=day).k2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from hive13_dp1 limit 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@hive13_dp1 +PREHOOK: Input: default@hive13_dp1@day=day +#### A masked pattern was here #### +POSTHOOK: query: select * from hive13_dp1 limit 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@hive13_dp1 +POSTHOOK: Input: default@hive13_dp1@day=day +#### A masked pattern was here #### +0 3 day +10 1 day +100 2 day +103 2 day +104 2 day +PREHOOK: query: drop table hive13_dp1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@hive13_dp1 +PREHOOK: Output: default@hive13_dp1 +POSTHOOK: query: drop table hive13_dp1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@hive13_dp1 +POSTHOOK: Output: default@hive13_dp1 diff --git ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out index 3789c09..db5c77c 100644 --- ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out +++ ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out @@ -239,7 +239,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 386 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -282,7 +282,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 390 + totalSize 388 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -458,7 +458,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 386 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -501,7 +501,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 390 + totalSize 388 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -690,7 +690,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 386 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -733,7 +733,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 390 + totalSize 388 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -905,7 +905,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 383 + totalSize 386 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde @@ -948,7 +948,7 @@ STAGE PLANS: serialization.ddl struct loc_orc_1d { string state, i32 locid, i32 zip} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde - totalSize 390 + totalSize 388 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde diff --git ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out index 2b1ec58..8f83ada 100644 --- ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out +++ ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out @@ -231,7 +231,7 @@ Partition Parameters: numFiles 1 numRows 0 rawDataSize 0 - totalSize 1381 + totalSize 1342 #### A masked pattern was here #### # Storage Information @@ -302,7 +302,7 @@ Partition Parameters: numFiles 1 numRows 0 rawDataSize 0 - totalSize 722 + totalSize 719 #### A masked pattern was here #### # Storage Information @@ -310,9 +310,9 @@ SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] +Num Buckets: 1 +Bucket Columns: [key] +Sort Columns: [Order(col:key, order:1)] Storage Desc Params: serialization.format 1 PREHOOK: query: DESCRIBE FORMATTED test_table PARTITION (ds='2008-04-08', hr='12') @@ -344,7 +344,7 @@ Partition Parameters: numFiles 1 numRows 0 rawDataSize 0 - totalSize 741 + totalSize 722 #### A masked pattern was here #### # Storage Information @@ -352,9 +352,9 @@ SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] +Num Buckets: 1 +Bucket Columns: [key] +Sort Columns: [Order(col:key, order:1)] Storage Desc Params: serialization.format 1 PREHOOK: query: CREATE TABLE srcpart_merge_dp LIKE srcpart @@ -468,14 +468,13 @@ GROUP BY key) a POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -513,37 +512,17 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.test_table + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.test_table - Stage: Stage-8 + Stage: Stage-7 Conditional Operator - Stage: Stage-5 + Stage: Stage-4 Move Operator files: hdfs directory: true @@ -562,24 +541,24 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.test_table - Stage: Stage-3 + Stage: Stage-2 Stats-Aggr Operator - Stage: Stage-4 + Stage: Stage-3 Merge File Operator Map Operator Tree: RCFile Merge Operator merge level: block input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - Stage: Stage-6 + Stage: Stage-5 Merge File Operator Map Operator Tree: RCFile Merge Operator merge level: block input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - Stage: Stage-7 + Stage: Stage-6 Move Operator files: hdfs directory: true @@ -639,7 +618,7 @@ Partition Parameters: numFiles 1 numRows 0 rawDataSize 0 - totalSize 94 + totalSize 115 #### A masked pattern was here #### # Storage Information @@ -678,10 +657,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 1 + numFiles 2 numRows 0 rawDataSize 0 - totalSize 1346 + totalSize 1427 #### A masked pattern was here #### # Storage Information diff --git ql/src/test/results/clientpositive/insert_into6.q.out ql/src/test/results/clientpositive/insert_into6.q.out index 53f8bac..388b200 100644 --- ql/src/test/results/clientpositive/insert_into6.q.out +++ ql/src/test/results/clientpositive/insert_into6.q.out @@ -132,8 +132,13 @@ POSTHOOK: query: EXPLAIN INSERT INTO TABLE insert_into6b PARTITION (ds) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -146,23 +151,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.insert_into6b + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into6b + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -179,6 +184,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into6b + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.insert_into6b + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT INTO TABLE insert_into6b PARTITION (ds) SELECT * FROM insert_into6a PREHOOK: type: QUERY PREHOOK: Input: default@insert_into6a diff --git ql/src/test/results/clientpositive/load_dyn_part1.q.out ql/src/test/results/clientpositive/load_dyn_part1.q.out index 4c9ee05..e7dace5 100644 --- ql/src/test/results/clientpositive/load_dyn_part1.q.out +++ ql/src/test/results/clientpositive/load_dyn_part1.q.out @@ -58,11 +58,20 @@ insert overwrite table nzhang_part2 partition(ds='2008-12-31', hr) select key, v POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 + Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 + Stage-14 depends on stages: Stage-2 , consists of Stage-11, Stage-10, Stage-12 + Stage-11 + Stage-1 depends on stages: Stage-11, Stage-10, Stage-13 + Stage-9 depends on stages: Stage-1 + Stage-10 + Stage-12 + Stage-13 depends on stages: Stage-12 STAGE PLANS: Stage: Stage-2 @@ -78,12 +87,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 Filter Operator predicate: (ds > '2008-04-08') (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE @@ -93,21 +104,21 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 666 Data size: 7075 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.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-5 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -129,23 +140,40 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 + + Stage: Stage-7 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-14 + Conditional Operator + + Stage: Stage-11 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-1 Move Operator @@ -160,9 +188,39 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part2 - Stage: Stage-5 + Stage: Stage-9 Stats-Aggr Operator + Stage: Stage-10 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + + Stage: Stage-12 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + + Stage: Stage-13 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: from srcpart insert overwrite table nzhang_part1 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table nzhang_part2 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08' diff --git ql/src/test/results/clientpositive/load_dyn_part10.q.out ql/src/test/results/clientpositive/load_dyn_part10.q.out index d05e4f1..ca388b9 100644 --- ql/src/test/results/clientpositive/load_dyn_part10.q.out +++ ql/src/test/results/clientpositive/load_dyn_part10.q.out @@ -62,23 +62,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part10 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part10 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/load_dyn_part14.q.out ql/src/test/results/clientpositive/load_dyn_part14.q.out index 37ae8de..118d198 100644 --- ql/src/test/results/clientpositive/load_dyn_part14.q.out +++ ql/src/test/results/clientpositive/load_dyn_part14.q.out @@ -55,11 +55,16 @@ select key, value from ( POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4, Stage-5 - Stage-0 depends on stages: Stage-2 + Stage-2 depends on stages: Stage-1, Stage-9, Stage-10 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 + Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 Stage-3 depends on stages: Stage-0 - Stage-4 is a root stage - Stage-5 is a root stage + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 + Stage-9 is a root stage + Stage-10 is a root stage STAGE PLANS: Stage: Stage-1 @@ -104,12 +109,14 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 TableScan Union Statistics: Num rows: 6 Data size: 1022 Basic stats: COMPLETE Column stats: COMPLETE @@ -117,12 +124,14 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 TableScan Union Statistics: Num rows: 6 Data size: 1022 Basic stats: COMPLETE Column stats: COMPLETE @@ -130,23 +139,23 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part14 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-5 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -167,6 +176,36 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part14 + + Stage: Stage-7 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-9 + Map Reduce + Map Operator Tree: + TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator @@ -195,7 +234,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-5 + Stage: Stage-10 Map Reduce Map Operator Tree: TableScan diff --git ql/src/test/results/clientpositive/load_dyn_part3.q.out ql/src/test/results/clientpositive/load_dyn_part3.q.out index 77ba8aa..3242c3d 100644 --- ql/src/test/results/clientpositive/load_dyn_part3.q.out +++ ql/src/test/results/clientpositive/load_dyn_part3.q.out @@ -60,23 +60,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part3 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part3 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/load_dyn_part4.q.out ql/src/test/results/clientpositive/load_dyn_part4.q.out index 80955e3..d24875f 100644 --- ql/src/test/results/clientpositive/load_dyn_part4.q.out +++ ql/src/test/results/clientpositive/load_dyn_part4.q.out @@ -70,23 +70,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part4 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part4 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/load_dyn_part5.q.out ql/src/test/results/clientpositive/load_dyn_part5.q.out index 0bcc432..e4bc742 100644 --- ql/src/test/results/clientpositive/load_dyn_part5.q.out +++ ql/src/test/results/clientpositive/load_dyn_part5.q.out @@ -43,23 +43,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part5 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part5 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/load_dyn_part8.q.out ql/src/test/results/clientpositive/load_dyn_part8.q.out index a542fa8..dc55eec 100644 --- ql/src/test/results/clientpositive/load_dyn_part8.q.out +++ ql/src/test/results/clientpositive/load_dyn_part8.q.out @@ -115,9 +115,8 @@ STAGE DEPENDENCIES: Stage-2 is a root stage Stage-0 depends on stages: Stage-2 Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 + Stage-1 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 @@ -135,14 +134,34 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - auto parallelism: false +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.nzhang_part8 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct nzhang_part8 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part8 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Filter Operator isSamplingPred: false predicate: (ds > '2008-04-08') (type: boolean) @@ -153,20 +172,32 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - GlobalTableId: 0 + GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 + Static Partition Specification: ds=2008-12-31/ + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - columns _col0,_col1,_col2 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + bucket_count -1 + columns key,value + columns.comments defaultdefault + columns.types string:string +#### A masked pattern was here #### + name default.nzhang_part8 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct nzhang_part8 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part8 TotalFiles: 1 - GatherStats: false + GatherStats: true MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### @@ -360,38 +391,6 @@ STAGE PLANS: /srcpart/ds=2008-04-08/hr=12 [srcpart] /srcpart/ds=2008-04-09/hr=11 [srcpart] /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments defaultdefault - columns.types string:string -#### A masked pattern was here #### - name default.nzhang_part8 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct nzhang_part8 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part8 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false Stage: Stage-0 Move Operator @@ -424,78 +423,6 @@ STAGE PLANS: Stats-Aggr Operator #### A masked pattern was here #### - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10002 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 2 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Static Partition Specification: ds=2008-12-31/ - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments defaultdefault - columns.types string:string -#### A masked pattern was here #### - name default.nzhang_part8 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct nzhang_part8 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part8 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Stage: Stage-1 Move Operator tables: @@ -523,7 +450,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part8 - Stage: Stage-5 + Stage: Stage-4 Stats-Aggr Operator #### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/load_dyn_part9.q.out ql/src/test/results/clientpositive/load_dyn_part9.q.out index d782880..300f41e 100644 --- ql/src/test/results/clientpositive/load_dyn_part9.q.out +++ ql/src/test/results/clientpositive/load_dyn_part9.q.out @@ -62,23 +62,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part9 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part9 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/merge3.q.out ql/src/test/results/clientpositive/merge3.q.out index 1701be1..a0dc3a8 100644 --- ql/src/test/results/clientpositive/merge3.q.out +++ ql/src/test/results/clientpositive/merge3.q.out @@ -2447,14 +2447,34 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - auto parallelism: false +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.merge_src_part2 + partition_columns ds + partition_columns.types string + serialization.ddl struct merge_src_part2 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.merge_src_part2 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2473,7 +2493,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.merge_src_part - numFiles 1 + numFiles 2 numRows 1000 partition_columns ds partition_columns.types string @@ -2518,7 +2538,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.merge_src_part - numFiles 1 + numFiles 2 numRows 1000 partition_columns ds partition_columns.types string @@ -2551,38 +2571,6 @@ STAGE PLANS: Truncated Path -> Alias: /merge_src_part/ds=2008-04-08 [merge_src_part] /merge_src_part/ds=2008-04-09 [merge_src_part] - Needs Tagging: false - Reduce Operator Tree: - Extract - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.merge_src_part2 - partition_columns ds - partition_columns.types string - serialization.ddl struct merge_src_part2 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.merge_src_part2 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false Stage: Stage-7 Conditional Operator @@ -4915,8 +4903,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + + sort order: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE tag: -1 @@ -4940,7 +4927,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.merge_src_part - numFiles 1 + numFiles 2 numRows 1000 partition_columns ds partition_columns.types string @@ -4985,7 +4972,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.merge_src_part - numFiles 1 + numFiles 2 numRows 1000 partition_columns ds partition_columns.types string diff --git ql/src/test/results/clientpositive/merge4.q.out ql/src/test/results/clientpositive/merge4.q.out index 515395f..f86c21c 100644 --- ql/src/test/results/clientpositive/merge4.q.out +++ ql/src/test/results/clientpositive/merge4.q.out @@ -37,23 +37,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part Stage: Stage-7 Conditional Operator @@ -2830,12 +2821,14 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part TableScan Union Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE @@ -2843,23 +2836,14 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1001 Data size: 10883 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part Stage: Stage-8 Conditional Operator diff --git ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out index 06b11dc..86978f3 100644 --- ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out +++ ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out @@ -155,23 +155,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 174 Data size: 34830 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 174 Data size: 34830 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 174 Data size: 34830 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 174 Data size: 34830 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.merge_dynamic_part + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.merge_dynamic_part Stage: Stage-7 Conditional Operator @@ -286,9 +277,9 @@ outputformat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat columns:struct columns { string key, string value} partitioned:true partitionColumns:struct partition_columns { string ds, string hr} -totalNumberFiles:4 +totalNumberFiles:6 totalFileSize:34830 -maxFileSize:11603 -minFileSize:5812 +maxFileSize:5812 +minFileSize:5791 #### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out index f14d6ca..7fd0bfc 100644 --- ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out +++ ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out @@ -158,23 +158,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), if(((key % 2) = 0), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.merge_dynamic_part + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.merge_dynamic_part Stage: Stage-7 Conditional Operator diff --git ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out index 8a786c8..044b76f 100644 --- ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out +++ ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out @@ -132,23 +132,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), if(((key % 100) = 0), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.merge_dynamic_part + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.merge_dynamic_part Stage: Stage-7 Conditional Operator diff --git ql/src/test/results/clientpositive/orc_analyze.q.out ql/src/test/results/clientpositive/orc_analyze.q.out index af79e26..e718b29 100644 --- ql/src/test/results/clientpositive/orc_analyze.q.out +++ ql/src/test/results/clientpositive/orc_analyze.q.out @@ -624,10 +624,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 21980 - totalSize 4959 + rawDataSize 21950 + totalSize 2024 #### A masked pattern was here #### # Storage Information @@ -669,10 +669,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 22048 - totalSize 5044 + rawDataSize 22050 + totalSize 2043 #### A masked pattern was here #### # Storage Information @@ -777,10 +777,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 21980 - totalSize 4959 + rawDataSize 21950 + totalSize 2024 #### A masked pattern was here #### # Storage Information @@ -822,10 +822,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 22048 - totalSize 5044 + rawDataSize 22050 + totalSize 2043 #### A masked pattern was here #### # Storage Information diff --git ql/src/test/results/clientpositive/orc_merge2.q.out ql/src/test/results/clientpositive/orc_merge2.q.out index 8f26ef0..b927b75e 100644 --- ql/src/test/results/clientpositive/orc_merge2.q.out +++ ql/src/test/results/clientpositive/orc_merge2.q.out @@ -26,8 +26,13 @@ POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge2a PARTITION (one=' POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -40,23 +45,23 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col3 (type: int) + File Output Operator + compressed: false Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) - Reduce Operator Tree: - Extract - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat - serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde - name: default.orcfile_merge2a + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge2a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -75,6 +80,26 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge2a PARTITION (one='1', two, three) SELECT key, value, PMOD(HASH(key), 10) as two, PMOD(HASH(value), 10) as three diff --git ql/src/test/results/clientpositive/stats2.q.out ql/src/test/results/clientpositive/stats2.q.out index 963f8d4..694c1a2 100644 --- ql/src/test/results/clientpositive/stats2.q.out +++ ql/src/test/results/clientpositive/stats2.q.out @@ -27,23 +27,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.analyze_t1 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.analyze_t1 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/stats4.q.out ql/src/test/results/clientpositive/stats4.q.out index 7327b54..39d5413 100644 --- ql/src/test/results/clientpositive/stats4.q.out +++ ql/src/test/results/clientpositive/stats4.q.out @@ -48,11 +48,20 @@ insert overwrite table nzhang_part2 partition(ds='2008-12-31', hr) select key, v POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 + Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 + Stage-14 depends on stages: Stage-2 , consists of Stage-11, Stage-10, Stage-12 + Stage-11 + Stage-1 depends on stages: Stage-11, Stage-10, Stage-13 + Stage-9 depends on stages: Stage-1 + Stage-10 + Stage-12 + Stage-13 depends on stages: Stage-12 STAGE PLANS: Stage: Stage-2 @@ -68,12 +77,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 Filter Operator predicate: (ds > '2008-04-08') (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE @@ -83,21 +94,21 @@ STAGE PLANS: Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 666 Data size: 7075 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.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + + Stage: Stage-8 + Conditional Operator + + Stage: Stage-5 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -119,23 +130,40 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part2 + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 + + Stage: Stage-6 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 + + Stage: Stage-7 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-14 + Conditional Operator + + Stage: Stage-11 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-1 Move Operator @@ -150,9 +178,39 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part2 - Stage: Stage-5 + Stage: Stage-9 Stats-Aggr Operator + Stage: Stage-10 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + + Stage: Stage-12 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + + Stage: Stage-13 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: from srcpart insert overwrite table nzhang_part1 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table nzhang_part2 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08' diff --git ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out index 27a3742..982baab 100644 --- ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out +++ ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out @@ -20,8 +20,13 @@ POSTHOOK: query: explain insert overwrite table tmptable partition (part) select POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 @@ -37,23 +42,23 @@ STAGE PLANS: expressions: 'no_such_value' (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### Stage: Stage-0 Move Operator @@ -70,6 +75,36 @@ STAGE PLANS: Stage: Stage-2 Stats-Aggr Operator + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable + + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: insert overwrite table tmptable partition (part) select key, value from src where key = 'no_such_value' PREHOOK: type: QUERY PREHOOK: Input: default@src diff --git ql/src/test/results/clientpositive/tez/auto_sortmerge_join_16.q.out ql/src/test/results/clientpositive/tez/auto_sortmerge_join_16.q.out index 03507dd..b32ac06 100644 --- ql/src/test/results/clientpositive/tez/auto_sortmerge_join_16.q.out +++ ql/src/test/results/clientpositive/tez/auto_sortmerge_join_16.q.out @@ -232,6 +232,16 @@ POSTHOOK: Input: default@bucket_small@pri=2 0 val_0 val_0 day1 1 0 val_0 val_0 day1 1 0 val_0 val_0 day1 1 +103 val_103 val_103 day1 1 +103 val_103 val_103 day1 1 +103 val_103 val_103 day1 1 +103 val_103 val_103 day1 1 +374 val_374 val_374 day1 1 +374 val_374 val_374 day1 1 +172 val_172 val_172 day1 1 +172 val_172 val_172 day1 1 +172 val_172 val_172 day1 1 +172 val_172 val_172 day1 1 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 @@ -240,13 +250,3 @@ POSTHOOK: Input: default@bucket_small@pri=2 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 169 val_169 val_169 day1 1 -374 val_374 val_374 day1 1 -374 val_374 val_374 day1 1 -172 val_172 val_172 day1 1 -172 val_172 val_172 day1 1 -172 val_172 val_172 day1 1 -172 val_172 val_172 day1 1 -103 val_103 val_103 day1 1 -103 val_103 val_103 day1 1 -103 val_103 val_103 day1 1 -103 val_103 val_103 day1 1 diff --git ql/src/test/results/clientpositive/tez/delete_all_partitioned.q.out ql/src/test/results/clientpositive/tez/delete_all_partitioned.q.out index 4486323..12efe78 100644 --- ql/src/test/results/clientpositive/tez/delete_all_partitioned.q.out +++ ql/src/test/results/clientpositive/tez/delete_all_partitioned.q.out @@ -84,3 +84,5 @@ POSTHOOK: Input: default@acid_dap POSTHOOK: Input: default@acid_dap@ds=today POSTHOOK: Input: default@acid_dap@ds=tomorrow #### A masked pattern was here #### +-1071480828 aw724t8c5558x2xneC624 today +-1072076362 2uLyD28144vklju213J1mr today diff --git ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out index ed42e67..d520217 100644 --- ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out +++ ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out @@ -352,11 +352,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -420,11 +420,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -727,11 +727,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -795,11 +795,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -2160,11 +2160,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Execution mode: vectorized Reducer 2 Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out index 5ff3e49..8c93095 100644 --- ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out +++ ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out @@ -291,11 +291,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reducer 2 Reduce Operator Tree: Extract @@ -357,11 +357,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reducer 2 Reduce Operator Tree: Extract @@ -644,11 +644,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) sort order: ++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reducer 2 Reduce Operator Tree: Extract @@ -710,11 +710,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reducer 2 Reduce Operator Tree: Extract @@ -2058,11 +2058,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float) + key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) + value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string) Reducer 2 Reduce Operator Tree: Extract diff --git ql/src/test/results/clientpositive/tez/dynpart_sort_optimization2.q.out ql/src/test/results/clientpositive/tez/dynpart_sort_optimization2.q.out new file mode 100644 index 0000000..f6299e7 --- /dev/null +++ ql/src/test/results/clientpositive/tez/dynpart_sort_optimization2.q.out @@ -0,0 +1,1582 @@ +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss +POSTHOOK: query: create table ss ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss +PREHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part +POSTHOOK: query: create table ss_part ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part +PREHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ss +POSTHOOK: query: load data local inpath '../../data/files/dynpart_test.txt' overwrite into table ss +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ss +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reducer 2 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: -- SORT DYNAMIC PARTITION DISABLED + +explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + Statistics: Num rows: 46 Data size: 553 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Reducer 2 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ss_part + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_part +POSTHOOK: query: insert overwrite table ss_part partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 151 + totalSize 162 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part +POSTHOOK: query: desc formatted ss_part partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 186 + totalSize 199 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part +PREHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part +POSTHOOK: Input: default@ss_part@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_orc +POSTHOOK: query: -- VECTORIZATION IS ENABLED + +create table ss_orc ( +ss_sold_date_sk int, +ss_net_paid_inc_tax float, +ss_net_profit float) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_orc +PREHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: create table ss_part_orc ( +ss_net_paid_inc_tax float, +ss_net_profit float) +partitioned by (ss_sold_date_sk int) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss_part_orc +PREHOOK: query: insert overwrite table ss_orc select * from ss +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss_orc +POSTHOOK: query: insert overwrite table ss_orc select * from ss +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss_orc +POSTHOOK: Lineage: ss_orc.ss_net_paid_inc_tax SIMPLE [(ss)ss.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_net_profit SIMPLE [(ss)ss.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_orc.ss_sold_date_sk SIMPLE [(ss)ss.FieldSchema(name:ss_sold_date_sk, type:int, comment:null), ] +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss +PREHOOK: Output: default@ss +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss +POSTHOOK: Output: default@ss +PREHOOK: query: drop table ss_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part +PREHOOK: Output: default@ss_part +POSTHOOK: query: drop table ss_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part +POSTHOOK: Output: default@ss_part +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + outputColumnNames: ss_sold_date_sk, ss_net_paid_inc_tax, ss_net_profit + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: float), _col2 (type: float) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + Execution mode: vectorized + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + group by ss_sold_date_sk, + ss_net_paid_inc_tax, + ss_net_profit + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +2.1 -2026.3 2452617 +2.99 -11.32 2452617 +85.8 25.61 2452617 +552.96 -1363.84 2452617 +565.92 196.48 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +7412.83 2071.68 2452617 +10022.63 3952.8 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +0.15 -241.22 2452638 +150.39 -162.12 2452638 +156.67 -4626.56 2452638 +181.03 -207.24 2452638 +267.01 -3266.36 2452638 +317.87 -3775.38 2452638 +1327.08 57.97 2452638 +1413.19 178.08 2452638 +1524.33 494.37 2452638 +1971.35 -488.25 2452638 +4133.98 -775.72 2452638 +4329.49 -4000.51 2452638 +10171.1 660.48 2452638 +PREHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +POSTHOOK: query: explain insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss_orc + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_net_paid_inc_tax (type: float), ss_net_profit (type: float), ss_sold_date_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) + Execution mode: vectorized + Reducer 2 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + Execution mode: vectorized + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ss_sold_date_sk + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.ss_part_orc + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: insert overwrite table ss_part_orc partition (ss_sold_date_sk) +select ss_net_paid_inc_tax, + ss_net_profit, + ss_sold_date_sk + from ss_orc + where ss_sold_date_sk>=2452617 and ss_sold_date_sk<=2452638 + distribute by ss_sold_date_sk +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452617 +POSTHOOK: Output: default@ss_part_orc@ss_sold_date_sk=2452638 +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452617).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_paid_inc_tax SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: ss_part_orc PARTITION(ss_sold_date_sk=2452638).ss_net_profit SIMPLE [(ss_orc)ss_orc.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452617) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452617] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 11 + rawDataSize 88 + totalSize 417 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452617 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452617 +#### A masked pattern was here #### +3423.95 -3164.07 2452617 +5362.01 -600.28 2452617 +565.92 196.48 2452617 +85.8 25.61 2452617 +7412.83 2071.68 2452617 +879.07 -2185.76 2452617 +1765.07 -4648.8 2452617 +552.96 -1363.84 2452617 +2.1 -2026.3 2452617 +10022.63 3952.8 2452617 +2.99 -11.32 2452617 +PREHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@ss_part_orc +POSTHOOK: query: desc formatted ss_part_orc partition(ss_sold_date_sk=2452638) +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@ss_part_orc +# col_name data_type comment + +ss_net_paid_inc_tax float +ss_net_profit float + +# Partition Information +# col_name data_type comment + +ss_sold_date_sk int + +# Detailed Partition Information +Partition Value: [2452638] +Database: default +Table: ss_part_orc +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 13 + rawDataSize 104 + totalSize 440 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss_part_orc +PREHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +POSTHOOK: query: select * from ss_part_orc where ss_sold_date_sk=2452638 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Input: default@ss_part_orc@ss_sold_date_sk=2452638 +#### A masked pattern was here #### +4329.49 -4000.51 2452638 +1413.19 178.08 2452638 +150.39 -162.12 2452638 +1524.33 494.37 2452638 +0.15 -241.22 2452638 +267.01 -3266.36 2452638 +181.03 -207.24 2452638 +1971.35 -488.25 2452638 +1327.08 57.97 2452638 +156.67 -4626.56 2452638 +317.87 -3775.38 2452638 +10171.1 660.48 2452638 +4133.98 -775.72 2452638 +PREHOOK: query: drop table ss_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_orc +PREHOOK: Output: default@ss_orc +POSTHOOK: query: drop table ss_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_orc +POSTHOOK: Output: default@ss_orc +PREHOOK: query: drop table ss_part_orc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@ss_part_orc +PREHOOK: Output: default@ss_part_orc +POSTHOOK: query: drop table ss_part_orc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@ss_part_orc +POSTHOOK: Output: default@ss_part_orc diff --git ql/src/test/results/clientpositive/tez/load_dyn_part1.q.out ql/src/test/results/clientpositive/tez/load_dyn_part1.q.out index 8ff926b..dcf011e 100644 --- ql/src/test/results/clientpositive/tez/load_dyn_part1.q.out +++ ql/src/test/results/clientpositive/tez/load_dyn_part1.q.out @@ -67,9 +67,6 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-2 Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -84,12 +81,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 Filter Operator predicate: (ds > '2008-04-08') (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE @@ -97,36 +96,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Reducer 2 - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part1 - Reducer 3 - Reduce Operator Tree: - Extract - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part2 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 Stage: Stage-3 Dependency Collection diff --git ql/src/test/results/clientpositive/tez/load_dyn_part3.q.out ql/src/test/results/clientpositive/tez/load_dyn_part3.q.out index 9745dea..8f95a76 100644 --- ql/src/test/results/clientpositive/tez/load_dyn_part3.q.out +++ ql/src/test/results/clientpositive/tez/load_dyn_part3.q.out @@ -53,8 +53,6 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -66,24 +64,14 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reducer 2 - Reduce Operator Tree: - Extract - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part3 + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part3 Stage: Stage-2 Dependency Collection diff --git ql/src/test/results/clientpositive/tez/orc_analyze.q.out ql/src/test/results/clientpositive/tez/orc_analyze.q.out index af79e26..e718b29 100644 --- ql/src/test/results/clientpositive/tez/orc_analyze.q.out +++ ql/src/test/results/clientpositive/tez/orc_analyze.q.out @@ -624,10 +624,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 21980 - totalSize 4959 + rawDataSize 21950 + totalSize 2024 #### A masked pattern was here #### # Storage Information @@ -669,10 +669,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 22048 - totalSize 5044 + rawDataSize 22050 + totalSize 2043 #### A masked pattern was here #### # Storage Information @@ -777,10 +777,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 21980 - totalSize 4959 + rawDataSize 21950 + totalSize 2024 #### A masked pattern was here #### # Storage Information @@ -822,10 +822,10 @@ Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true - numFiles 4 + numFiles 1 numRows 50 - rawDataSize 22048 - totalSize 5044 + rawDataSize 22050 + totalSize 2043 #### A masked pattern was here #### # Storage Information diff --git ql/src/test/results/clientpositive/tez/orc_merge2.q.out ql/src/test/results/clientpositive/tez/orc_merge2.q.out index e08e211..0f1917f 100644 --- ql/src/test/results/clientpositive/tez/orc_merge2.q.out +++ ql/src/test/results/clientpositive/tez/orc_merge2.q.out @@ -33,8 +33,6 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -46,24 +44,14 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col3 (type: int) + File Output Operator + compressed: false Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) - Reducer 2 - Reduce Operator Tree: - Extract - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat - serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde - name: default.orcfile_merge2a + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge2a Stage: Stage-2 Dependency Collection diff --git ql/src/test/results/clientpositive/tez/tez_dml.q.out ql/src/test/results/clientpositive/tez/tez_dml.q.out index a6c45d5..9b7f564 100644 --- ql/src/test/results/clientpositive/tez/tez_dml.q.out +++ ql/src/test/results/clientpositive/tez/tez_dml.q.out @@ -443,8 +443,6 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -456,24 +454,14 @@ STAGE PLANS: expressions: value (type: string), cnt (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: bigint) - sort order: + - Map-reduce partition columns: _col1 (type: bigint) + File Output Operator + compressed: false Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint) - Reducer 2 - Reduce Operator Tree: - Extract - Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 309 Data size: 2718 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_src_part + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_src_part Stage: Stage-2 Dependency Collection @@ -529,314 +517,314 @@ POSTHOOK: Input: default@tmp_src_part@d=4 POSTHOOK: Input: default@tmp_src_part@d=5 #### A masked pattern was here #### val_490 1 -val_289 1 -val_291 1 -val_292 1 -val_296 1 -val_180 1 -val_30 1 -val_302 1 -val_305 1 -val_306 1 -val_491 1 -val_308 1 -val_96 1 -val_310 1 -val_178 1 -val_315 1 -val_177 1 -val_493 1 -val_170 1 -val_494 1 -val_495 1 -val_323 1 -val_496 1 -val_17 1 -val_33 1 -val_497 1 -val_332 1 -val_111 1 -val_335 1 -val_336 1 -val_338 1 -val_339 1 -val_34 1 -val_341 1 -val_11 1 -val_85 1 -val_345 1 -val_168 1 -val_166 1 -val_351 1 -val_53 1 -val_356 1 -val_360 1 -val_362 1 -val_364 1 -val_365 1 -val_366 1 -val_54 1 -val_368 1 -val_163 1 -val_57 1 -val_373 1 -val_374 1 -val_375 1 -val_377 1 -val_378 1 -val_379 1 -val_86 1 -val_162 1 -val_386 1 -val_389 1 -val_392 1 -val_393 1 -val_394 1 -val_64 1 -val_160 1 -val_65 1 -val_66 1 -val_4 1 -val_400 1 -val_158 1 -val_402 1 -val_157 1 -val_87 1 -val_156 1 -val_407 1 -val_155 1 -val_41 1 -val_411 1 -val_69 1 -val_105 1 -val_153 1 -val_418 1 -val_419 1 -val_9 1 -val_421 1 -val_74 1 -val_427 1 -val_10 1 -val_43 1 -val_150 1 -val_145 1 -val_432 1 -val_435 1 -val_436 1 -val_437 1 -val_143 1 -val_77 1 -val_44 1 -val_443 1 -val_444 1 -val_446 1 -val_448 1 -val_192 1 -val_190 1 -val_194 1 -val_449 1 -val_196 1 -val_452 1 -val_19 1 -val_2 1 -val_20 1 -val_453 1 -val_201 1 -val_202 1 -val_136 1 -val_455 1 -val_457 1 -val_189 1 -val_78 1 -val_8 1 -val_214 1 -val_460 1 -val_80 1 -val_218 1 -val_82 1 -val_133 1 -val_222 1 -val_467 1 -val_131 1 -val_226 1 -val_228 1 -val_126 1 -val_186 1 -val_47 1 -val_235 1 -val_470 1 -val_472 1 -val_475 1 -val_477 1 -val_241 1 -val_92 1 -val_244 1 -val_247 1 -val_248 1 -val_249 1 -val_252 1 -val_479 1 -val_116 1 -val_257 1 -val_258 1 -val_481 1 -val_260 1 -val_262 1 -val_263 1 -val_482 1 -val_266 1 -val_27 1 -val_483 1 -val_183 1 -val_274 1 -val_275 1 -val_181 1 -val_484 1 -val_28 1 -val_485 1 -val_487 1 -val_114 1 -val_283 1 -val_284 1 -val_285 1 -val_286 1 val_287 1 -val_84 2 -val_95 2 -val_97 2 -val_98 2 -val_100 2 -val_103 2 -val_104 2 -val_113 2 -val_118 2 -val_12 2 -val_120 2 -val_125 2 -val_129 2 -val_134 2 -val_137 2 -val_146 2 -val_149 2 -val_15 2 -val_152 2 -val_164 2 -val_165 2 -val_172 2 -val_174 2 -val_175 2 -val_176 2 -val_179 2 -val_18 2 -val_191 2 -val_195 2 -val_197 2 -val_200 2 -val_203 2 -val_205 2 -val_207 2 -val_209 2 -val_213 2 -val_216 2 -val_217 2 -val_219 2 -val_221 2 -val_223 2 -val_224 2 -val_229 2 -val_233 2 -val_237 2 -val_238 2 -val_239 2 -val_24 2 -val_242 2 -val_255 2 -val_256 2 -val_26 2 -val_265 2 -val_272 2 -val_278 2 -val_280 2 -val_281 2 -val_282 2 -val_288 2 -val_307 2 -val_309 2 -val_317 2 -val_321 2 -val_322 2 -val_325 2 -val_331 2 -val_333 2 -val_342 2 -val_344 2 -val_353 2 -val_367 2 -val_37 2 -val_382 2 -val_395 2 -val_397 2 -val_399 2 -val_404 2 -val_413 2 -val_414 2 -val_42 2 -val_424 2 -val_429 2 -val_439 2 -val_458 2 -val_459 2 -val_462 2 -val_463 2 -val_478 2 -val_492 2 -val_51 2 -val_58 2 -val_67 2 -val_72 2 -val_76 2 +val_286 1 +val_285 1 +val_284 1 +val_283 1 +val_114 1 +val_487 1 +val_485 1 +val_28 1 +val_484 1 +val_181 1 +val_275 1 +val_274 1 +val_183 1 +val_483 1 +val_27 1 +val_266 1 +val_482 1 +val_263 1 +val_262 1 +val_260 1 +val_481 1 +val_258 1 +val_257 1 +val_116 1 +val_479 1 +val_252 1 +val_249 1 +val_248 1 +val_247 1 +val_244 1 +val_92 1 +val_241 1 +val_477 1 +val_475 1 +val_472 1 +val_470 1 +val_235 1 +val_47 1 +val_186 1 +val_126 1 +val_228 1 +val_226 1 +val_131 1 +val_467 1 +val_222 1 +val_133 1 +val_82 1 +val_218 1 +val_80 1 +val_460 1 +val_214 1 +val_8 1 +val_78 1 +val_189 1 +val_457 1 +val_455 1 +val_136 1 +val_202 1 +val_201 1 +val_453 1 +val_20 1 +val_2 1 +val_19 1 +val_452 1 +val_196 1 +val_449 1 +val_194 1 +val_190 1 +val_192 1 +val_448 1 +val_446 1 +val_444 1 +val_443 1 +val_44 1 +val_77 1 +val_143 1 +val_437 1 +val_436 1 +val_435 1 +val_432 1 +val_145 1 +val_150 1 +val_43 1 +val_10 1 +val_427 1 +val_74 1 +val_421 1 +val_9 1 +val_419 1 +val_418 1 +val_153 1 +val_105 1 +val_69 1 +val_411 1 +val_41 1 +val_155 1 +val_407 1 +val_156 1 +val_87 1 +val_157 1 +val_402 1 +val_158 1 +val_400 1 +val_4 1 +val_66 1 +val_65 1 +val_160 1 +val_64 1 +val_394 1 +val_393 1 +val_392 1 +val_389 1 +val_386 1 +val_162 1 +val_86 1 +val_379 1 +val_378 1 +val_377 1 +val_375 1 +val_374 1 +val_373 1 +val_57 1 +val_163 1 +val_368 1 +val_54 1 +val_366 1 +val_365 1 +val_364 1 +val_362 1 +val_360 1 +val_356 1 +val_53 1 +val_351 1 +val_166 1 +val_168 1 +val_345 1 +val_85 1 +val_11 1 +val_341 1 +val_34 1 +val_339 1 +val_338 1 +val_336 1 +val_335 1 +val_111 1 +val_332 1 +val_497 1 +val_33 1 +val_17 1 +val_496 1 +val_323 1 +val_495 1 +val_494 1 +val_170 1 +val_493 1 +val_177 1 +val_315 1 +val_178 1 +val_310 1 +val_96 1 +val_308 1 +val_491 1 +val_306 1 +val_305 1 +val_302 1 +val_30 1 +val_180 1 +val_296 1 +val_292 1 +val_291 1 +val_289 1 +val_98 2 +val_97 2 +val_95 2 +val_84 2 val_83 2 -val_396 3 -val_384 3 -val_369 3 +val_76 2 +val_72 2 +val_67 2 +val_58 2 +val_51 2 +val_492 2 +val_478 2 +val_463 2 +val_462 2 +val_459 2 +val_458 2 +val_439 2 +val_429 2 +val_424 2 +val_42 2 +val_414 2 +val_413 2 +val_404 2 +val_399 2 +val_397 2 +val_395 2 +val_382 2 +val_37 2 +val_367 2 +val_353 2 +val_344 2 +val_342 2 +val_333 2 +val_331 2 +val_325 2 +val_322 2 +val_321 2 +val_317 2 +val_309 2 +val_307 2 +val_288 2 +val_282 2 +val_281 2 +val_280 2 +val_278 2 +val_272 2 +val_265 2 +val_26 2 +val_256 2 +val_255 2 +val_242 2 +val_24 2 +val_239 2 +val_238 2 +val_237 2 +val_233 2 +val_229 2 +val_224 2 +val_223 2 +val_221 2 +val_219 2 +val_217 2 +val_216 2 +val_213 2 +val_209 2 +val_207 2 +val_205 2 +val_203 2 +val_200 2 +val_197 2 +val_195 2 +val_191 2 +val_18 2 +val_179 2 +val_176 2 +val_175 2 +val_174 2 +val_172 2 +val_165 2 +val_164 2 +val_152 2 +val_15 2 +val_149 2 +val_146 2 +val_137 2 +val_134 2 +val_129 2 +val_125 2 +val_120 2 +val_12 2 +val_118 2 +val_113 2 +val_104 2 +val_103 2 +val_100 2 val_498 3 -val_35 3 -val_167 3 -val_327 3 -val_318 3 -val_128 3 -val_90 3 -val_466 3 -val_316 3 -val_311 3 -val_454 3 -val_298 3 -val_273 3 -val_187 3 -val_208 3 -val_199 3 -val_193 3 -val_480 3 -val_438 3 -val_431 3 -val_0 3 -val_119 3 -val_70 3 -val_430 3 -val_5 3 -val_417 3 -val_409 3 +val_369 3 +val_384 3 +val_396 3 val_403 3 -val_406 4 -val_489 4 +val_409 3 +val_417 3 +val_5 3 +val_430 3 +val_70 3 +val_119 3 +val_0 3 +val_431 3 +val_438 3 +val_480 3 +val_193 3 +val_199 3 +val_208 3 +val_187 3 +val_273 3 +val_298 3 +val_454 3 +val_311 3 +val_316 3 +val_466 3 +val_90 3 +val_128 3 +val_318 3 +val_327 3 +val_167 3 +val_35 3 val_468 4 -val_277 4 -val_138 4 +val_489 4 +val_406 4 val_169 4 -val_348 5 -val_230 5 -val_401 5 +val_138 4 +val_277 4 val_469 5 +val_401 5 +val_230 5 +val_348 5 PREHOOK: query: -- multi insert CREATE TABLE even (c int, d string) PREHOOK: type: CREATETABLE diff --git ql/src/test/results/clientpositive/tez/update_all_partitioned.q.out ql/src/test/results/clientpositive/tez/update_all_partitioned.q.out index 3fae6a9..922b5bf 100644 --- ql/src/test/results/clientpositive/tez/update_all_partitioned.q.out +++ ql/src/test/results/clientpositive/tez/update_all_partitioned.q.out @@ -85,15 +85,21 @@ POSTHOOK: Input: default@acid_uap@ds=today POSTHOOK: Input: default@acid_uap@ds=tomorrow #### A masked pattern was here #### -1073279343 fred today +-1073279343 oj1YrV5Wa today -1073051226 fred today -1072910839 fred today +-1072081801 dPkN74F7 today -1072081801 fred today -1072076362 fred today -1071480828 fred today +-1071363017 Anj0oF today -1071363017 fred today +-1070883071 0ruyd6Y50JpdGRf6HqD today -1070883071 fred today -1070551679 fred today +-1070551679 iUR3Q today -1069736047 fred today +-1069736047 k17Am8uPHWk02cEf1jet today 762 fred tomorrow 762 fred tomorrow 762 fred tomorrow diff --git ql/src/test/results/clientpositive/union_remove_17.q.out ql/src/test/results/clientpositive/union_remove_17.q.out index 593ed06..5b466c6 100644 --- ql/src/test/results/clientpositive/union_remove_17.q.out +++ ql/src/test/results/clientpositive/union_remove_17.q.out @@ -81,12 +81,14 @@ STAGE PLANS: expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 60 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 60 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 TableScan alias: inputtbl1 Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE @@ -100,23 +102,14 @@ STAGE PLANS: expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 0 Data size: 60 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 0 Data size: 60 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) - Reduce Operator Tree: - Extract - Statistics: Num rows: 0 Data size: 60 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 60 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.outputtbl1 + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.outputtbl1 Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/update_all_partitioned.q.out ql/src/test/results/clientpositive/update_all_partitioned.q.out index 3fae6a9..922b5bf 100644 --- ql/src/test/results/clientpositive/update_all_partitioned.q.out +++ ql/src/test/results/clientpositive/update_all_partitioned.q.out @@ -85,15 +85,21 @@ POSTHOOK: Input: default@acid_uap@ds=today POSTHOOK: Input: default@acid_uap@ds=tomorrow #### A masked pattern was here #### -1073279343 fred today +-1073279343 oj1YrV5Wa today -1073051226 fred today -1072910839 fred today +-1072081801 dPkN74F7 today -1072081801 fred today -1072076362 fred today -1071480828 fred today +-1071363017 Anj0oF today -1071363017 fred today +-1070883071 0ruyd6Y50JpdGRf6HqD today -1070883071 fred today -1070551679 fred today +-1070551679 iUR3Q today -1069736047 fred today +-1069736047 k17Am8uPHWk02cEf1jet today 762 fred tomorrow 762 fred tomorrow 762 fred tomorrow