diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index afee315378..c6665f8f68 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -2537,6 +2537,11 @@ private static void populateLlapDaemonVarsSet(Set llapDaemonVarsSetLocal "When estimating output rows for a join involving multiple columns, the default behavior assumes" + "the columns are independent. Setting this flag to true will cause the estimator to assume" + "the columns are correlated."), + HIVE_STATS_RANGE_SELECTIVITY_UNIFORM_DISTRIBUTION("hive.stats.filter.range.uniform", true, + "When estimating output rows from a condition, if a range predicate is applied over a column and the\n" + + "minimum and maximum values for that column are available, assume uniform distribution of values\n" + + "across that range and scales number of rows proportionally. If this is set to false, default\n" + + "selectivity value is used."), // in the absence of uncompressed/raw data size, total file size will be used for statistics // annotation. But the file may be compressed, encoded and serialized which may be lesser in size // than the actual uncompressed/raw data size. This factor will be multiplied to file size to estimate diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java index 187ec254a7..8056161488 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/AnnotateStatsProcCtx.java @@ -31,36 +31,37 @@ private ParseContext pctx; private HiveConf conf; - private Statistics andExprStats = null; + private boolean uniformWithinRange; + private Statistics andExprStats; private Set affectedColumns; public AnnotateStatsProcCtx(ParseContext pctx) { - this.setParseContext(pctx); + this.pctx = pctx; if(pctx != null) { - this.setConf(pctx.getConf()); + this.conf = pctx.getConf(); + this.uniformWithinRange = HiveConf.getBoolVar(this.conf, + HiveConf.ConfVars.HIVE_STATS_RANGE_SELECTIVITY_UNIFORM_DISTRIBUTION); } else { - this.setConf(null); + this.conf = null; + this.uniformWithinRange = false; } - affectedColumns = new HashSet<>(); + this.andExprStats = null; + this.affectedColumns = new HashSet<>(); } public HiveConf getConf() { return conf; } - public void setConf(HiveConf conf) { - this.conf = conf; + public boolean isUniformWithinRange() { + return uniformWithinRange; } public ParseContext getParseContext() { return pctx; } - public void setParseContext(ParseContext pctx) { - this.pctx = pctx; - } - public Statistics getAndExprStats() { return andExprStats; } diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java index 4fc73620fe..5b2568a5b0 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/stats/annotation/StatsRulesProcFactory.java @@ -20,6 +20,7 @@ import java.lang.reflect.Field; import java.math.BigDecimal; +import java.math.RoundingMode; import java.util.ArrayList; import java.util.Arrays; import java.util.Collections; @@ -911,6 +912,7 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E ExprNodeColumnDesc columnDesc; ExprNodeConstantDesc constantDesc; boolean upperBound; + boolean closedBound; String boundValue = null; if (genFunc.getChildren().get(0) instanceof ExprNodeColumnDesc && genFunc.getChildren().get(1) instanceof ExprNodeConstantDesc) { @@ -921,14 +923,10 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E if (constantDesc.getValue() == null) { return 0; } - if (udf instanceof GenericUDFOPEqualOrGreaterThan || - udf instanceof GenericUDFOPGreaterThan) { - boundValue = constantDesc.getValue().toString(); - upperBound = false; - } else { - boundValue = constantDesc.getValue().toString(); - upperBound = true; - } + boundValue = constantDesc.getValue().toString(); + upperBound = udf instanceof GenericUDFOPEqualOrLessThan || + udf instanceof GenericUDFOPLessThan; + closedBound = isClosedBound(udf); } else if (genFunc.getChildren().get(1) instanceof ExprNodeColumnDesc && genFunc.getChildren().get(0) instanceof ExprNodeConstantDesc) { columnDesc = (ExprNodeColumnDesc) genFunc.getChildren().get(1); @@ -938,14 +936,10 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E if (constantDesc.getValue() == null) { return 0; } - if (udf instanceof GenericUDFOPEqualOrGreaterThan || - udf instanceof GenericUDFOPGreaterThan) { - boundValue = constantDesc.getValue().toString(); - upperBound = true; - } else { - boundValue = constantDesc.getValue().toString(); - upperBound = false; - } + boundValue = constantDesc.getValue().toString(); + upperBound = udf instanceof GenericUDFOPEqualOrGreaterThan || + udf instanceof GenericUDFOPGreaterThan; + closedBound = isClosedBound(udf); } else { // default return numRows / 3; @@ -961,43 +955,63 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E byte maxValue = cs.getRange().maxValue.byteValue(); byte minValue = cs.getRange().minValue.byteValue(); if (upperBound) { - if (maxValue < value) { + if (maxValue < value || maxValue == value && closedBound) { return numRows; } - if (minValue > value) { + if (minValue > value || minValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (value - minValue) / (maxValue - minValue)) * numRows); + } } else { - if (minValue >= value) { + if (minValue > value || minValue == value && closedBound) { return numRows; } - if (maxValue < value) { + if (maxValue < value || maxValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (maxValue - value) / (maxValue - minValue)) * numRows); + } } } else if (colTypeLowerCase.equals(serdeConstants.SMALLINT_TYPE_NAME)) { short value = Short.parseShort(boundValue); short maxValue = cs.getRange().maxValue.shortValue(); short minValue = cs.getRange().minValue.shortValue(); if (upperBound) { - if (maxValue < value) { + if (maxValue < value || maxValue == value && closedBound) { return numRows; } - if (minValue > value) { + if (minValue > value || minValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (value - minValue) / (maxValue - minValue)) * numRows); + } } else { - if (minValue >= value) { + if (minValue > value || minValue == value && closedBound) { return numRows; } - if (maxValue < value) { + if (maxValue < value || maxValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (maxValue - value) / (maxValue - minValue)) * numRows); + } } } else if (colTypeLowerCase.equals(serdeConstants.INT_TYPE_NAME) || colTypeLowerCase.equals(serdeConstants.DATE_TYPE_NAME)) { int value; - if (colTypeLowerCase == serdeConstants.DATE_TYPE_NAME) { + if (colTypeLowerCase.equals(serdeConstants.DATE_TYPE_NAME)) { DateWritable writableVal = new DateWritable(java.sql.Date.valueOf(boundValue)); value = writableVal.getDays(); } else { @@ -1007,76 +1021,116 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E int maxValue = cs.getRange().maxValue.intValue(); int minValue = cs.getRange().minValue.intValue(); if (upperBound) { - if (maxValue < value) { + if (maxValue < value || maxValue == value && closedBound) { return numRows; } - if (minValue > value) { + if (minValue > value || minValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (value - minValue) / (maxValue - minValue)) * numRows); + } } else { - if (minValue >= value) { + if (minValue > value || minValue == value && closedBound) { return numRows; } - if (maxValue < value) { + if (maxValue < value || maxValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (maxValue - value) / (maxValue - minValue)) * numRows); + } } } else if (colTypeLowerCase.equals(serdeConstants.BIGINT_TYPE_NAME)) { long value = Long.parseLong(boundValue); long maxValue = cs.getRange().maxValue.longValue(); long minValue = cs.getRange().minValue.longValue(); if (upperBound) { - if (maxValue < value) { + if (maxValue < value || maxValue == value && closedBound) { return numRows; } - if (minValue > value) { + if (minValue > value || minValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (value - minValue) / (maxValue - minValue)) * numRows); + } } else { - if (minValue >= value) { + if (minValue > value || minValue == value && closedBound) { return numRows; } - if (maxValue < value) { + if (maxValue < value || maxValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (maxValue - value) / (maxValue - minValue)) * numRows); + } } } else if (colTypeLowerCase.equals(serdeConstants.FLOAT_TYPE_NAME)) { float value = Float.parseFloat(boundValue); float maxValue = cs.getRange().maxValue.floatValue(); float minValue = cs.getRange().minValue.floatValue(); if (upperBound) { - if (maxValue < value) { + if (maxValue < value || maxValue == value && closedBound) { return numRows; } - if (minValue > value) { + if (minValue > value || minValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (value - minValue) / (maxValue - minValue)) * numRows); + } } else { - if (minValue >= value) { + if (minValue > value || minValue == value && closedBound) { return numRows; } - if (maxValue < value) { + if (maxValue < value || maxValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (maxValue - value) / (maxValue - minValue)) * numRows); + } } } else if (colTypeLowerCase.equals(serdeConstants.DOUBLE_TYPE_NAME)) { double value = Double.parseDouble(boundValue); double maxValue = cs.getRange().maxValue.doubleValue(); double minValue = cs.getRange().minValue.doubleValue(); if (upperBound) { - if (maxValue < value) { + if (maxValue < value || maxValue == value && closedBound) { return numRows; } - if (minValue > value) { + if (minValue > value || minValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (value - minValue) / (maxValue - minValue)) * numRows); + } } else { - if (minValue >= value) { + if (minValue > value || minValue == value && closedBound) { return numRows; } - if (maxValue < value) { + if (maxValue < value || maxValue == value && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round(((double) (maxValue - value) / (maxValue - minValue)) * numRows); + } } } else if (colTypeLowerCase.startsWith(serdeConstants.DECIMAL_TYPE_NAME)) { BigDecimal value = new BigDecimal(boundValue); @@ -1085,19 +1139,35 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E int minComparison = value.compareTo(minValue); int maxComparison = value.compareTo(maxValue); if (upperBound) { - if (maxComparison > 0) { + if (maxComparison > 0 || maxComparison == 0 && closedBound) { return numRows; } - if (minComparison < 0) { + if (minComparison < 0 || minComparison == 0 && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round( + ((value.subtract(minValue)).divide(maxValue.subtract(minValue), RoundingMode.UP)) + .multiply(BigDecimal.valueOf(numRows)) + .doubleValue()); + } } else { - if (minComparison <= 0) { + if (minComparison < 0 || minComparison == 0 && closedBound) { return numRows; } - if (maxComparison > 0) { + if (maxComparison > 0 || maxComparison == 0 && !closedBound) { return 0; } + if (aspCtx.isUniformWithinRange()) { + // Assuming uniform distribution, we can use the range to calculate + // new estimate for the number of rows + return Math.round( + ((maxValue.subtract(value)).divide(maxValue.subtract(minValue), RoundingMode.UP)) + .multiply(BigDecimal.valueOf(numRows)) + .doubleValue()); + } } } } catch (NumberFormatException nfe) { @@ -1108,9 +1178,15 @@ private long evaluateComparator(Statistics stats, AnnotateStatsProcCtx aspCtx, E return numRows / 3; } + private boolean isClosedBound(GenericUDF udf) { + return udf instanceof GenericUDFOPEqualOrGreaterThan || + udf instanceof GenericUDFOPEqualOrLessThan; + } + private long evaluateChildExpr(Statistics stats, ExprNodeDesc child, AnnotateStatsProcCtx aspCtx, List neededCols, - Operator op, long currNumRows) throws SemanticException { + Operator op, long currNumRows) + throws SemanticException { long numRows = currNumRows; @@ -1946,6 +2022,8 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, pred = jop.getConf().getResidualFilterExprs().get(0); } // evaluate filter expression and update statistics + final boolean uniformWithinRange = HiveConf.getBoolVar( + aspCtx.getConf(), HiveConf.ConfVars.HIVE_STATS_RANGE_SELECTIVITY_UNIFORM_DISTRIBUTION); newNumRows = evaluateExpression(stats, pred, aspCtx, jop.getSchema().getColumnNames(), jop, stats.getNumRows()); // update statistics based on column statistics. @@ -2039,6 +2117,8 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, pred = jop.getConf().getResidualFilterExprs().get(0); } // evaluate filter expression and update statistics + final boolean uniformWithinRange = HiveConf.getBoolVar( + aspCtx.getConf(), HiveConf.ConfVars.HIVE_STATS_RANGE_SELECTIVITY_UNIFORM_DISTRIBUTION); newNumRows = evaluateExpression(wcStats, pred, aspCtx, jop.getSchema().getColumnNames(), jop, wcStats.getNumRows()); // update only the basic statistics in the absence of column statistics diff --git a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java index 9a00a75b11..be527095c3 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java @@ -127,6 +127,10 @@ private static final Logger LOG = LoggerFactory.getLogger(StatsUtils.class.getName()); + // Range lower limit for date type when not defined (days, heuristic): '1999-01-01' + private static final int DATE_RANGE_LOWER_LIMIT = 10593; + // Range upper limit for date type when not defined (days, heuristic): '2024-12-31' + private static final int DATE_RANGE_UPPER_LIMIT = 20089; /** * Collect table, partition and column level statistics @@ -944,7 +948,7 @@ else if(colTypeLowerCase.equals(serdeConstants.SMALLINT_TYPE_NAME)){ } else if (colTypeLowerCase.equals(serdeConstants.DATE_TYPE_NAME)) { cs.setAvgColLen(JavaDataModel.get().lengthOfDate()); // epoch, days since epoch - cs.setRange(0, 25201); + cs.setRange(DATE_RANGE_LOWER_LIMIT, DATE_RANGE_UPPER_LIMIT); } else { cs.setAvgColLen(getSizeOfComplexTypes(conf, cinfo.getObjectInspector())); } diff --git a/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q b/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q index ec32e9c820..0fbb3855eb 100644 --- a/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q +++ b/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q @@ -1,4 +1,5 @@ --! qt:dataset:src +set hive.stats.filter.range.uniform=false; set hive.stats.column.autogather=false; set hive.strict.checks.bucketing=false; diff --git a/ql/src/test/queries/clientpositive/retry_failure_stat_changes.q b/ql/src/test/queries/clientpositive/retry_failure_stat_changes.q index 08fd4a2551..78825385ca 100644 --- a/ql/src/test/queries/clientpositive/retry_failure_stat_changes.q +++ b/ql/src/test/queries/clientpositive/retry_failure_stat_changes.q @@ -1,4 +1,5 @@ SET hive.vectorized.execution.enabled=false; +set hive.stats.filter.range.uniform=false; create table tx_n2(a int,u int); insert into tx_n2 values (1,1),(2,2),(3,3),(4,4),(5,5),(6,6),(7,7),(10,10); diff --git a/ql/src/test/queries/clientpositive/semijoin_reddedup.q b/ql/src/test/queries/clientpositive/semijoin_reddedup.q index b01e58ccd8..8e298acb67 100644 --- a/ql/src/test/queries/clientpositive/semijoin_reddedup.q +++ b/ql/src/test/queries/clientpositive/semijoin_reddedup.q @@ -20,6 +20,7 @@ set hive.stats.fetch.column.stats=true; set hive.tez.bloom.filter.factor=1.0f; set hive.auto.convert.join=false; set hive.optimize.shared.work=false; +set hive.stats.filter.range.uniform=false; create database tpch_test; diff --git a/ql/src/test/results/clientpositive/annotate_stats_filter.q.out b/ql/src/test/results/clientpositive/annotate_stats_filter.q.out index 957fd1262d..588b04caf5 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_filter.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_filter.q.out @@ -1101,14 +1101,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid < 3) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1143,14 +1143,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid > 3) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1185,14 +1185,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid <= 3) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1227,14 +1227,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid >= 3) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out index 709de139ca..18f2c6aecd 100644 --- a/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out +++ b/ql/src/test/results/clientpositive/annotate_stats_join_pkfk.q.out @@ -601,32 +601,32 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((s_company_id > 0) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: PARTIAL TableScan alias: ss filterExpr: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 7676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 6724 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 1240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -635,10 +635,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 90 Data size: 360 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 90 Data size: 360 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -763,16 +763,16 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 7676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 6724 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 1240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -781,10 +781,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1181,16 +1181,16 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 7676 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_quantity > 10) and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 321 Data size: 2468 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 6724 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 1240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3380 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s filterExpr: s_store_sk is not null (type: boolean) @@ -1215,7 +1215,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 321 Data size: 2524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 6884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1231,7 +1231,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 321 Data size: 2524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 6884 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: s1 @@ -1257,14 +1257,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 321 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 876 Data size: 3504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out index 57a78e0885..425b92074d 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out @@ -664,11 +664,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -765,11 +765,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -888,11 +888,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1001,11 +1001,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1291,11 +1291,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1384,11 +1384,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1495,11 +1495,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out index 058d4ed68a..4c000f8864 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out @@ -55,19 +55,19 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 97660 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 342 Data size: 32490 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 23560 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan alias: x1 @@ -75,35 +75,35 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 101772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 19602 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c3 (type: string) outputColumnNames: c1, c3 - Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 19602 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 223 Data size: 22969 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 342 Data size: 35226 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 25544 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -111,11 +111,11 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -127,9 +127,9 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 342 Data size: 35226 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 25544 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -137,11 +137,11 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -156,16 +156,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: bigint), _col5 (type: bigint) sort order: ++++++ - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out index 506fbe1365..73d345096e 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out @@ -56,19 +56,19 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c1 > 100)) (type: boolean) - Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -77,7 +77,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -93,14 +93,14 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -110,14 +110,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 34 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 34 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 34 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -132,19 +132,19 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 > 100) and (c2 < 120)) (type: boolean) - Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c2 (type: int) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -153,7 +153,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -228,19 +228,19 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c1 > 100)) (type: boolean) - Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x1 @@ -248,31 +248,31 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 > 100) and (c2 < 120)) (type: boolean) - Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c2 (type: int) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 68 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 118 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 68 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 118 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -280,14 +280,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1557 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1557 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1557 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -297,9 +297,9 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 59 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 68 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 118 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -307,14 +307,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1557 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1557 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 129 Data size: 1557 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -389,19 +389,19 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 97660 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 342 Data size: 32490 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 23560 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -410,7 +410,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -426,14 +426,14 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -443,14 +443,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 94 Data size: 19364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 163 Data size: 33578 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 94 Data size: 19364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 163 Data size: 33578 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 94 Data size: 19364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 163 Data size: 33578 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -465,23 +465,23 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 101772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 19602 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c3 (type: string) outputColumnNames: c1, c3 - Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 19602 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -490,7 +490,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -565,19 +565,19 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 97660 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 342 Data size: 32490 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 23560 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan alias: x1 @@ -585,35 +585,35 @@ STAGE PLANS: Statistics: Num rows: 1028 Data size: 101772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 19602 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c3 (type: string) outputColumnNames: c1, c3 - Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 198 Data size: 19602 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 10197 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 223 Data size: 22969 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 342 Data size: 35226 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 25544 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -621,14 +621,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -638,9 +638,9 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 124 Data size: 12772 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 342 Data size: 35226 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 248 Data size: 25544 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -648,14 +648,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 376 Data size: 38748 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 272 Data size: 28098 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/folder_predicate.q.out b/ql/src/test/results/clientpositive/folder_predicate.q.out index 5fe3341ef9..b4c4724a24 100644 --- a/ql/src/test/results/clientpositive/folder_predicate.q.out +++ b/ql/src/test/results/clientpositive/folder_predicate.q.out @@ -100,14 +100,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value is null or (value < 3)) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -155,14 +155,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value is null or (value > 3)) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -210,14 +210,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value is null or (value <= 3)) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -266,14 +266,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value is null or (value >= 3)) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -376,14 +376,14 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value is null or (value <= 1) or (value > 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out b/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out index bbb0d6d1b4..83341282a1 100644 --- a/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out @@ -24,11 +24,11 @@ STAGE PLANS: Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_discount BETWEEN 0.05D AND 0.07D (type: boolean) - Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 35 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_extendedprice (type: double) outputColumnNames: l_extendedprice - Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 35 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(l_extendedprice) minReductionHashAggr: 0.99 @@ -97,11 +97,11 @@ STAGE PLANS: Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_discount BETWEEN 0.05D AND 0.07D (type: boolean) - Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 35 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_extendedprice (type: double) outputColumnNames: l_extendedprice - Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 35 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(l_extendedprice) minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/join_merging.q.out b/ql/src/test/results/clientpositive/join_merging.q.out index af840a8f4f..6fd4052dea 100644 --- a/ql/src/test/results/clientpositive/join_merging.q.out +++ b/ql/src/test/results/clientpositive/join_merging.q.out @@ -44,16 +44,16 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_size > 10) and p_partkey is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_size (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -63,11 +63,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 252 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 252 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -95,7 +95,7 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 252 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int) Reduce Operator Tree: Join Operator @@ -105,14 +105,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col3 - Statistics: Num rows: 34 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 34 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 34 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -170,16 +170,16 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_size > 10) and p_partkey is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_size (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -189,14 +189,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 8 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col4 > _col2) (type: boolean) - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -224,7 +224,7 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int) Reduce Operator Tree: Join Operator @@ -234,14 +234,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col3 - Statistics: Num rows: 28 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 33 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 33 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 28 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 33 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out b/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out index 4225b7e9d5..362f3720af 100644 --- a/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out +++ b/ql/src/test/results/clientpositive/llap/acid_vectorization_original.q.out @@ -436,15 +436,15 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 41920 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t < 100Y) and (b = 4294967363L)) (type: boolean) - Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: may be used (ACID table) Reducer 2 @@ -453,10 +453,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -510,15 +510,15 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 41920 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t < 100Y) and (b = 4294967363L)) (type: boolean) - Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ROW__ID (type: struct), t (type: tinyint), si (type: smallint), i (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint), _col2 (type: smallint), _col3 (type: int) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -528,10 +528,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -587,16 +587,16 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 706986 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((b = 4294967363L) and (t < 100Y)) (type: boolean) - Statistics: Num rows: 2 Data size: 674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2022 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ROW__ID (type: struct), t (type: tinyint), si (type: smallint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) outputColumnNames: _col0, _col1, _col2, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint), _col2 (type: smallint), _col5 (type: float), _col6 (type: double), _col7 (type: boolean), _col8 (type: string), _col9 (type: timestamp), _col10 (type: decimal(4,2)), _col11 (type: binary) Execution mode: vectorized, llap LLAP IO: may be used (ACID table) @@ -606,10 +606,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), 0 (type: int), 4294967363L (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: boolean), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: decimal(4,2)), VALUE._col9 (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out index 184a21ee4b..650d2cc4b9 100644 --- a/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_smb_mapjoin_14.q.out @@ -588,11 +588,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -600,21 +600,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -714,11 +714,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -726,21 +726,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -862,11 +862,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -874,21 +874,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1000,11 +1000,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1012,21 +1012,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.9230769 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1246,11 +1246,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1258,21 +1258,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1365,11 +1365,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1377,11 +1377,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1389,12 +1389,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -1404,16 +1404,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1425,10 +1425,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.8333333 + minReductionHashAggr: 0.9166667 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1535,11 +1535,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1547,21 +1547,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out index 7c95815758..629a8f389a 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out @@ -91,16 +91,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -111,16 +111,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 6 @@ -131,16 +131,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 3 @@ -152,10 +152,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.8888889 + minReductionHashAggr: 0.94736844 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -256,11 +256,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -268,22 +268,22 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int) mode: final outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.85714287 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out index ed16aefbb3..fe21b2d0b9 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_9.q.out @@ -714,11 +714,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -726,21 +726,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -840,11 +840,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -852,21 +852,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -988,11 +988,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1000,21 +1000,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1126,11 +1126,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1138,21 +1138,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.9230769 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1372,11 +1372,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1384,21 +1384,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1482,11 +1482,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1494,21 +1494,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1603,11 +1603,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1615,11 +1615,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1627,12 +1627,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -1642,16 +1642,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1663,10 +1663,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.8333333 + minReductionHashAggr: 0.9166667 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1773,11 +1773,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1785,21 +1785,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2537,11 +2537,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -2549,21 +2549,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2663,11 +2663,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -2675,21 +2675,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2811,11 +2811,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -2823,21 +2823,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2949,11 +2949,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -2961,21 +2961,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.9230769 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3061,11 +3061,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -3073,21 +3073,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3171,11 +3171,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -3183,21 +3183,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3292,11 +3292,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -3304,11 +3304,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -3316,12 +3316,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -3331,16 +3331,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -3352,10 +3352,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.8333333 + minReductionHashAggr: 0.9166667 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3462,11 +3462,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -3474,21 +3474,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/colstats_date_min_max.q.out b/ql/src/test/results/clientpositive/llap/colstats_date_min_max.q.out index fd5e563791..ef65a73540 100644 --- a/ql/src/test/results/clientpositive/llap/colstats_date_min_max.q.out +++ b/ql/src/test/results/clientpositive/llap/colstats_date_min_max.q.out @@ -162,8 +162,8 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_12] Group By Operator [GBY_11] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_10] (rows=3 width=56) - Filter Operator [FIL_9] (rows=3 width=56) + Select Operator [SEL_10] (rows=2 width=56) + Filter Operator [FIL_9] (rows=2 width=56) predicate:(d < DATE'2010-10-03') TableScan [TS_0] (rows=10 width=56) default@d1,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d"] diff --git a/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out b/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out index 7e7933cbfb..3c45a0d6a5 100644 --- a/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out +++ b/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out @@ -1104,16 +1104,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value1 > 2.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1126,10 +1126,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1195,16 +1195,16 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value1 > 2.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1217,19 +1217,19 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1239,14 +1239,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out index 05819ef46a..064837efc0 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out @@ -4173,19 +4173,19 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 27Y) or t is null) (type: boolean) - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), 'foo' (type: string), _col4 (type: tinyint) outputColumnNames: si, i, b, f, ds, t - Statistics: Num rows: 352 Data size: 39072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 89236 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(si, 'hll'), compute_stats(i, 'hll'), compute_stats(b, 'hll'), compute_stats(f, 'hll') keys: ds (type: string), t (type: tinyint) - minReductionHashAggr: 0.6363636 + minReductionHashAggr: 0.840796 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 129 Data size: 230523 Basic stats: COMPLETE Column stats: COMPLETE @@ -4199,7 +4199,7 @@ STAGE PLANS: key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Execution mode: llap LLAP IO: no inputs @@ -4232,7 +4232,7 @@ STAGE PLANS: File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4431,14 +4431,14 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 27Y) or t is null) (type: boolean) - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4447,11 +4447,11 @@ STAGE PLANS: Select Operator expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), 'foo' (type: string), _col4 (type: tinyint) outputColumnNames: si, i, b, f, ds, t - Statistics: Num rows: 352 Data size: 39072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 89236 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(si, 'hll'), compute_stats(i, 'hll'), compute_stats(b, 'hll'), compute_stats(f, 'hll') keys: ds (type: string), t (type: tinyint) - minReductionHashAggr: 0.6363636 + minReductionHashAggr: 0.840796 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 129 Data size: 230523 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out index c6f3852c92..f66363ad42 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization2.q.out @@ -1224,18 +1224,18 @@ STAGE PLANS: Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: ss_sold_date_sk (type: int), ss_net_paid_inc_tax (type: float), ss_net_profit (type: float) minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE 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: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -1245,14 +1245,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: float), KEY._col2 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: float), _col2 (type: float), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1261,20 +1261,20 @@ STAGE PLANS: Select Operator expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) outputColumnNames: ss_net_paid_inc_tax, ss_net_profit, ss_sold_date_sk - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ss_net_paid_inc_tax, 'hll'), compute_stats(ss_net_profit, 'hll') keys: ss_sold_date_sk (type: int) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1704 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1704 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1493,16 +1493,16 @@ STAGE PLANS: Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sold_date_sk >= 2452617) and (ss_sold_date_sk <= 2452638)) (type: boolean) - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE 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: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1512,10 +1512,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: float), VALUE._col1 (type: float), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1524,20 +1524,20 @@ STAGE PLANS: Select Operator expressions: _col0 (type: float), _col1 (type: float), _col2 (type: int) outputColumnNames: ss_net_paid_inc_tax, ss_net_profit, ss_sold_date_sk - Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ss_net_paid_inc_tax, 'hll'), compute_stats(ss_net_profit, 'hll') keys: ss_sold_date_sk (type: int) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1704 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 1704 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 6da07d4642..0dc5b513b6 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -2704,16 +2704,16 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_24] - Select Operator [SEL_23] (rows=41 width=223) + Select Operator [SEL_23] (rows=33 width=223) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_22] (rows=41 width=229) + Filter Operator [FIL_22] (rows=33 width=227) predicate:((_col7 is null or (_col4 = 0L) or _col4 is null) and ((_col5 < _col4) is not true or (_col4 = 0L) or _col4 is null or _col7 is not null or _col0 is null) and (_col0 is not null or (_col4 = 0L) or _col4 is null or _col7 is not null)) - Merge Join Operator [MERGEJOIN_45] (rows=41 width=229) + Merge Join Operator [MERGEJOIN_45] (rows=33 width=227) Conds:RS_19._col0, _col1=RS_20._col0, _col2(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col7"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_19] PartitionCols:_col0, _col1 - Merge Join Operator [MERGEJOIN_44] (rows=36 width=227) + Merge Join Operator [MERGEJOIN_44] (rows=31 width=226) Conds:RS_16._col1=RS_17._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_16] @@ -2725,33 +2725,33 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] llap SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_7] (rows=2 width=114) + Group By Operator [GBY_7] (rows=1 width=114) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] PartitionCols:_col0 - Group By Operator [GBY_5] (rows=2 width=114) + Group By Operator [GBY_5] (rows=1 width=114) Output:["_col0","_col1","_col2"],aggregations:["count()","count(p_name)"],keys:p_mfgr - Select Operator [SEL_4] (rows=8 width=223) + Select Operator [SEL_4] (rows=5 width=223) Output:["p_name","p_mfgr"] - Filter Operator [FIL_27] (rows=8 width=223) + Filter Operator [FIL_27] (rows=5 width=223) predicate:((p_size < 10) and p_mfgr is not null) Please refer to the previous TableScan [TS_0] <-Reducer 5 [SIMPLE_EDGE] llap SHUFFLE [RS_20] PartitionCols:_col0, _col2 - Select Operator [SEL_15] (rows=4 width=223) + Select Operator [SEL_15] (rows=2 width=223) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_14] (rows=4 width=219) + Group By Operator [GBY_14] (rows=2 width=219) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_13] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=4 width=219) + Group By Operator [GBY_12] (rows=2 width=219) Output:["_col0","_col1"],keys:p_name, p_mfgr - Select Operator [SEL_11] (rows=8 width=223) + Select Operator [SEL_11] (rows=5 width=223) Output:["p_name","p_mfgr"] - Filter Operator [FIL_28] (rows=8 width=223) + Filter Operator [FIL_28] (rows=5 width=223) predicate:((p_size < 10) and p_mfgr is not null and p_name is not null) Please refer to the previous TableScan [TS_0] @@ -2813,7 +2813,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_6] Group By Operator [GBY_5] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(p_size)","count(p_size)"] - Filter Operator [FIL_37] (rows=8 width=4) + Filter Operator [FIL_37] (rows=5 width=4) predicate:(p_size < 10) TableScan [TS_2] (rows=26 width=4) default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_size"] diff --git a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out index f216d64598..e91926626f 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out @@ -30,27 +30,27 @@ Stage-0 Stage-1 Reducer 3 vectorized, llap File Output Operator [FS_35] - Select Operator [SEL_34] (rows=2048 width=552) + Select Operator [SEL_34] (rows=4626 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_27] (rows=2048 width=552) + Merge Join Operator [MERGEJOIN_27] (rows=4626 width=552) Conds:RS_30._col2=RS_33._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_30] PartitionCols:_col2 - Select Operator [SEL_29] (rows=1365 width=251) + Select Operator [SEL_29] (rows=3078 width=251) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_28] (rows=1365 width=251) + Filter Operator [FIL_28] (rows=3078 width=251) predicate:cint BETWEEN 1000000 AND 3000000 TableScan [TS_0] (rows=12288 width=251) default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] <-Map 4 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_33] PartitionCols:_col2 - Select Operator [SEL_32] (rows=1019 width=251) + Select Operator [SEL_32] (rows=2298 width=251) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_31] (rows=1019 width=251) + Filter Operator [FIL_31] (rows=2298 width=251) predicate:(cint BETWEEN 1000000 AND 3000000 and cbigint is not null) TableScan [TS_3] (rows=12288 width=251) default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] @@ -119,23 +119,23 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_11] Group By Operator [GBY_10] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_29] (rows=2048 width=8) + Merge Join Operator [MERGEJOIN_29] (rows=4626 width=8) Conds:RS_32._col0=RS_35._col0(Inner) <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_32] PartitionCols:_col0 - Select Operator [SEL_31] (rows=1365 width=2) + Select Operator [SEL_31] (rows=3078 width=2) Output:["_col0"] - Filter Operator [FIL_30] (rows=1365 width=2) + Filter Operator [FIL_30] (rows=3078 width=2) predicate:cint BETWEEN 1000000 AND 3000000 TableScan [TS_0] (rows=12288 width=2) default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["cint"] <-Map 4 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_35] PartitionCols:_col0 - Select Operator [SEL_34] (rows=1019 width=2) + Select Operator [SEL_34] (rows=2298 width=2) Output:["_col0"] - Filter Operator [FIL_33] (rows=1019 width=8) + Filter Operator [FIL_33] (rows=2298 width=8) predicate:(cint BETWEEN 1000000 AND 3000000 and cbigint is not null) TableScan [TS_3] (rows=12288 width=8) default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["cint","cbigint"] @@ -192,34 +192,34 @@ Stage-0 Stage-1 Reducer 4 vectorized, llap File Output Operator [FS_41] - Select Operator [SEL_40] (rows=1024 width=11) + Select Operator [SEL_40] (rows=2313 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_39] - Group By Operator [GBY_38] (rows=1024 width=11) + Group By Operator [GBY_38] (rows=2313 width=11) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=1024 width=11) + Group By Operator [GBY_10] (rows=2313 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_31] (rows=2048 width=3) + Merge Join Operator [MERGEJOIN_31] (rows=4626 width=3) Conds:RS_34._col1=RS_37._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_34] PartitionCols:_col1 - Select Operator [SEL_33] (rows=1365 width=5) + Select Operator [SEL_33] (rows=3078 width=5) Output:["_col0","_col1"] - Filter Operator [FIL_32] (rows=1365 width=5) + Filter Operator [FIL_32] (rows=3078 width=5) predicate:cint BETWEEN 1000000 AND 3000000 TableScan [TS_0] (rows=12288 width=5) default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["csmallint","cint"] <-Map 5 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_37] PartitionCols:_col0 - Select Operator [SEL_36] (rows=1019 width=2) + Select Operator [SEL_36] (rows=2298 width=2) Output:["_col0"] - Filter Operator [FIL_35] (rows=1019 width=8) + Filter Operator [FIL_35] (rows=2298 width=8) predicate:(cint BETWEEN 1000000 AND 3000000 and cbigint is not null) TableScan [TS_3] (rows=12288 width=8) default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["cint","cbigint"] diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out index 587123c81d..51b8999c15 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out @@ -70,22 +70,22 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 1030 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c > 20) (type: boolean) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1030 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: varchar(256)) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1030 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: a (type: int), b (type: varchar(256)) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.6 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: varchar(256)) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: varchar(256)) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -95,14 +95,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: varchar(256)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: varchar(256)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -166,22 +166,22 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 1030 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c > 20) (type: boolean) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1030 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: varchar(256)) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1030 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: a (type: int), b (type: varchar(256)) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.6 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: varchar(256)) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: varchar(256)) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -191,14 +191,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: varchar(256)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: varchar(256)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,14 +264,14 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c > 20) (type: boolean) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: varchar(256)) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: a (type: int), b (type: varchar(256)) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.6666666 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out index 4a58aee647..7f1ec5650d 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out @@ -182,16 +182,16 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((empid < 120) and deptno is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: varchar(256)), _col3 (type: float), _col4 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -222,14 +222,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: int), _col0 (type: int), _col2 (type: varchar(256)), _col3 (type: float), _col4 (type: int), _col6 (type: varchar(256)), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -465,14 +465,14 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid > 120) (type: boolean) - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -487,14 +487,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid < 150) (type: boolean) - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out index 7d5493e7d9..71d44a488a 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out @@ -190,16 +190,16 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid < 120) (type: boolean) - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), name (type: varchar(256)), salary (type: float), commission (type: int), deptno (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int) sort order: + Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: varchar(256)), _col2 (type: float), _col3 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -246,14 +246,14 @@ STAGE PLANS: 0 _col4 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: int), _col0 (type: int), _col1 (type: varchar(256)), _col2 (type: float), _col3 (type: int), _col6 (type: varchar(256)), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -513,14 +513,14 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid > 120) (type: boolean) - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -535,14 +535,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid < 150) (type: boolean) - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out index 3c51db6489..22e88fda69 100644 --- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out +++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out @@ -190,16 +190,16 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid < 120) (type: boolean) - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), name (type: varchar(256)), salary (type: float), commission (type: int), deptno (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int) sort order: + Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: varchar(256)), _col2 (type: float), _col3 (type: int) Execution mode: llap LLAP IO: all inputs @@ -246,14 +246,14 @@ STAGE PLANS: 0 _col4 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: int), _col0 (type: int), _col1 (type: varchar(256)), _col2 (type: float), _col3 (type: int), _col6 (type: varchar(256)), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 594 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -442,14 +442,14 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid > 120) (type: boolean) - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -464,14 +464,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (empid < 150) (type: boolean) - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: empid (type: int), deptno (type: int), name (type: varchar(256)), salary (type: float), commission (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/orc_llap.q.out b/ql/src/test/results/clientpositive/llap/orc_llap.q.out index b9c5b06025..0ad9682eb8 100644 --- a/ql/src/test/results/clientpositive/llap/orc_llap.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_llap.q.out @@ -269,11 +269,11 @@ STAGE PLANS: Statistics: Num rows: 122880 Data size: 1467736 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 10) and cbigint is not null) (type: boolean) - Statistics: Num rows: 30577 Data size: 365240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 45873 Data size: 547936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(cint,csmallint,cbigint) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 30577 Data size: 365240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 45873 Data size: 547936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 @@ -347,11 +347,11 @@ STAGE PLANS: Statistics: Num rows: 122880 Data size: 30929630 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 10) and cbigint is not null) (type: boolean) - Statistics: Num rows: 30577 Data size: 7696590 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 45873 Data size: 11546630 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 30577 Data size: 7696590 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 45873 Data size: 11546630 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 @@ -425,11 +425,11 @@ STAGE PLANS: Statistics: Num rows: 122880 Data size: 9173100 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 5) and (cint < 10)) (type: boolean) - Statistics: Num rows: 13653 Data size: 1019300 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 30720 Data size: 2293300 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(cstring2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 13653 Data size: 1019300 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 30720 Data size: 2293300 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 @@ -753,11 +753,11 @@ STAGE PLANS: Statistics: Num rows: 245760 Data size: 2935456 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 10) and cbigint is not null) (type: boolean) - Statistics: Num rows: 61153 Data size: 730452 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 91747 Data size: 1095872 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(cint,csmallint,cbigint) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 61153 Data size: 730452 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 91747 Data size: 1095872 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 @@ -831,11 +831,11 @@ STAGE PLANS: Statistics: Num rows: 245760 Data size: 61859030 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 10) and cbigint is not null) (type: boolean) - Statistics: Num rows: 61153 Data size: 15392750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 91747 Data size: 23093340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 61153 Data size: 15392750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 91747 Data size: 23093340 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 @@ -909,11 +909,11 @@ STAGE PLANS: Statistics: Num rows: 245760 Data size: 18346100 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 5) and (cint < 10)) (type: boolean) - Statistics: Num rows: 27306 Data size: 2038500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 61440 Data size: 4586600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(cstring2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27306 Data size: 2038500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 61440 Data size: 4586600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out index b210c09ace..f8cae8a33c 100644 --- a/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out @@ -338,14 +338,14 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t < 0Y) and (UDFToInteger(t) > -2)) (type: boolean) - Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) - minReductionHashAggr: 0.99 + minReductionHashAggr: 0.875 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -411,14 +411,14 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t < 0Y) and (UDFToInteger(t) > -2)) (type: boolean) - Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) - minReductionHashAggr: 0.99 + minReductionHashAggr: 0.875 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -829,15 +829,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 0Y) and (d >= 10.0D) and (d < 12.0D) and UDFToInteger(si) BETWEEN 300 AND 400 and (s like '%son') and (not (s like '%car%'))) (type: boolean) - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -848,7 +848,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -912,15 +912,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 0Y) and (d >= 10.0D) and (d < 12.0D) and UDFToInteger(si) BETWEEN 300 AND 400 and (s like '%son') and (not (s like '%car%'))) (type: boolean) - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -931,7 +931,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -1061,15 +1061,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 10Y) and (t <> 101Y) and (d >= 10) and (d < 12.0D) and (s like '%son') and (not (s like '%car%')) and (t > 0Y) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -1080,7 +1080,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -1165,15 +1165,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 10Y) and (t <> 101Y) and (d >= 10) and (d < 12.0D) and (s like '%son') and (not (s like '%car%')) and (t > 0Y) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -1184,7 +1184,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out index eff0fd6b95..9e4c6f7afc 100644 --- a/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/parquet_predicate_pushdown.q.out @@ -765,15 +765,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 0Y) and (d >= 10.0D) and (d < 12.0D) and UDFToInteger(si) BETWEEN 300 AND 400 and (s like '%son') and (not (s like '%car%'))) (type: boolean) - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -784,7 +784,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -848,15 +848,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 0Y) and (d >= 10.0D) and (d < 12.0D) and UDFToInteger(si) BETWEEN 300 AND 400 and (s like '%son') and (not (s like '%car%'))) (type: boolean) - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -867,7 +867,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 565 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 25 Data size: 2825 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -1042,15 +1042,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 10Y) and (t <> 101Y) and (d >= 10) and (d < 12.0D) and (s like '%son') and (not (s like '%car%')) and (t > 0Y) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -1061,7 +1061,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -1146,15 +1146,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 10Y) and (t <> 101Y) and (d >= 10) and (d < 12.0D) and (s like '%son') and (not (s like '%car%')) and (t > 0Y) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -1165,7 +1165,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 44 Data size: 4972 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 339 Basic stats: COMPLETE Column stats: COMPLETE @@ -1262,15 +1262,15 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 16784 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((f < 123.2) and (f > 1.92) and (f >= 9.99) and f BETWEEN 1.92 AND 123.2 and (i < 67627) and (i > 60627) and (i >= 60626) and i BETWEEN 60626 AND 67627 and (b < 4294967861L) and (b > 4294967261L) and (b >= 4294967260L) and b BETWEEN 4294967261L AND 4294967861L) (type: boolean) - Statistics: Num rows: 38 Data size: 608 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 911 Data size: 14576 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: f (type: float), i (type: int), b (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 38 Data size: 608 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 911 Data size: 14576 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float) sort order: - - Statistics: Num rows: 38 Data size: 608 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 911 Data size: 14576 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: bigint) Execution mode: llap @@ -1281,7 +1281,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), VALUE._col0 (type: int), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 38 Data size: 608 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 911 Data size: 14576 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out b/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out index 6b36584cfe..e2dcb1f14b 100644 --- a/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out +++ b/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out @@ -40,19 +40,19 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: int) - minReductionHashAggr: 0.5060241 + minReductionHashAggr: 0.6 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -64,10 +64,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -121,19 +121,19 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: int) - minReductionHashAggr: 0.5060241 + minReductionHashAggr: 0.6 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -145,10 +145,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/retry_failure_reorder.q.out b/ql/src/test/results/clientpositive/llap/retry_failure_reorder.q.out index 5c0f1d32e3..f404daafb3 100644 --- a/ql/src/test/results/clientpositive/llap/retry_failure_reorder.q.out +++ b/ql/src/test/results/clientpositive/llap/retry_failure_reorder.q.out @@ -144,23 +144,23 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_18] Group By Operator [GBY_17] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_15] (rows=114 width=12) + Select Operator [SEL_15] (rows=98 width=12) Output:["_col0"] - Merge Join Operator [MERGEJOIN_51] (rows=114 width=12) + Merge Join Operator [MERGEJOIN_51] (rows=98 width=12) Conds:RS_12._col1=RS_60._col0(Inner),Output:["_col2","_col4","_col6"] <-Map 6 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_59] (rows=16 width=8) + Select Operator [SEL_59] (rows=6 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_58] (rows=16 width=8) + Filter Operator [FIL_58] (rows=6 width=8) predicate:((w > 9) and id_uw is not null) TableScan [TS_6] (rows=50 width=8) default@tw,tw,Tbl:COMPLETE,Col:COMPLETE,Output:["id_uw","w"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_50] (rows=50 width=12) + Merge Join Operator [MERGEJOIN_50] (rows=115 width=12) Conds:RS_54._col0=RS_57._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_54] @@ -174,9 +174,9 @@ Stage-0 <-Map 5 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=10 width=8) + Select Operator [SEL_56] (rows=23 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_55] (rows=10 width=8) + Filter Operator [FIL_55] (rows=23 width=8) predicate:((v > 3) and id_uv is not null) TableScan [TS_3] (rows=30 width=8) default@tv,tv,Tbl:COMPLETE,Col:COMPLETE,Output:["id_uv","v"] @@ -285,7 +285,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_59] (runtime: rows=25 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_58] (rows=10 width=8) + Filter Operator [FIL_58] (rows=23 width=8) predicate:((v > 3) and id_uv is not null) TableScan [TS_6] (runtime: rows=30 width=8) default@tv,tv,Tbl:COMPLETE,Col:COMPLETE,Output:["id_uv","v"] @@ -308,7 +308,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_56] (runtime: rows=5 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_55] (rows=16 width=8) + Filter Operator [FIL_55] (rows=6 width=8) predicate:((w > 9) and id_uw is not null) TableScan [TS_3] (runtime: rows=50 width=8) default@tw,tw,Tbl:COMPLETE,Col:COMPLETE,Output:["id_uw","w"] @@ -429,23 +429,23 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_18] Group By Operator [GBY_17] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_15] (rows=114 width=12) + Select Operator [SEL_15] (rows=98 width=12) Output:["_col0"] - Merge Join Operator [MERGEJOIN_51] (rows=114 width=12) + Merge Join Operator [MERGEJOIN_51] (rows=98 width=12) Conds:RS_12._col1=RS_60._col0(Inner),Output:["_col2","_col4","_col6"] <-Map 6 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_59] (rows=16 width=8) + Select Operator [SEL_59] (rows=6 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_58] (rows=16 width=8) + Filter Operator [FIL_58] (rows=6 width=8) predicate:((w > 9) and id_uw is not null) TableScan [TS_6] (rows=50 width=8) default@tw,tw,Tbl:COMPLETE,Col:COMPLETE,Output:["id_uw","w"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_50] (rows=50 width=12) + Merge Join Operator [MERGEJOIN_50] (rows=115 width=12) Conds:RS_54._col0=RS_57._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_54] @@ -459,9 +459,9 @@ Stage-0 <-Map 5 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=10 width=8) + Select Operator [SEL_56] (rows=23 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_55] (rows=10 width=8) + Filter Operator [FIL_55] (rows=23 width=8) predicate:((v > 3) and id_uv is not null) TableScan [TS_3] (rows=30 width=8) default@tv,tv,Tbl:COMPLETE,Col:COMPLETE,Output:["id_uv","v"] diff --git a/ql/src/test/results/clientpositive/llap/retry_failure_stat_changes.q.out b/ql/src/test/results/clientpositive/llap/retry_failure_stat_changes.q.out index c72a512214..8ec6624ae3 100644 --- a/ql/src/test/results/clientpositive/llap/retry_failure_stat_changes.q.out +++ b/ql/src/test/results/clientpositive/llap/retry_failure_stat_changes.q.out @@ -237,42 +237,42 @@ POSTHOOK: Input: default@tx_n2 Plan optimized by CBO. Vertex dependency in root stage -Map 2 <- Map 1 (BROADCAST_EDGE) -Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Map 3 (BROADCAST_EDGE) +Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 3 llap + Reducer 2 llap File Output Operator [FS_15] Select Operator [SEL_14] (rows=1 width=4) Output:["_col0"] Group By Operator [GBY_13] (rows=1 width=8) Output:["_col0"],aggregations:["sum(VALUE._col0)"] - <-Map 2 [CUSTOM_SIMPLE_EDGE] llap + <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_12] Group By Operator [GBY_11] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_9] (rows=2 width=8) + Select Operator [SEL_9] (rows=1 width=8) Output:["_col0"] - Map Join Operator [MAPJOIN_30] (rows=2 width=8) - Conds:RS_6._col0=SEL_5._col0(Inner),Output:["_col1","_col3"] - <-Map 1 [BROADCAST_EDGE] llap - BROADCAST [RS_6] + Map Join Operator [MAPJOIN_30] (rows=1 width=8) + Conds:SEL_2._col0=RS_7._col0(Inner),Output:["_col1","_col3"] + <-Map 3 [BROADCAST_EDGE] llap + BROADCAST [RS_7] PartitionCols:_col0 - Select Operator [SEL_2] (rows=2 width=8) + Select Operator [SEL_5] (rows=1 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_18] (rows=2 width=8) - predicate:((u < 10) and a is not null) - TableScan [TS_0] (rows=8 width=8) - default@tx_n2,tx_n2,Tbl:COMPLETE,Col:COMPLETE,Output:["a","u"] - <-Select Operator [SEL_5] (rows=5 width=8) + Filter Operator [FIL_19] (rows=1 width=8) + predicate:((p > 2) and a is not null) + TableScan [TS_3] (rows=5 width=8) + default@px,px,Tbl:COMPLETE,Col:COMPLETE,Output:["a","p"] + <-Select Operator [SEL_2] (rows=2 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_19] (rows=5 width=8) - predicate:((p > 2) and a is not null) - TableScan [TS_3] (rows=5 width=8) - default@px,px,Tbl:COMPLETE,Col:COMPLETE,Output:["a","p"] + Filter Operator [FIL_18] (rows=2 width=8) + predicate:((u < 10) and a is not null) + TableScan [TS_0] (rows=8 width=8) + default@tx_n2,tx_n2,Tbl:COMPLETE,Col:COMPLETE,Output:["a","u"] PREHOOK: query: select assert_true_oom(1 > sum(u*p)) from tx_n2 join px on (tx_n2.a=px.a) where u<10 and p>2 PREHOOK: type: QUERY @@ -280,17 +280,17 @@ PREHOOK: Input: default@px PREHOOK: Input: default@tx_n2 #### A masked pattern was here #### Status: Failed -Vertex failed, vertexName=Reducer 3, vertexId=vertex_#ID#, diagnostics=[Task failed, taskId=task_#ID#, diagnostics=[TaskAttempt 0 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: org.apache.hadoop.hive.ql.exec.mapjoin.MapJoinMemoryExhaustionError: assert_true_oom: assertation failed; Simulated OOM +Vertex failed, vertexName=Reducer 2, vertexId=vertex_#ID#, diagnostics=[Task failed, taskId=task_#ID#, diagnostics=[TaskAttempt 0 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: org.apache.hadoop.hive.ql.exec.mapjoin.MapJoinMemoryExhaustionError: assert_true_oom: assertation failed; Simulated OOM #### A masked pattern was here #### ], TaskAttempt 1 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: org.apache.hadoop.hive.ql.exec.mapjoin.MapJoinMemoryExhaustionError: assert_true_oom: assertation failed; Simulated OOM #### A masked pattern was here #### -]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1 killedTasks:0, Vertex vertex_#ID# [Reducer 3] killed/failed due to:OWN_TASK_FAILURE] +]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1 killedTasks:0, Vertex vertex_#ID# [Reducer 2] killed/failed due to:OWN_TASK_FAILURE] DAG did not succeed due to VERTEX_FAILURE. failedVertices:1 killedVertices:0 -FAILED: Execution Error, return code 2 from org.apache.hadoop.hive.ql.exec.tez.TezTask. Vertex failed, vertexName=Reducer 3, vertexId=vertex_#ID#, diagnostics=[Task failed, taskId=task_#ID#, diagnostics=[TaskAttempt 0 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: org.apache.hadoop.hive.ql.exec.mapjoin.MapJoinMemoryExhaustionError: assert_true_oom: assertation failed; Simulated OOM +FAILED: Execution Error, return code 2 from org.apache.hadoop.hive.ql.exec.tez.TezTask. Vertex failed, vertexName=Reducer 2, vertexId=vertex_#ID#, diagnostics=[Task failed, taskId=task_#ID#, diagnostics=[TaskAttempt 0 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: org.apache.hadoop.hive.ql.exec.mapjoin.MapJoinMemoryExhaustionError: assert_true_oom: assertation failed; Simulated OOM #### A masked pattern was here #### ], TaskAttempt 1 failed, info=[Error: Error while running task ( failure ) : attempt_#ID#:java.lang.RuntimeException: org.apache.hadoop.hive.ql.exec.mapjoin.MapJoinMemoryExhaustionError: assert_true_oom: assertation failed; Simulated OOM #### A masked pattern was here #### -]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1 killedTasks:0, Vertex vertex_#ID# [Reducer 3] killed/failed due to:OWN_TASK_FAILURE]DAG did not succeed due to VERTEX_FAILURE. failedVertices:1 killedVertices:0 +]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1 killedTasks:0, Vertex vertex_#ID# [Reducer 2] killed/failed due to:OWN_TASK_FAILURE]DAG did not succeed due to VERTEX_FAILURE. failedVertices:1 killedVertices:0 PREHOOK: query: select assert_true_oom(2000 > sum(u*p)) from tx_n2 join px on (tx_n2.a=px.a) where u<10 and p>2 PREHOOK: type: QUERY PREHOOK: Input: default@px diff --git a/ql/src/test/results/clientpositive/llap/runtime_stats_hs2.q.out b/ql/src/test/results/clientpositive/llap/runtime_stats_hs2.q.out index df8ef0da1b..1899eff404 100644 --- a/ql/src/test/results/clientpositive/llap/runtime_stats_hs2.q.out +++ b/ql/src/test/results/clientpositive/llap/runtime_stats_hs2.q.out @@ -64,25 +64,25 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_12] Group By Operator [GBY_11] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_9] (rows=1 width=8) + Select Operator [SEL_9] (rows=4 width=8) Output:["_col0"] - Merge Join Operator [MERGEJOIN_30] (rows=1 width=8) + Merge Join Operator [MERGEJOIN_30] (rows=4 width=8) Conds:RS_33._col0=RS_36._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_33] PartitionCols:_col0 - Select Operator [SEL_32] (rows=1 width=4) + Select Operator [SEL_32] (rows=7 width=4) Output:["_col0"] - Filter Operator [FIL_31] (rows=1 width=4) + Filter Operator [FIL_31] (rows=7 width=4) predicate:((u < 10) and (u > 2)) TableScan [TS_0] (rows=8 width=4) default@tx_n3,tx_n3,Tbl:COMPLETE,Col:COMPLETE,Output:["u"] <-Map 4 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_36] PartitionCols:_col0 - Select Operator [SEL_35] (rows=1 width=4) + Select Operator [SEL_35] (rows=4 width=4) Output:["_col0"] - Filter Operator [FIL_34] (rows=1 width=4) + Filter Operator [FIL_34] (rows=4 width=4) predicate:((p > 2) and (p < 10)) TableScan [TS_3] (rows=5 width=4) default@px_n0,px_n0,Tbl:COMPLETE,Col:COMPLETE,Output:["p"] diff --git a/ql/src/test/results/clientpositive/llap/semijoin.q.out b/ql/src/test/results/clientpositive/llap/semijoin.q.out index 99ed8de40b..c33b7bb35b 100644 --- a/ql/src/test/results/clientpositive/llap/semijoin.q.out +++ b/ql/src/test/results/clientpositive/llap/semijoin.q.out @@ -518,22 +518,22 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 15) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col1 - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int), _col1 (type: int) - minReductionHashAggr: 0.28571427 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -546,25 +546,25 @@ STAGE PLANS: 0 key (type: int) 1 _col1 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -743,22 +743,22 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 5) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.57142854 + minReductionHashAggr: 0.5294118 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -788,25 +788,25 @@ STAGE PLANS: 0 key (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -862,14 +862,14 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE @@ -978,22 +978,22 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 2) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.5555556 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: no inputs Map 4 @@ -1023,21 +1023,21 @@ STAGE PLANS: 0 key (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out index 1aebec391f..ae6cd4cf5c 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out @@ -480,11 +480,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -492,21 +492,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -606,11 +606,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -618,21 +618,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -754,11 +754,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -766,21 +766,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -892,11 +892,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -904,21 +904,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.9230769 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1138,11 +1138,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1150,21 +1150,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1246,11 +1246,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1258,21 +1258,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1365,11 +1365,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1377,11 +1377,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 @@ -1389,12 +1389,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: @@ -1404,16 +1404,16 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1425,10 +1425,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.8333333 + minReductionHashAggr: 0.9166667 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1535,11 +1535,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1547,21 +1547,21 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() - minReductionHashAggr: 0.75 + minReductionHashAggr: 0.8888889 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out index 76d6400619..e1fc35fab5 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out @@ -3630,22 +3630,22 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_size < 10) and p_mfgr is not null and p_name is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 1784 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1115 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_mfgr (type: string), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1095 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.375 + minReductionHashAggr: 0.6 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 438 Basic stats: COMPLETE Column stats: COMPLETE 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: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 438 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -3658,15 +3658,15 @@ STAGE PLANS: 0 _col1 (type: string), _col0 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: _col1, _col3, _col4 - Statistics: Num rows: 4 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 650 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int) sort order: ++ - Statistics: Num rows: 4 Data size: 1300 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 650 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: vectorized, llap @@ -3674,10 +3674,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out index d48ee3d095..2ed6090caa 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out @@ -3918,14 +3918,14 @@ STAGE PLANS: Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey BETWEEN 10000 AND 20000 (type: boolean) - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_size (type: int) outputColumnNames: p_size - Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(p_size) - minReductionHashAggr: 0.875 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out index 3c7183e784..1654067562 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out @@ -359,7 +359,7 @@ STAGE PLANS: Group By Operator aggregations: count() keys: _col0 (type: smallint) - minReductionHashAggr: 0.49951172 + minReductionHashAggr: 0.4997838 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out index 9303b4d261..7b1de5793a 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out @@ -50,16 +50,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint < 100S) and UDFToInteger(csmallint) is not null) (type: boolean) - Statistics: Num rows: 3058 Data size: 769960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1161780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -102,12 +102,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -119,11 +119,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -131,10 +131,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -255,16 +255,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint < 100S) and UDFToInteger(csmallint) is not null) (type: boolean) - Statistics: Num rows: 3058 Data size: 769960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1161780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -307,12 +307,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -324,11 +324,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -336,10 +336,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -460,16 +460,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint < 100S) and UDFToInteger(csmallint) is not null) (type: boolean) - Statistics: Num rows: 3058 Data size: 769960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1161780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -512,12 +512,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -529,11 +529,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -541,10 +541,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out index 116bb11704..7bfa26fde3 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out @@ -359,7 +359,7 @@ STAGE PLANS: Group By Operator aggregations: count() keys: _col0 (type: smallint) - minReductionHashAggr: 0.49951172 + minReductionHashAggr: 0.4997838 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index 9303b4d261..7b1de5793a 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -50,16 +50,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint < 100S) and UDFToInteger(csmallint) is not null) (type: boolean) - Statistics: Num rows: 3058 Data size: 769960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1161780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -102,12 +102,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -119,11 +119,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -131,10 +131,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -255,16 +255,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint < 100S) and UDFToInteger(csmallint) is not null) (type: boolean) - Statistics: Num rows: 3058 Data size: 769960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1161780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -307,12 +307,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -324,11 +324,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -336,10 +336,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -460,16 +460,16 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint < 100S) and UDFToInteger(csmallint) is not null) (type: boolean) - Statistics: Num rows: 3058 Data size: 769960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1161780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), UDFToInteger(csmallint) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 3058 Data size: 779096 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4615 Data size: 1175564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap LLAP IO: all inputs @@ -512,12 +512,12 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int) sort order: + Map-reduce partition columns: _col12 (type: int) - Statistics: Num rows: 1083 Data size: 158946 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1084 Data size: 86954 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: llap @@ -529,11 +529,11 @@ STAGE PLANS: 0 _col12 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 4 Execution mode: vectorized, llap @@ -541,10 +541,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1713 Data size: 353010 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 282560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_between_in.q.out b/ql/src/test/results/clientpositive/llap/vector_between_in.q.out index 99c7f4483b..7b1d7a7713 100644 --- a/ql/src/test/results/clientpositive/llap/vector_between_in.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_between_in.q.out @@ -492,7 +492,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColumnBetween(col 3:date, left -2, right 1) predicate: cdate BETWEEN DATE'1969-12-30' AND DATE'1970-01-02' (type: boolean) - Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3087 Data size: 85288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdate (type: date) outputColumnNames: _col0 @@ -500,7 +500,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3087 Data size: 85288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -508,7 +508,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3087 Data size: 85288 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -536,13 +536,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3087 Data size: 85288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3087 Data size: 85288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -592,7 +592,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColumnNotBetween(col 3:date, left -610, right 608) predicate: cdate NOT BETWEEN DATE'1968-05-01' AND DATE'1971-09-01' (type: boolean) - Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 462 Data size: 12824 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdate (type: date) outputColumnNames: _col0 @@ -600,7 +600,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 462 Data size: 12824 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -608,7 +608,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 462 Data size: 12824 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -636,13 +636,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 462 Data size: 12824 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 462 Data size: 12824 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -692,7 +692,7 @@ STAGE PLANS: native: true predicateExpression: FilterDecimalColumnBetween(col 1:decimal(20,10), left -20, right 45.9918918919) predicate: cdecimal1 BETWEEN -20 AND 45.9918918919 (type: boolean) - Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdecimal1 (type: decimal(20,10)) outputColumnNames: _col0 @@ -700,7 +700,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(20,10)) sort order: + @@ -708,7 +708,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -736,13 +736,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -792,13 +792,13 @@ STAGE PLANS: native: true predicateExpression: FilterDecimalColumnNotBetween(col 1:decimal(20,10), left -2000, right 4390.1351351351) predicate: cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351 (type: boolean) - Statistics: Num rows: 10924 Data size: 913472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12259 Data size: 1025136 Basic stats: COMPLETE Column stats: COMPLETE Select Operator Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumnNums: [] - Statistics: Num rows: 10924 Data size: 913472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12259 Data size: 1025136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_expressions.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_expressions.q.out index b4fb00f31c..23639c003d 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_expressions.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_expressions.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDecimalColGreaterDecimalScalar(col 1:decimal(20,10), val 0), FilterDecimalColLessDecimalScalar(col 1:decimal(20,10), val 12345.5678), FilterDecimalColGreaterDecimalScalar(col 2:decimal(23,14), val 1000), SelectColumnIsNotNull(col 0:double), FilterDecimalColNotEqualDecimalScalar(col 2:decimal(23,14), val 0)) predicate: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 > 1000) and cdouble is not null and (cdecimal2 <> 0)) (type: boolean) - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(26,14)), ((cdecimal1 + 2.34) / cdecimal2) (type: decimal(38,13)), (cdecimal1 * (cdecimal2 / 3.4)) (type: decimal(38,17)), (cdecimal1 % 10) (type: decimal(12,10)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), CAST( cdecimal2 AS STRING) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -82,7 +82,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] selectExpressions: DecimalColAddDecimalColumn(col 1:decimal(20,10), col 2:decimal(23,14)) -> 4:decimal(25,14), DecimalColSubtractDecimalColumn(col 1:decimal(20,10), col 5:decimal(25,14))(children: DecimalScalarMultiplyDecimalColumn(val 2, col 2:decimal(23,14)) -> 5:decimal(25,14)) -> 6:decimal(26,14), DecimalColDivideDecimalColumn(col 7:decimal(21,10), col 2:decimal(23,14))(children: DecimalColAddDecimalScalar(col 1:decimal(20,10), val 2.34) -> 7:decimal(21,10)) -> 8:decimal(38,13), DecimalColMultiplyDecimalColumn(col 1:decimal(20,10), col 9:decimal(27,17))(children: DecimalColDivideDecimalScalar(col 2:decimal(23,14), val 3.4) -> 9:decimal(27,17)) -> 10:decimal(38,17), DecimalColModuloDecimalScalar(col 1:decimal(20,10), val 10) -> 11:decimal(12,10), CastDecimalToLong(col 1:decimal(20,10)) -> 12:int, CastDecimalToLong(col 2:decimal(23,14)) -> 13:smallint, CastDecimalToLong(col 2:decimal(23,14)) -> 14:tinyint, CastDecimalToLong(col 1:decimal(20,10)) -> 15:bigint, CastDecimalToBoolean(col 1:decimal(20,10)) -> 16:boolean, CastDecimalToDouble(col 2:decimal(23,14)) -> 17:double, CastDecimalToFloat(col 1:decimal(20,10)) -> 18:float, CastDecimalToString(col 2:decimal(23,14)) -> 19:string, CastDecimalToTimestamp(col 1:decimal(20,10)) -> 20:timestamp - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(25,14)), _col1 (type: decimal(26,14)), _col2 (type: decimal(38,13)), _col3 (type: decimal(38,17)), _col4 (type: decimal(12,10)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) sort order: ++++++++++++++ @@ -91,7 +91,7 @@ STAGE PLANS: keyColumns: 4:decimal(25,14), 6:decimal(26,14), 8:decimal(38,13), 10:decimal(38,17), 11:decimal(12,10), 12:int, 13:smallint, 14:tinyint, 15:bigint, 16:boolean, 17:double, 18:float, 19:string, 20:timestamp native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -133,19 +133,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -250,7 +250,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDecimal64ColGreaterDecimal64Scalar(col 1:decimal(10,3)/DECIMAL_64, val 0), FilterDecimalColLessDecimalScalar(col 4:decimal(10,3), val 12345.5678)(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)), FilterDecimal64ColGreaterDecimal64Scalar(col 2:decimal(7,2)/DECIMAL_64, val 100000), SelectColumnIsNotNull(col 0:double), FilterDecimal64ColNotEqualDecimal64Scalar(col 2:decimal(7,2)/DECIMAL_64, val 0)) predicate: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 > 1000) and cdouble is not null and (cdecimal2 <> 0)) (type: boolean) - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(11,3)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(11,3)), ((cdecimal1 + 2.34) / cdecimal2) (type: decimal(21,11)), (cdecimal1 * (cdecimal2 / 3.4)) (type: decimal(23,9)), (cdecimal1 % 10) (type: decimal(5,3)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), CAST( cdecimal2 AS STRING) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -259,7 +259,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [7, 11, 14, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36, 38] selectExpressions: DecimalColAddDecimalColumn(col 5:decimal(10,3), col 6:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 5:decimal(10,3), ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 6:decimal(7,2)) -> 7:decimal(11,3), DecimalColSubtractDecimalColumn(col 8:decimal(10,3), col 10:decimal(9,2))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 8:decimal(10,3), DecimalScalarMultiplyDecimalColumn(val 2, col 9:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 9:decimal(7,2)) -> 10:decimal(9,2)) -> 11:decimal(11,3), DecimalColDivideDecimalColumn(col 39:decimal(11,3), col 13:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 12:decimal(11,3)/DECIMAL_64)(children: Decimal64ColAddDecimal64Scalar(col 1:decimal(10,3)/DECIMAL_64, decimal64Val 2340, decimalVal 2.34) -> 12:decimal(11,3)/DECIMAL_64) -> 39:decimal(11,3), ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 13:decimal(7,2)) -> 14:decimal(21,11), DecimalColMultiplyDecimalColumn(col 15:decimal(10,3), col 17:decimal(12,6))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 15:decimal(10,3), DecimalColDivideDecimalScalar(col 16:decimal(7,2), val 3.4)(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 16:decimal(7,2)) -> 17:decimal(12,6)) -> 18:decimal(23,9), DecimalColModuloDecimalScalar(col 19:decimal(10,3), val 10)(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 19:decimal(10,3)) -> 20:decimal(5,3), CastDecimalToLong(col 21:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 21:decimal(10,3)) -> 22:int, CastDecimalToLong(col 23:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 23:decimal(7,2)) -> 24:smallint, CastDecimalToLong(col 25:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 25:decimal(7,2)) -> 26:tinyint, CastDecimalToLong(col 27:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 27:decimal(10,3)) -> 28:bigint, CastDecimalToBoolean(col 29:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 29:decimal(10,3)) -> 30:boolean, CastDecimalToDouble(col 31:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 31:decimal(7,2)) -> 32:double, CastDecimalToFloat(col 33:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 33:decimal(10,3)) -> 34:float, CastDecimalToString(col 35:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 35:decimal(7,2)) -> 36:string, CastDecimalToTimestamp(col 37:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 37:decimal(10,3)) -> 38:timestamp - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(11,3)), _col1 (type: decimal(11,3)), _col2 (type: decimal(21,11)), _col3 (type: decimal(23,9)), _col4 (type: decimal(5,3)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) sort order: ++++++++++++++ @@ -268,7 +268,7 @@ STAGE PLANS: keyColumns: 7:decimal(11,3), 11:decimal(11,3), 14:decimal(21,11), 18:decimal(23,9), 20:decimal(5,3), 22:int, 24:smallint, 26:tinyint, 28:bigint, 30:boolean, 32:double, 34:float, 36:string, 38:timestamp native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -310,19 +310,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_elt.q.out b/ql/src/test/results/clientpositive/llap/vector_elt.q.out index 9da99a6367..39c1fcc7e6 100644 --- a/ql/src/test/results/clientpositive/llap/vector_elt.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_elt.q.out @@ -37,7 +37,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:tinyint, val 0) predicate: (ctinyint > 0Y) (type: boolean) - Statistics: Num rows: 4096 Data size: 312018 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6046 Data size: 460522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -46,7 +46,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [14, 6, 2, 18] selectExpressions: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 14:int, VectorElt(columns [16, 6, 17])(children: LongColAddLongScalar(col 15:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 15:int) -> 16:int, col 6:string, CastLongToString(col 2:int) -> 17:string) -> 18:string - Statistics: Num rows: 4096 Data size: 1069830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6046 Data size: 1579114 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vector_inner_join.q.out b/ql/src/test/results/clientpositive/llap/vector_inner_join.q.out index 5db54ea720..68a0542729 100644 --- a/ql/src/test/results/clientpositive/llap/vector_inner_join.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_inner_join.q.out @@ -75,7 +75,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int) outputColumnNames: _col0 @@ -83,7 +83,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -102,7 +102,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 @@ -110,13 +110,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -153,7 +153,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) outputColumnNames: _col0 @@ -161,7 +161,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -171,7 +171,7 @@ STAGE PLANS: keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -250,7 +250,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int) outputColumnNames: _col0 @@ -258,7 +258,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 @@ -321,7 +321,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) outputColumnNames: _col0 @@ -329,7 +329,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -339,7 +339,7 @@ STAGE PLANS: vectorProcessingMode: HASH projectedOutputColumnNums: [] keys: _col0 (type: int) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE @@ -467,7 +467,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int) outputColumnNames: _col0 @@ -475,7 +475,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -495,7 +495,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 2 - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1 @@ -503,13 +503,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3, 0] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -546,7 +546,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 @@ -554,7 +554,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -565,7 +565,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -645,7 +645,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 @@ -653,7 +653,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -664,7 +664,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -698,7 +698,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string) outputColumnNames: _col0, _col1 @@ -706,7 +706,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -727,13 +727,13 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -816,7 +816,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string), (c * 5) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -825,7 +825,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 3] selectExpressions: LongColMultiplyLongScalar(col 0:int, val 5) -> 3:int - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -846,7 +846,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col5 input vertices: 1 Map 2 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col5 (type: int), _col2 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -854,13 +854,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [4, 5, 3, 1] - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -897,7 +897,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int), (a * 2) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -906,7 +906,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 3] selectExpressions: LongColMultiplyLongScalar(col 1:int, val 2) -> 3:int - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -917,7 +917,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string, 3:int - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -997,7 +997,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string) outputColumnNames: _col0, _col1 @@ -1005,7 +1005,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1026,7 +1026,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -1034,13 +1034,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3, 1, 0] - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1077,7 +1077,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 @@ -1085,7 +1085,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -1096,7 +1096,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1176,7 +1176,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string) outputColumnNames: _col0, _col1 @@ -1184,7 +1184,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1205,7 +1205,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Map 2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -1213,13 +1213,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 3, 1] - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1256,7 +1256,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 @@ -1264,7 +1264,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -1275,7 +1275,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1355,7 +1355,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 @@ -1363,7 +1363,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -1374,7 +1374,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1408,7 +1408,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string) outputColumnNames: _col0, _col1 @@ -1416,7 +1416,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1437,7 +1437,7 @@ STAGE PLANS: outputColumnNames: _col0, _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -1445,13 +1445,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3, 1, 0] - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1534,7 +1534,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 1:int, val 2) predicate: (a > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 @@ -1542,7 +1542,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -1553,7 +1553,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 0:string - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs @@ -1587,7 +1587,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 2) predicate: (c > 2) (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string) outputColumnNames: _col0, _col1 @@ -1595,7 +1595,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1616,7 +1616,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -1624,13 +1624,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 3, 1] - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out index 6d6b0f0fd6..bc533891cd 100644 --- a/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out @@ -522,15 +522,15 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 3 @@ -541,22 +541,22 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 15) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col1 - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int), _col1 (type: int) - minReductionHashAggr: 0.28571427 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 2 @@ -565,10 +565,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -752,22 +752,22 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 5) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.57142854 + minReductionHashAggr: 0.5294118 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 2 @@ -788,15 +788,15 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 3 @@ -805,10 +805,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -870,14 +870,14 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE @@ -985,22 +985,22 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 2) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.5555556 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 2 @@ -1021,11 +1021,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 3 @@ -1034,10 +1034,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3630,16 +3630,16 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 3 @@ -3650,22 +3650,22 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 15) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col1 - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int), _col1 (type: int) - minReductionHashAggr: 0.28571427 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 2 @@ -3674,10 +3674,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3862,22 +3862,22 @@ STAGE PLANS: Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 5) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.57142854 + minReductionHashAggr: 0.5294118 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 2 @@ -3898,16 +3898,16 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 3 @@ -3916,10 +3916,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3981,14 +3981,14 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE @@ -4097,22 +4097,22 @@ STAGE PLANS: Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 2) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.5555556 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Map 2 @@ -4133,12 +4133,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 3 @@ -4147,10 +4147,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -9791,7 +9791,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Select Operator expressions: _col1 (type: string) @@ -9799,7 +9799,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -9807,7 +9807,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -9832,14 +9832,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key < 15) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col1 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -9847,10 +9847,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col1 (type: int), _col1 (type: int) - minReductionHashAggr: 0.28571427 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -9859,7 +9859,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -9886,13 +9886,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -10144,14 +10144,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key > 5) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -10159,10 +10159,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int) - minReductionHashAggr: 0.57142854 + minReductionHashAggr: 0.5294118 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -10171,7 +10171,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -10212,7 +10212,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Select Operator expressions: _col1 (type: string) @@ -10220,7 +10220,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -10228,7 +10228,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -10255,13 +10255,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -10328,14 +10328,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -10343,7 +10343,7 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE @@ -10509,14 +10509,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key > 2) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -10524,10 +10524,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.5555556 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -10536,7 +10536,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -10577,7 +10577,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) @@ -10586,7 +10586,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -10613,13 +10613,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -14232,14 +14232,14 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -14247,7 +14247,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -14272,14 +14272,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key < 15) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col1 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -14287,10 +14287,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col1 (type: int), _col1 (type: int) - minReductionHashAggr: 0.28571427 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -14299,7 +14299,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -14326,13 +14326,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -14581,14 +14581,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key > 5) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -14596,10 +14596,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int) - minReductionHashAggr: 0.57142854 + minReductionHashAggr: 0.5294118 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -14608,7 +14608,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -14647,14 +14647,14 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -14662,7 +14662,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -14689,13 +14689,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -14762,14 +14762,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -14777,7 +14777,7 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE @@ -14940,14 +14940,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key > 2) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -14955,10 +14955,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.5555556 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -14967,7 +14967,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -15006,7 +15006,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -15014,7 +15014,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -15041,13 +15041,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -18613,7 +18613,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 3 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Select Operator expressions: _col1 (type: string) @@ -18621,7 +18621,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -18629,7 +18629,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -18654,14 +18654,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key < 15) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col1 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -18669,10 +18669,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col1 (type: int), _col1 (type: int) - minReductionHashAggr: 0.28571427 + minReductionHashAggr: 0.0 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -18681,7 +18681,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -18708,13 +18708,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -18964,14 +18964,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key > 5) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -18979,10 +18979,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int) - minReductionHashAggr: 0.57142854 + minReductionHashAggr: 0.5294118 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -18991,7 +18991,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -19030,7 +19030,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 1 - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Select Operator expressions: _col1 (type: string) @@ -19038,7 +19038,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -19046,7 +19046,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -19073,13 +19073,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -19146,14 +19146,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: ((key > 5) and (value <= 'val_20')) (type: boolean) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -19161,7 +19161,7 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int), _col1 (type: string) - minReductionHashAggr: 0.0 + minReductionHashAggr: 0.5 mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE @@ -19325,14 +19325,14 @@ STAGE PLANS: className: VectorFilterOperator native: true predicate: (key > 2) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -19340,10 +19340,10 @@ STAGE PLANS: native: false vectorProcessingMode: HASH keys: _col0 (type: int) - minReductionHashAggr: 0.6666666 + minReductionHashAggr: 0.5555556 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -19352,7 +19352,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -19391,7 +19391,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) @@ -19400,7 +19400,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -19427,13 +19427,13 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_10.q.out b/ql/src/test/results/clientpositive/llap/vectorization_10.q.out index 3342549193..67879495e5 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_10.q.out @@ -78,7 +78,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a)))) predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 9557 Data size: 1937820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -87,13 +87,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 8, 0, 10, 6, 16, 18, 21, 22, 24, 25, 26, 28, 31, 33] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleColAddDoubleColumn(col 5:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, DoubleColModuloDoubleScalar(col 20:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: CastLongToDouble(col 1:smallint) -> 19:double) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 5:double) -> 22:double, DoubleColModuloDoubleColumn(col 23:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 23:double) -> 24:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 25:smallint, DoubleColUnaryMinus(col 5:double) -> 26:double, LongColMultiplyLongColumn(col 3:bigint, col 27:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 27:smallint) -> 28:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 30:double)(children: DoubleColAddDoubleColumn(col 5:double, col 29:double)(children: CastLongToDouble(col 1:smallint) -> 29:double) -> 30:double) -> 31:double, DoubleColUnaryMinus(col 32:double)(children: DoubleColUnaryMinus(col 5:double) -> 32:double) -> 33:double - Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2434654 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2434654 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_13.q.out b/ql/src/test/results/clientpositive/llap/vectorization_13.q.out index 18ebf12e6a..e1d303204e 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_13.q.out @@ -100,7 +100,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 15:decimal(11,4)))) predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -109,7 +109,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -124,7 +124,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -135,7 +135,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 5:tinyint, 6:double, 7:double, 8:double, 9:bigint, 10:double, 11:double, 12:bigint, 13:float, 14:tinyint - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -183,7 +183,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 64822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 @@ -192,7 +192,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 15, 5, 17, 6, 21, 22, 23, 28, 29, 34, 38, 40, 43, 13, 49, 14] selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 20:double)(children: CastLongToDouble(col 19:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 19:tinyint) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 6:double) -> 22:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 23:float, FuncPowerDoubleToDouble(col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 24:double) -> 25:double) -> 26:double) -> 27:double) -> 28:double, DoubleColUnaryMinus(col 6:double) -> 29:double, FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 32:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 30:double) -> 31:double) -> 32:double) -> 33:double) -> 34:double, DecimalColSubtractDecimalScalar(col 37:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 36:tinyint)(children: LongColAddLongColumn(col 35:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 35:tinyint) -> 36:tinyint) -> 37:decimal(3,0)) -> 38:decimal(7,3), DoubleColUnaryMinus(col 39:double)(children: DoubleColUnaryMinus(col 6:double) -> 39:double) -> 40:double, DoubleScalarDivideDoubleColumn(val -26.28, col 42:double)(children: DoubleColUnaryMinus(col 41:double)(children: DoubleColUnaryMinus(col 6:double) -> 41:double) -> 42:double) -> 43:double, DoubleColDivideDoubleColumn(col 47:double, col 48:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 46:double)(children: CastLongToDouble(col 45:tinyint)(children: LongColAddLongColumn(col 44:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 44:tinyint) -> 45:tinyint) -> 46:double) -> 47:double, CastLongToDouble(col 1:tinyint) -> 48:double) -> 49:double - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -201,7 +201,7 @@ STAGE PLANS: keyColumns: 0:boolean, 1:tinyint, 2:timestamp, 3:float, 4:string, 15:tinyint, 5:tinyint, 17:tinyint, 6:double, 21:double, 22:double, 23:float, 28:double, 29:double, 34:double, 38:decimal(7,3), 40:double, 43:double, 13:float, 49:double, 14:tinyint native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -226,7 +226,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Limit Vectorization: @@ -459,7 +459,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 15:decimal(11,4)))) predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -468,7 +468,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -483,7 +483,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -492,7 +492,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -527,7 +527,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 64822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 @@ -536,7 +536,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 15, 5, 17, 6, 21, 22, 23, 28, 29, 34, 38, 40, 43, 13, 49, 14] selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 20:double)(children: CastLongToDouble(col 19:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 19:tinyint) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 6:double) -> 22:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 23:float, FuncPowerDoubleToDouble(col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 24:double) -> 25:double) -> 26:double) -> 27:double) -> 28:double, DoubleColUnaryMinus(col 6:double) -> 29:double, FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 32:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 30:double) -> 31:double) -> 32:double) -> 33:double) -> 34:double, DecimalColSubtractDecimalScalar(col 37:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 36:tinyint)(children: LongColAddLongColumn(col 35:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 35:tinyint) -> 36:tinyint) -> 37:decimal(3,0)) -> 38:decimal(7,3), DoubleColUnaryMinus(col 39:double)(children: DoubleColUnaryMinus(col 6:double) -> 39:double) -> 40:double, DoubleScalarDivideDoubleColumn(val -26.28, col 42:double)(children: DoubleColUnaryMinus(col 41:double)(children: DoubleColUnaryMinus(col 6:double) -> 41:double) -> 42:double) -> 43:double, DoubleColDivideDoubleColumn(col 47:double, col 48:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 46:double)(children: CastLongToDouble(col 45:tinyint)(children: LongColAddLongColumn(col 44:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 44:tinyint) -> 45:tinyint) -> 46:double) -> 47:double, CastLongToDouble(col 1:tinyint) -> 48:double) -> 49:double - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) sort order: +++++++++++++++++++++ @@ -544,7 +544,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -562,7 +562,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_14.q.out b/ql/src/test/results/clientpositive/llap/vectorization_14.q.out index 84c1e3515e..1f7084acd3 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_14.q.out @@ -100,7 +100,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 14:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 14:float)), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 15:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 15:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp))) predicate: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 758 Data size: 132082 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -109,7 +109,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 4, 6, 10, 5, 17, 22, 4, 23] selectExpressions: DoubleColUnaryMinus(col 16:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 19:double, col 21:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 20:double) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 23:double - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 758 Data size: 132082 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) Group By Vectorization: @@ -124,7 +124,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 379 Data size: 66108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -135,7 +135,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 5:double, 6:double, 7:bigint, 8:float, 9:double, 10:double, 11:bigint - Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 379 Data size: 66108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -183,7 +183,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 151 Data size: 26432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 33008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 @@ -192,7 +192,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 1, 0, 4, 2, 12, 14, 22, 23, 8, 24, 25, 28, 33, 11, 37, 46, 47, 51, 56, 63, 65] selectExpressions: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 12:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 13:double) -> 14:double, FuncPowerDoubleToDouble(col 21:double)(children: DoubleColDivideLongColumn(col 17:double, col 20:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 16:double)(children: DoubleColDivideLongColumn(col 15:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 15:double) -> 16:double) -> 17:double, IfExprNullCondExpr(col 18:boolean, null, col 19:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 18:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 19:bigint) -> 20:bigint) -> 21:double) -> 22:double, DoubleColMultiplyDoubleScalar(col 1:float, val -26.280000686645508) -> 23:float, DoubleColUnaryMinus(col 1:float) -> 24:float, DoubleColUnaryMinus(col 8:float) -> 25:float, DoubleColDivideDoubleScalar(col 27:double, val 10.175)(children: DoubleColUnaryMinus(col 26:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 26:double) -> 27:double) -> 28:double, FuncPowerDoubleToDouble(col 32:double)(children: DoubleColDivideLongColumn(col 31:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 29:double) -> 30:double) -> 31:double) -> 32:double) -> 33:double, DoubleColUnaryMinus(col 36:double)(children: DoubleColDivideDoubleScalar(col 35:double, val 10.175)(children: DoubleColUnaryMinus(col 34:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 34:double) -> 35:double) -> 36:double) -> 37:double, DoubleScalarModuloDoubleColumn(val -1.389, col 45:double)(children: FuncPowerDoubleToDouble(col 44:double)(children: DoubleColDivideLongColumn(col 40:double, col 43:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 39:double)(children: DoubleColDivideLongColumn(col 38:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 38:double) -> 39:double) -> 40:double, IfExprNullCondExpr(col 41:boolean, null, col 42:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 41:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 42:bigint) -> 43:bigint) -> 44:double) -> 45:double) -> 46:double, DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 47:double, DoubleColDivideLongColumn(col 50:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 49:double)(children: DoubleColDivideLongColumn(col 48:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 48:double) -> 49:double) -> 50:double) -> 51:double, DoubleColModuloDoubleScalar(col 55:double, val 10.175)(children: DoubleColDivideLongColumn(col 54:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 53:double)(children: DoubleColDivideLongColumn(col 52:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 52:double) -> 53:double) -> 54:double) -> 55:double) -> 56:double, DoubleColDivideLongColumn(col 59:double, col 62:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 58:double)(children: DoubleColDivideLongColumn(col 57:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 57:double) -> 58:double) -> 59:double, IfExprNullCondExpr(col 60:boolean, null, col 61:bigint)(children: LongColEqualLongScalar(col 11:bigint, val 1) -> 60:boolean, LongColSubtractLongScalar(col 11:bigint, val 1) -> 61:bigint) -> 62:bigint) -> 63:double, DoubleColUnaryMinus(col 64:double)(children: DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 64:double) -> 65:double - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) sort order: ++++ @@ -202,7 +202,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 4:boolean, 12:double, 14:double, 22:double, 23:float, 8:float, 24:float, 25:float, 28:double, 33:double, 11:bigint, 37:double, 46:double, 47:double, 51:double, 56:double, 63:double, 65:double - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -227,13 +227,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3, 1, 0, 4, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_16.q.out b/ql/src/test/results/clientpositive/llap/vectorization_16.q.out index 8dcf6d0d1b..e9e8d1f0fe 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_16.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -82,7 +82,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -97,7 +97,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -108,7 +108,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 3:bigint, 4:double, 5:double, 6:double - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -156,7 +156,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 227586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -165,13 +165,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 7, 9, 3, 17, 26, 36, 6, 37, 39, 47] selectExpressions: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 7:double, DoubleColUnaryMinus(col 8:double)(children: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 8:double) -> 9:double, FuncPowerDoubleToDouble(col 16:double)(children: DoubleColDivideLongColumn(col 12:double, col 15:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 11:double) -> 12:double, IfExprNullCondExpr(col 13:boolean, null, col 14:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 14:bigint) -> 15:bigint) -> 16:double) -> 17:double, DoubleColUnaryMinus(col 25:double)(children: FuncPowerDoubleToDouble(col 24:double)(children: DoubleColDivideLongColumn(col 20:double, col 23:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 19:double)(children: DoubleColDivideLongColumn(col 18:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 18:double) -> 19:double) -> 20:double, IfExprNullCondExpr(col 21:boolean, null, col 22:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 21:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 22:bigint) -> 23:bigint) -> 24:double) -> 25:double) -> 26:double, DoubleColMultiplyDoubleColumn(col 34:double, col 35:double)(children: FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 29:double, col 32:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 27:double) -> 28:double) -> 29:double, IfExprNullCondExpr(col 30:boolean, null, col 31:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 30:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 31:bigint) -> 32:bigint) -> 33:double) -> 34:double, CastLongToDouble(col 3:bigint) -> 35:double) -> 36:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 1:double) -> 37:double, DecimalColDivideDecimalScalar(col 38:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 38:decimal(19,0)) -> 39:decimal(28,6), FuncPowerDoubleToDouble(col 46:double)(children: DoubleColDivideLongColumn(col 42:double, col 45:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 41:double)(children: DoubleColDivideLongColumn(col 40:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 40:double) -> 41:double) -> 42:double, IfExprNullCondExpr(col 43:boolean, null, col 44:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 43:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 44:bigint) -> 45:bigint) -> 46:double) -> 47:double - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_17.q.out b/ql/src/test/results/clientpositive/llap/vectorization_17.q.out index ff11dfa7bb..1b7dc7ea59 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_17.q.out @@ -81,7 +81,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)))) predicate: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) - Statistics: Num rows: 4096 Data size: 549274 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 823456 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -90,7 +90,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 17, 20, 22, 24, 26, 29] selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 17:double, DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 18:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 18:double) -> 19:double) -> 20:double, DoubleColDivideDoubleColumn(col 5:double, col 21:double)(children: CastLongToDouble(col 2:int) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColUnaryMinus(col 5:double) -> 23:double) -> 24:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 25:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 25:decimal(19,0)) -> 26:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 28:double)(children: DoubleColUnaryMinus(col 27:double)(children: DoubleColUnaryMinus(col 5:double) -> 27:double) -> 28:double) -> 29:double - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -100,7 +100,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 6:string, 2:int, 8:timestamp, 5:double, 15:double, 16:bigint, 17:double, 20:double, 22:double, 24:double, 26:decimal(11,4), 29:double - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -142,13 +142,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1, 2, 3, 4, 5, 0, 6, 7, 8, 9, 10, 11, 12, 13] - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_7.q.out b/ql/src/test/results/clientpositive/llap/vectorization_7.q.out index ef03189910..51ae4a0eb2 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_7.q.out @@ -87,7 +87,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 2711364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -96,7 +96,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -105,7 +105,7 @@ STAGE PLANS: keyColumns: 10:boolean, 3:bigint, 1:smallint, 0:tinyint, 8:timestamp, 6:string, 15:bigint, 16:int, 17:smallint, 18:tinyint, 20:int, 22:bigint, 23:int, 24:tinyint, 26:tinyint native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -147,7 +147,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 9, 14] - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: @@ -340,7 +340,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 2711364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -349,7 +349,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -357,7 +357,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -386,7 +386,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 9, 14] - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_9.q.out b/ql/src/test/results/clientpositive/llap/vectorization_9.q.out index 8dcf6d0d1b..e9e8d1f0fe 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_9.q.out @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -82,7 +82,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -97,7 +97,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -108,7 +108,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 3:bigint, 4:double, 5:double, 6:double - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -156,7 +156,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 227586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -165,13 +165,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 7, 9, 3, 17, 26, 36, 6, 37, 39, 47] selectExpressions: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 7:double, DoubleColUnaryMinus(col 8:double)(children: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 8:double) -> 9:double, FuncPowerDoubleToDouble(col 16:double)(children: DoubleColDivideLongColumn(col 12:double, col 15:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 11:double) -> 12:double, IfExprNullCondExpr(col 13:boolean, null, col 14:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 14:bigint) -> 15:bigint) -> 16:double) -> 17:double, DoubleColUnaryMinus(col 25:double)(children: FuncPowerDoubleToDouble(col 24:double)(children: DoubleColDivideLongColumn(col 20:double, col 23:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 19:double)(children: DoubleColDivideLongColumn(col 18:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 18:double) -> 19:double) -> 20:double, IfExprNullCondExpr(col 21:boolean, null, col 22:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 21:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 22:bigint) -> 23:bigint) -> 24:double) -> 25:double) -> 26:double, DoubleColMultiplyDoubleColumn(col 34:double, col 35:double)(children: FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 29:double, col 32:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 27:double) -> 28:double) -> 29:double, IfExprNullCondExpr(col 30:boolean, null, col 31:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 30:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 31:bigint) -> 32:bigint) -> 33:double) -> 34:double, CastLongToDouble(col 3:bigint) -> 35:double) -> 36:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 1:double) -> 37:double, DecimalColDivideDecimalScalar(col 38:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 38:decimal(19,0)) -> 39:decimal(28,6), FuncPowerDoubleToDouble(col 46:double)(children: DoubleColDivideLongColumn(col 42:double, col 45:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 41:double)(children: DoubleColDivideLongColumn(col 40:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 40:double) -> 41:double) -> 42:double, IfExprNullCondExpr(col 43:boolean, null, col 44:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 43:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 44:bigint) -> 45:bigint) -> 46:double) -> 47:double - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out index 3fe514b8b1..d6e28a1dba 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out @@ -258,7 +258,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000)) predicate: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 38416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cbigint - 988888L) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888L))) (type: double), (1.2 / CAST( (cbigint - 988888L) AS decimal(19,0))) (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 @@ -267,7 +267,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 19] selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double, DecimalScalarDivideDecimalColumn(val 1.2, col 18:decimal(19,0))(children: CastLongToDecimal(col 17:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 17:bigint) -> 18:decimal(19,0)) -> 19:decimal(22,21) - Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: decimal(22,21)) sort order: +++ @@ -275,7 +275,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -304,7 +304,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 Limit Vectorization: @@ -482,7 +482,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0)) predicate: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -491,7 +491,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 19, 22, 24, 26] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 17:double, col 18:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 17:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 18:double) -> 19:double, DoubleColDivideDoubleColumn(col 20:double, col 21:double)(children: CastLongToDouble(col 3:bigint) -> 20:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 21:double) -> 22:double, DoubleScalarDivideDoubleColumn(val 3.0, col 23:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 23:double) -> 24:double, DoubleScalarDivideDoubleColumn(val 1.2, col 25:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 25:double) -> 26:double - Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double) sort order: ++++++ @@ -499,7 +499,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -528,19 +528,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 1, 4, 5] - Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -706,7 +706,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 2:int, val 500000000), FilterDoubleColGreaterDoubleScalar(col 5:double, val 1.0E9), FilterLongColEqualLongScalar(col 0:tinyint, val 0)) predicate: ((cint > 500000000) or (cdouble > 1.0E9D) or (ctinyint = 0Y)) (type: boolean) - Statistics: Num rows: 4191 Data size: 75120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3378 Data size: 60552 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cbigint (type: bigint), ctinyint (type: tinyint), (UDFToDouble(cint) / UDFToDouble((cint - 528534767))) (type: double), (UDFToDouble(cbigint) / UDFToDouble((cbigint - 1018195815L))) (type: double), (UDFToDouble(ctinyint) / UDFToDouble(ctinyint)) (type: double), (cint % (cint - 528534767)) (type: int), (cbigint % (cbigint - 1018195815L)) (type: bigint), (ctinyint % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -715,7 +715,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 3, 0, 16, 20, 23, 25, 27, 28] selectExpressions: DoubleColDivideDoubleColumn(col 13:double, col 15:double)(children: CastLongToDouble(col 2:int) -> 13:double, CastLongToDouble(col 14:int)(children: LongColSubtractLongScalar(col 2:int, val 528534767) -> 14:int) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 3:bigint) -> 17:double, CastLongToDouble(col 18:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 1018195815) -> 18:bigint) -> 19:double) -> 20:double, DoubleColDivideDoubleColumn(col 21:double, col 22:double)(children: CastLongToDouble(col 0:tinyint) -> 21:double, CastLongToDouble(col 0:tinyint) -> 22:double) -> 23:double, LongColModuloLongColumn(col 2:int, col 24:int)(children: LongColSubtractLongScalar(col 2:int, val 528534767) -> 24:int) -> 25:int, LongColModuloLongColumn(col 3:bigint, col 26:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 1018195815) -> 26:bigint) -> 27:bigint, LongColModuloLongColumn(col 0:tinyint, col 0:tinyint) -> 28:tinyint - Statistics: Num rows: 4191 Data size: 217720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3378 Data size: 175488 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: tinyint), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: int), _col7 (type: bigint), _col8 (type: tinyint) sort order: +++++++++ @@ -723,7 +723,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 4191 Data size: 217720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3378 Data size: 175488 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -752,7 +752,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8] - Statistics: Num rows: 4191 Data size: 217720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3378 Data size: 175488 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out index 4ed197813e..f17b61ebec 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out @@ -33,15 +33,15 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs @@ -66,7 +66,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out index 2eadb1f899..8eb523d6f3 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out @@ -374,7 +374,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -26.28), FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 1:smallint) -> 13:double)), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 3:bigint, val 197), FilterLongColLessLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 4:float, val 79.5530014038086), FilterStringColLikeStringScalar(col 7:string, pattern 10%)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 14:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 0:tinyint) -> 14:float), FilterStringColRegExpStringScalar(col 6:string, pattern .*ss.*))) predicate: (((cdouble >= -26.28D) and (UDFToDouble(csmallint) > cdouble)) or ((cbigint <= 197L) and (UDFToLong(cint) < cbigint)) or ((cfloat > 79.553) and (cstring2 like '10%')) or ((UDFToFloat(ctinyint) > cfloat) and cstring1 regexp '.*ss.*')) (type: boolean) - Statistics: Num rows: 6826 Data size: 1131534 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8186 Data size: 1356970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -383,7 +383,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 3, 1, 5, 0, 15, 18, 19, 22, 23, 26] selectExpressions: CastLongToDouble(col 3:bigint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 16:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 18:double, CastLongToDouble(col 1:smallint) -> 19:double, DoubleColMultiplyDoubleColumn(col 20:double, col 21:double)(children: CastLongToDouble(col 1:smallint) -> 20:double, CastLongToDouble(col 1:smallint) -> 21:double) -> 22:double, CastLongToDouble(col 2:int) -> 23:double, DoubleColMultiplyDoubleColumn(col 24:double, col 25:double)(children: CastLongToDouble(col 2:int) -> 24:double, CastLongToDouble(col 2:int) -> 25:double) -> 26:double - Statistics: Num rows: 6826 Data size: 1131534 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8186 Data size: 1356970 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col0), sum(_col6), sum(_col5), count(_col1), sum(_col8), sum(_col7), count(_col2), max(_col3), sum(_col4), count(_col4), min(_col0), min(_col3), sum(_col10), sum(_col9), count(_col0) Group By Vectorization: @@ -2516,7 +2516,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 2563.58), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 3:bigint, col 2:bigint)(children: col 2:int), FilterLongColLessLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterDoubleColLessDoubleScalar(col 4:float, val -5638.14990234375)), FilterDecimalColEqualDecimalScalar(col 13:decimal(6,2), val 2563.58)(children: CastLongToDecimal(col 0:tinyint) -> 13:decimal(6,2)), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5:double, col 14:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(21,2), val -5638.15)(children: CastLongToDecimal(col 3:bigint) -> 15:decimal(21,2))))) predicate: ((cdouble > 2563.58D) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (cfloat < -5638.15)) or (CAST( ctinyint AS decimal(6,2)) = 2563.58) or ((cdouble <= UDFToDouble(cbigint)) and (CAST( cbigint AS decimal(21,2)) < -5638.15)))) (type: boolean) - Statistics: Num rows: 2503 Data size: 59820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7494 Data size: 179052 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), cfloat (type: float), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2 @@ -2525,7 +2525,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 4, 16] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 16:double - Statistics: Num rows: 2503 Data size: 59820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7494 Data size: 179052 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col0), count(_col0), count(_col1), sum(_col1) Group By Vectorization: @@ -2537,10 +2537,10 @@ STAGE PLANS: vectorProcessingMode: HASH projectedOutputColumnNums: [0, 1, 2, 3, 4] keys: _col0 (type: double) - minReductionHashAggr: 0.5497403 + minReductionHashAggr: 0.55004 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 155032 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2549,7 +2549,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 155032 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2584,7 +2584,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 155032 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END) (type: double), (2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), _col4 (type: bigint), ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D) (type: double), ((- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) * ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D)) (type: double), _col5 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (_col0 - (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END))) (type: double), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (_col0 + ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (_col0 * 762.0D) (type: double), _col2 (type: double), (-863.257D % (_col0 * 762.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -2593,7 +2593,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 12, 20, 28, 4, 37, 55, 5, 59, 68, 73, 81, 82, 2, 84] selectExpressions: DoubleColDivideLongColumn(col 8:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 7:double)(children: DoubleColDivideLongColumn(col 6:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 6:double) -> 7:double) -> 8:double, IfExprNullCondExpr(col 9:boolean, null, col 10:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 9:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 10:bigint) -> 11:bigint) -> 12:double, DoubleScalarMultiplyDoubleColumn(val 2563.58, col 19:double)(children: DoubleColDivideLongColumn(col 15:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 14:double)(children: DoubleColDivideLongColumn(col 13:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 13:double) -> 14:double) -> 15:double, IfExprNullCondExpr(col 16:boolean, null, col 17:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 17:bigint) -> 18:bigint) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 27:double)(children: DoubleColDivideLongColumn(col 23:double, col 26:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 22:double)(children: DoubleColDivideLongColumn(col 21:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 21:double) -> 22:double) -> 23:double, IfExprNullCondExpr(col 24:boolean, null, col 25:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 24:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 25:bigint) -> 26:bigint) -> 27:double) -> 28:double, DoubleColAddDoubleScalar(col 36:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 35:double)(children: DoubleColDivideLongColumn(col 31:double, col 34:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 29:double) -> 30:double) -> 31:double, IfExprNullCondExpr(col 32:boolean, null, col 33:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 32:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 33:bigint) -> 34:bigint) -> 35:double) -> 36:double) -> 37:double, DoubleColMultiplyDoubleColumn(col 45:double, col 54:double)(children: DoubleColUnaryMinus(col 44:double)(children: DoubleColDivideLongColumn(col 40:double, col 43:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 39:double)(children: DoubleColDivideLongColumn(col 38:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 38:double) -> 39:double) -> 40:double, IfExprNullCondExpr(col 41:boolean, null, col 42:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 41:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 42:bigint) -> 43:bigint) -> 44:double) -> 45:double, DoubleColAddDoubleScalar(col 53:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 52:double)(children: DoubleColDivideLongColumn(col 48:double, col 51:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 47:double)(children: DoubleColDivideLongColumn(col 46:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 46:double) -> 47:double) -> 48:double, IfExprNullCondExpr(col 49:boolean, null, col 50:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 49:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 50:bigint) -> 51:bigint) -> 52:double) -> 53:double) -> 54:double) -> 55:double, DoubleColDivideLongColumn(col 58:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 57:double)(children: DoubleColDivideLongColumn(col 56:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 56:double) -> 57:double) -> 58:double) -> 59:double, DoubleColSubtractDoubleColumn(col 0:double, col 67:double)(children: DoubleColUnaryMinus(col 66:double)(children: DoubleColDivideLongColumn(col 62:double, col 65:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 61:double)(children: DoubleColDivideLongColumn(col 60:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 60:double) -> 61:double) -> 62:double, IfExprNullCondExpr(col 63:boolean, null, col 64:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 63:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 64:bigint) -> 65:bigint) -> 66:double) -> 67:double) -> 68:double, FuncPowerDoubleToDouble(col 72:double)(children: DoubleColDivideLongColumn(col 71:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 70:double)(children: DoubleColDivideLongColumn(col 69:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 69:double) -> 70:double) -> 71:double) -> 72:double) -> 73:double, DoubleColAddDoubleColumn(col 0:double, col 80:double)(children: DoubleColDivideLongColumn(col 76:double, col 79:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 75:double)(children: DoubleColDivideLongColumn(col 74:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 74:double) -> 75:double) -> 76:double, IfExprNullCondExpr(col 77:boolean, null, col 78:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 77:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 78:bigint) -> 79:bigint) -> 80:double) -> 81:double, DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 82:double, DoubleScalarModuloDoubleColumn(val -863.257, col 83:double)(children: DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 83:double) -> 84:double - Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 424792 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2601,7 +2601,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 424792 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -2619,13 +2619,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13] - Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 424792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3372 Data size: 424792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3251,7 +3251,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 1:smallint) -> 13:double), FilterLongColEqualLongColumn(col 11:boolean, col 10:boolean), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(22,3), val -863.257)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3))), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -257), FilterLongColGreaterEqualLongScalar(col 10:boolean, val 1), SelectColumnIsNotNull(col 6:string)), FilterStringColRegExpStringScalar(col 7:string, pattern b), FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 1:smallint, col 0:smallint)(children: col 0:tinyint), SelectColumnIsNull(col 9:timestamp)))) predicate: (cboolean1 is not null and (((cdouble < UDFToDouble(csmallint)) and (cboolean2 = cboolean1) and (CAST( cbigint AS decimal(22,3)) <= -863.257)) or ((cint >= -257) and (cboolean1 >= 1) and cstring1 is not null) or cstring2 regexp 'b' or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null))) (type: boolean) - Statistics: Num rows: 5857 Data size: 1240180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6237 Data size: 1320590 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -3260,7 +3260,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 4, 3, 2, 5, 0, 1, 15, 18, 19, 22, 23, 26, 27, 30] selectExpressions: CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 17:double) -> 18:double, CastLongToDouble(col 3:bigint) -> 19:double, DoubleColMultiplyDoubleColumn(col 20:double, col 21:double)(children: CastLongToDouble(col 3:bigint) -> 20:double, CastLongToDouble(col 3:bigint) -> 21:double) -> 22:double, CastLongToDouble(col 0:tinyint) -> 23:double, DoubleColMultiplyDoubleColumn(col 24:double, col 25:double)(children: CastLongToDouble(col 0:tinyint) -> 24:double, CastLongToDouble(col 0:tinyint) -> 25:double) -> 26:double, CastLongToDouble(col 1:smallint) -> 27:double, DoubleColMultiplyDoubleColumn(col 28:double, col 29:double)(children: CastLongToDouble(col 1:smallint) -> 28:double, CastLongToDouble(col 1:smallint) -> 29:double) -> 30:double - Statistics: Num rows: 5857 Data size: 1240180 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6237 Data size: 1320590 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col2), sum(_col8), sum(_col7), count(_col3), sum(_col4), count(_col4), min(_col2), sum(_col10), sum(_col9), count(_col2), sum(_col3), sum(_col12), sum(_col11), count(_col5), sum(_col14), sum(_col13), count(_col6) Group By Vectorization: @@ -3275,7 +3275,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 2 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -3284,7 +3284,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: double), _col14 (type: double), _col15 (type: bigint), _col16 (type: double), _col17 (type: double), _col18 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -3319,7 +3319,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 2 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: float), (- _col1) (type: float), (-26.28D / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (CAST( _col2 AS decimal(19,0)) - 10.175) (type: decimal(23,3)), ((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END) % UDFToDouble(_col1)) (type: double), (10.175 + (- _col1)) (type: float), (_col6 / _col7) (type: double), (UDFToDouble((CAST( _col2 AS decimal(19,0)) - 10.175)) + ((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END)) (type: double), _col8 (type: bigint), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (- (10.175 + (- _col1))) (type: float), (79.553D / ((_col9 - ((_col10 * _col10) / _col11)) / _col11)) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / CASE WHEN ((_col5 = 1L)) THEN (null) ELSE ((_col5 - 1)) END) % (79.553D / ((_col9 - ((_col10 * _col10) / _col11)) / _col11))) (type: double), _col12 (type: bigint), power(((_col13 - ((_col14 * _col14) / _col15)) / CASE WHEN ((_col15 = 1L)) THEN (null) ELSE ((_col15 - 1)) END), 0.5) (type: double), (-1.389 * CAST( _col8 AS decimal(19,0))) (type: decimal(24,3)), (CAST( _col12 AS decimal(19,0)) - (-1.389 * CAST( _col8 AS decimal(19,0)))) (type: decimal(25,3)), power(((_col16 - ((_col17 * _col17) / _col18)) / _col18), 0.5) (type: double), (- (CAST( _col12 AS decimal(19,0)) - (-1.389 * CAST( _col8 AS decimal(19,0))))) (type: decimal(25,3)), (UDFToDouble(_col12) / _col5) (type: double), (- (UDFToDouble(_col12) / _col5)) (type: double), ((UDFToDouble(_col12) / _col5) * UDFToDouble(_col12)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 @@ -3328,7 +3328,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 19, 20, 2, 22, 29, 37, 39, 40, 51, 8, 55, 58, 63, 76, 12, 84, 86, 90, 95, 100, 102, 105, 109] selectExpressions: DoubleColUnaryMinus(col 1:float) -> 19:float, DoubleScalarDivideDoubleColumn(val -26.28, col 1:double)(children: col 1:float) -> 20:double, DecimalColSubtractDecimalScalar(col 21:decimal(19,0), val 10.175)(children: CastLongToDecimal(col 2:bigint) -> 21:decimal(19,0)) -> 22:decimal(23,3), DoubleColDivideLongColumn(col 25:double, col 28:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 24:double)(children: DoubleColDivideLongColumn(col 23:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 23:double) -> 24:double) -> 25:double, IfExprNullCondExpr(col 26:boolean, null, col 27:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 26:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 27:bigint) -> 28:bigint) -> 29:double, DoubleColModuloDoubleColumn(col 36:double, col 1:double)(children: DoubleColDivideLongColumn(col 32:double, col 35:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 30:double) -> 31:double) -> 32:double, IfExprNullCondExpr(col 33:boolean, null, col 34:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 33:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 34:bigint) -> 35:bigint) -> 36:double, col 1:float) -> 37:double, DoubleScalarAddDoubleColumn(val 10.175000190734863, col 38:float)(children: DoubleColUnaryMinus(col 1:float) -> 38:float) -> 39:float, DoubleColDivideLongColumn(col 6:double, col 7:bigint) -> 40:double, DoubleColAddDoubleColumn(col 43:double, col 50:double)(children: CastDecimalToDouble(col 42:decimal(23,3))(children: DecimalColSubtractDecimalScalar(col 41:decimal(19,0), val 10.175)(children: CastLongToDecimal(col 2:bigint) -> 41:decimal(19,0)) -> 42:decimal(23,3)) -> 43:double, DoubleColDivideLongColumn(col 46:double, col 49:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 45:double)(children: DoubleColDivideLongColumn(col 44:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 44:double) -> 45:double) -> 46:double, IfExprNullCondExpr(col 47:boolean, null, col 48:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 47:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 48:bigint) -> 49:bigint) -> 50:double) -> 51:double, DoubleColDivideLongColumn(col 54:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 53:double)(children: DoubleColDivideLongColumn(col 52:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 52:double) -> 53:double) -> 54:double) -> 55:double, DoubleColUnaryMinus(col 57:float)(children: DoubleScalarAddDoubleColumn(val 10.175000190734863, col 56:float)(children: DoubleColUnaryMinus(col 1:float) -> 56:float) -> 57:float) -> 58:float, DoubleScalarDivideDoubleColumn(val 79.553, col 62:double)(children: DoubleColDivideLongColumn(col 61:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 60:double)(children: DoubleColDivideLongColumn(col 59:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 59:double) -> 60:double) -> 61:double) -> 62:double) -> 63:double, DoubleColModuloDoubleColumn(col 70:double, col 75:double)(children: DoubleColDivideLongColumn(col 66:double, col 69:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 65:double)(children: DoubleColDivideLongColumn(col 64:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 64:double) -> 65:double) -> 66:double, IfExprNullCondExpr(col 67:boolean, null, col 68:bigint)(children: LongColEqualLongScalar(col 5:bigint, val 1) -> 67:boolean, LongColSubtractLongScalar(col 5:bigint, val 1) -> 68:bigint) -> 69:bigint) -> 70:double, DoubleScalarDivideDoubleColumn(val 79.553, col 74:double)(children: DoubleColDivideLongColumn(col 73:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 72:double)(children: DoubleColDivideLongColumn(col 71:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 71:double) -> 72:double) -> 73:double) -> 74:double) -> 75:double) -> 76:double, FuncPowerDoubleToDouble(col 83:double)(children: DoubleColDivideLongColumn(col 79:double, col 82:bigint)(children: DoubleColSubtractDoubleColumn(col 13:double, col 78:double)(children: DoubleColDivideLongColumn(col 77:double, col 15:bigint)(children: DoubleColMultiplyDoubleColumn(col 14:double, col 14:double) -> 77:double) -> 78:double) -> 79:double, IfExprNullCondExpr(col 80:boolean, null, col 81:bigint)(children: LongColEqualLongScalar(col 15:bigint, val 1) -> 80:boolean, LongColSubtractLongScalar(col 15:bigint, val 1) -> 81:bigint) -> 82:bigint) -> 83:double) -> 84:double, DecimalScalarMultiplyDecimalColumn(val -1.389, col 85:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 85:decimal(19,0)) -> 86:decimal(24,3), DecimalColSubtractDecimalColumn(col 87:decimal(19,0), col 89:decimal(24,3))(children: CastLongToDecimal(col 12:bigint) -> 87:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 88:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 88:decimal(19,0)) -> 89:decimal(24,3)) -> 90:decimal(25,3), FuncPowerDoubleToDouble(col 94:double)(children: DoubleColDivideLongColumn(col 93:double, col 18:bigint)(children: DoubleColSubtractDoubleColumn(col 16:double, col 92:double)(children: DoubleColDivideLongColumn(col 91:double, col 18:bigint)(children: DoubleColMultiplyDoubleColumn(col 17:double, col 17:double) -> 91:double) -> 92:double) -> 93:double) -> 94:double) -> 95:double, FuncNegateDecimalToDecimal(col 99:decimal(25,3))(children: DecimalColSubtractDecimalColumn(col 96:decimal(19,0), col 98:decimal(24,3))(children: CastLongToDecimal(col 12:bigint) -> 96:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 97:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 97:decimal(19,0)) -> 98:decimal(24,3)) -> 99:decimal(25,3)) -> 100:decimal(25,3), DoubleColDivideLongColumn(col 101:double, col 5:bigint)(children: CastLongToDouble(col 12:bigint) -> 101:double) -> 102:double, DoubleColUnaryMinus(col 104:double)(children: DoubleColDivideLongColumn(col 103:double, col 5:bigint)(children: CastLongToDouble(col 12:bigint) -> 103:double) -> 104:double) -> 105:double, DoubleColMultiplyDoubleColumn(col 107:double, col 108:double)(children: DoubleColDivideLongColumn(col 106:double, col 5:bigint)(children: CastLongToDouble(col 12:bigint) -> 106:double) -> 107:double, CastLongToDouble(col 12:bigint) -> 108:double) -> 109:double - Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -3336,7 +3336,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(23,3)), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: float), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,3)), _col21 (type: double), _col22 (type: decimal(25,3)), _col23 (type: double), _col24 (type: double), _col25 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -3354,13 +3354,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 13, 16, 17, 18, 19, 20, 21, 22, 23, 24] - Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_1.q.out b/ql/src/test/results/clientpositive/masking_1.q.out index 0958385b5c..fd025a4500 100644 --- a/ql/src/test/results/clientpositive/masking_1.q.out +++ b/ql/src/test/results/clientpositive/masking_1.q.out @@ -32,14 +32,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -88,14 +88,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -141,14 +141,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -194,14 +194,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 15272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -257,16 +257,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string), UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16268 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 980 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: double) sort order: + Map-reduce partition columns: _col2 (type: double) - Statistics: Num rows: 83 Data size: 16268 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 980 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: srcpart @@ -293,14 +293,14 @@ STAGE PLANS: 0 _col2 (type: double) 1 _col4 (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 525 Data size: 385350 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 31 Data size: 22754 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 525 Data size: 385350 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 31 Data size: 22754 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 525 Data size: 385350 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 31 Data size: 22754 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -400,14 +400,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -453,14 +453,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_12.q.out b/ql/src/test/results/clientpositive/masking_12.q.out index 6140a980ee..aa0ed40c5b 100644 --- a/ql/src/test/results/clientpositive/masking_12.q.out +++ b/ql/src/test/results/clientpositive/masking_12.q.out @@ -50,14 +50,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -360,14 +360,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 6) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger((UDFToDouble(key) / 2.0D)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -423,16 +423,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: masking_test_n5 @@ -442,16 +442,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 6) and ((key % 2) = 0) and ((UDFToInteger((UDFToDouble(key) / 2.0D)) % 2) = 0) and (UDFToInteger((UDFToDouble(key) / 2.0D)) < 10)) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger((UDFToDouble(key) / 2.0D)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -460,14 +460,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_13.q.out b/ql/src/test/results/clientpositive/masking_13.q.out index 4ca113df9c..672d65fd31 100644 --- a/ql/src/test/results/clientpositive/masking_13.q.out +++ b/ql/src/test/results/clientpositive/masking_13.q.out @@ -32,14 +32,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -133,14 +133,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 6) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger((UDFToDouble(key) / 2.0D)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_1_newdb.q.out b/ql/src/test/results/clientpositive/masking_1_newdb.q.out index a9c8f9deb4..293da26b7a 100644 --- a/ql/src/test/results/clientpositive/masking_1_newdb.q.out +++ b/ql/src/test/results/clientpositive/masking_1_newdb.q.out @@ -50,14 +50,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -106,14 +106,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_5.q.out b/ql/src/test/results/clientpositive/masking_5.q.out index c8334373fa..57fab2facb 100644 --- a/ql/src/test/results/clientpositive/masking_5.q.out +++ b/ql/src/test/results/clientpositive/masking_5.q.out @@ -33,14 +33,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -85,14 +85,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -171,14 +171,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((hash(key) & 2147483647) % 2) = 0) and ((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 7708 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 7708 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_8.q.out b/ql/src/test/results/clientpositive/masking_8.q.out index 939d965aff..ee11d376ad 100644 --- a/ql/src/test/results/clientpositive/masking_8.q.out +++ b/ql/src/test/results/clientpositive/masking_8.q.out @@ -37,14 +37,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 90500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 15023 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 905 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string), _c2 (type: string), ROW__ID (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 83 Data size: 29050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 29050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -93,14 +93,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 90500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 15023 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 905 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string), _c2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 22742 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1370 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 22742 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 1370 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -149,14 +149,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 90500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 15023 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 905 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: INPUT__FILE__NAME (type: string), key (type: int), reverse(value) (type: string), _c2 (type: string), ROW__ID (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 44322 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 2670 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 44322 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 2670 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -231,14 +231,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 433000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 71878 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 4330 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ROW__ID (type: struct), key (type: int), _c1 (type: string), _c2 (type: string), _c3 (type: string), _c4 (type: string), _c5 (type: string), _c6 (type: string), _c7 (type: string), _c8 (type: string), _c9 (type: string), _c10 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 83 Data size: 78186 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 4710 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 78186 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 4710 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out b/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out index 777352f86a..6ef55df2e7 100644 --- a/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out +++ b/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out @@ -32,14 +32,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -88,14 +88,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -141,14 +141,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -194,14 +194,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 15272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -257,16 +257,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 37848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 2280 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 37848 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 2280 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: srcpart @@ -289,14 +289,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1, _col5, _col6, _col7, _col8 - Statistics: Num rows: 525 Data size: 385350 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 31 Data size: 22754 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 525 Data size: 385350 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 31 Data size: 22754 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 525 Data size: 385350 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 31 Data size: 22754 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -396,14 +396,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -449,14 +449,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_mv.q.out b/ql/src/test/results/clientpositive/masking_mv.q.out index 99146ac854..5897635ce1 100644 --- a/ql/src/test/results/clientpositive/masking_mv.q.out +++ b/ql/src/test/results/clientpositive/masking_mv.q.out @@ -217,14 +217,14 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (0 = (key % 2))) (type: boolean) - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -291,28 +291,28 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (0 = (key % 2))) (type: boolean) - Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 41 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -364,32 +364,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,23 +441,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string), key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -466,10 +466,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -535,32 +535,32 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (0 = (key % 2))) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 7544 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -616,23 +616,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (0 = (key % 2))) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string), key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -641,10 +641,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 7872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullability_transitive_inference.q.out b/ql/src/test/results/clientpositive/nullability_transitive_inference.q.out index 879eaa2d88..c14e3cc87f 100644 --- a/ql/src/test/results/clientpositive/nullability_transitive_inference.q.out +++ b/ql/src/test/results/clientpositive/nullability_transitive_inference.q.out @@ -139,16 +139,16 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (deptno >= 20) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: deptno (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out index 0cbd846a54..0cc7e67363 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out @@ -74,7 +74,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a)))) predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 9557 Data size: 1937820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -83,13 +83,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 8, 0, 10, 6, 16, 18, 21, 22, 24, 25, 26, 28, 31, 33] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleColAddDoubleColumn(col 5:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, DoubleColModuloDoubleScalar(col 20:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: CastLongToDouble(col 1:smallint) -> 19:double) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 5:double) -> 22:double, DoubleColModuloDoubleColumn(col 23:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 23:double) -> 24:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 25:smallint, DoubleColUnaryMinus(col 5:double) -> 26:double, LongColMultiplyLongColumn(col 3:bigint, col 27:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 27:smallint) -> 28:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 30:double)(children: DoubleColAddDoubleColumn(col 5:double, col 29:double)(children: CastLongToDouble(col 1:smallint) -> 29:double) -> 30:double) -> 31:double, DoubleColUnaryMinus(col 32:double)(children: DoubleColUnaryMinus(col 5:double) -> 32:double) -> 33:double - Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2434654 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2434654 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out index 119842757b..134ce1f12e 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out @@ -93,7 +93,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 15:decimal(11,4)))) predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -102,7 +102,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -117,7 +117,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -127,7 +127,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -149,11 +149,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 64822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -175,7 +175,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -195,7 +195,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE @@ -416,7 +416,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 15:decimal(11,4)))) predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -425,7 +425,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -440,7 +440,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -450,7 +450,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -472,11 +472,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 64822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -498,7 +498,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -518,7 +518,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out index 1d4a41c268..c943d7b07b 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out @@ -93,7 +93,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 14:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 14:float)), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 15:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 15:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp))) predicate: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 758 Data size: 132082 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -102,7 +102,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 4, 6, 10, 5, 17, 22, 4, 23] selectExpressions: DoubleColUnaryMinus(col 16:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 19:double, col 21:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 20:double) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 23:double - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 758 Data size: 132082 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) Group By Vectorization: @@ -117,7 +117,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 379 Data size: 66108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -127,7 +127,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 379 Data size: 66108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -149,11 +149,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 151 Data size: 26432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 33008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -175,7 +175,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Execution mode: vectorized Map Vectorization: @@ -195,10 +195,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out index 6a038a3745..ae684e6cae 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out @@ -66,7 +66,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -75,7 +75,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -100,7 +100,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -122,14 +122,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 227586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out index 4a8eb4d0fa..6adb1289d7 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out @@ -74,7 +74,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)))) predicate: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) - Statistics: Num rows: 4096 Data size: 549274 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 823456 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -83,7 +83,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 17, 20, 22, 24, 26, 29] selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 17:double, DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 18:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 18:double) -> 19:double) -> 20:double, DoubleColDivideDoubleColumn(col 5:double, col 21:double)(children: CastLongToDouble(col 2:int) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColUnaryMinus(col 5:double) -> 23:double) -> 24:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 25:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 25:decimal(19,0)) -> 26:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 28:double)(children: DoubleColUnaryMinus(col 27:double)(children: DoubleColUnaryMinus(col 5:double) -> 27:double) -> 28:double) -> 29:double - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -92,7 +92,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -112,10 +112,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out index adfbdf9a8a..d1a1ae4065 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out @@ -80,7 +80,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 2711364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -89,7 +89,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -98,7 +98,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -118,7 +118,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE @@ -299,7 +299,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 2711364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -308,7 +308,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -317,7 +317,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -337,7 +337,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out index 6a038a3745..ae684e6cae 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out @@ -66,7 +66,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -75,7 +75,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -100,7 +100,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -122,14 +122,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 227586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out index bcd4bdb9d0..1aa85b850c 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out @@ -211,7 +211,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000)) predicate: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 38416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cbigint - 988888L) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888L))) (type: double), (1.2 / CAST( (cbigint - 988888L) AS decimal(19,0))) (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 @@ -220,7 +220,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 19] selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double, DecimalScalarDivideDecimalColumn(val 1.2, col 18:decimal(19,0))(children: CastLongToDecimal(col 17:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 17:bigint) -> 18:decimal(19,0)) -> 19:decimal(22,21) - Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ @@ -229,7 +229,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(22,21)) Execution mode: vectorized @@ -250,7 +250,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE @@ -414,7 +414,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0)) predicate: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col4, _col5 @@ -423,7 +423,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 19, 21, 23] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 17:double, col 18:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 17:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 18:double) -> 19:double, DoubleScalarDivideDoubleColumn(val 3.0, col 20:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 20:double) -> 21:double, DoubleScalarDivideDoubleColumn(val 1.2, col 22:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 22:double) -> 23:double - Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double) sort order: ++ @@ -432,7 +432,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) Execution mode: vectorized @@ -453,13 +453,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out index 67a99838c8..ad3b1acd92 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out @@ -25,11 +25,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out index e204b9eede..a384b7c00d 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out @@ -25,11 +25,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 2 Offset of rows: 3 diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index 584a4c4c14..54a9585598 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -80,16 +80,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (key < 5) (type: boolean) - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: zz sort order: ++ - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -201,13 +201,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -287,16 +287,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((key < 5) or (ds <= '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 10008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: z sort order: + - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -457,13 +457,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -578,16 +578,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((key < 5) and (value <> 'val_2')) (type: boolean) - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: zz sort order: ++ - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -699,13 +699,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -785,16 +785,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: zz sort order: ++ - Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -906,13 +906,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -996,16 +996,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: zz sort order: ++ - Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1166,13 +1166,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1266,16 +1266,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: zz sort order: ++ - Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1436,13 +1436,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query34.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query34.q.out index dcde40c322..f43a27a1ff 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query34.q.out @@ -108,16 +108,16 @@ Stage-0 PartitionCols:_col1 Filter Operator [FIL_121] (rows=6 width=12) predicate:_col2 BETWEEN 15L AND 20L - Select Operator [SEL_120] (rows=5521356 width=12) + Select Operator [SEL_120] (rows=13251253 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_119] (rows=5521356 width=12) + Group By Operator [GBY_119] (rows=13251253 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0, _col1 - Group By Operator [GBY_24] (rows=5521356 width=12) + Group By Operator [GBY_24] (rows=13251253 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_98] (rows=5521356 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=13251253 width=4) Conds:RS_20._col3=RS_118._col0(Inner),Output:["_col1","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_118] @@ -131,14 +131,14 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=10407948 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=24979074 width=5) Conds:RS_17._col2=RS_115._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] PartitionCols:_col0 - Select Operator [SEL_114] (rows=480 width=4) + Select Operator [SEL_114] (rows=1152 width=4) Output:["_col0"] - Filter Operator [FIL_113] (rows=480 width=104) + Filter Operator [FIL_113] (rows=1152 width=104) predicate:((hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (false) END and (hd_buy_potential) IN ('>10000', 'unknown')) TableScan [TS_8] (rows=7200 width=104) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out index 622fd78818..167a684afe 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query35.q.out @@ -169,39 +169,39 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_65] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_103] (rows=61 width=276) + Top N Key Operator [TNK_103] (rows=1635 width=276) keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 - Select Operator [SEL_64] (rows=61 width=276) + Select Operator [SEL_64] (rows=1635 width=276) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_63] (rows=61 width=276) + Filter Operator [FIL_63] (rows=1635 width=276) predicate:(_col11 is not null or _col13 is not null) - Merge Join Operator [MERGEJOIN_181] (rows=61 width=276) + Merge Join Operator [MERGEJOIN_181] (rows=1635 width=276) Conds:RS_60._col0=RS_217._col1(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col13"] <-Reducer 5 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_180] (rows=62 width=276) + Merge Join Operator [MERGEJOIN_180] (rows=1663 width=276) Conds:RS_57._col0=RS_209._col1(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col11"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_179] (rows=148065 width=272) + Merge Join Operator [MERGEJOIN_179] (rows=1334622 width=272) Conds:RS_54._col0=RS_55._col0(Left Semi),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col0 - Group By Operator [GBY_53] (rows=153432 width=2) + Group By Operator [GBY_53] (rows=1383003 width=3) Output:["_col0"],keys:_col0 - Select Operator [SEL_23] (rows=62428523 width=2) + Select Operator [SEL_23] (rows=187573258 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_176] (rows=62428523 width=2) + Merge Join Operator [MERGEJOIN_176] (rows=187573258 width=3) Conds:RS_201._col0=RS_191._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_191] PartitionCols:_col0 - Select Operator [SEL_190] (rows=217 width=4) + Select Operator [SEL_190] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_189] (rows=217 width=12) + Filter Operator [FIL_189] (rows=652 width=12) predicate:((d_year = 1999) and (d_qoy < 4)) TableScan [TS_17] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] @@ -222,7 +222,7 @@ Stage-0 SHUFFLE [RS_196] Group By Operator [GBY_195] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_192] (rows=217 width=4) + Select Operator [SEL_192] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_190] <-Reducer 3 [SIMPLE_EDGE] @@ -263,16 +263,16 @@ Stage-0 <-Reducer 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_209] PartitionCols:_col1 - Select Operator [SEL_208] (rows=168147 width=7) + Select Operator [SEL_208] (rows=505213 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_207] (rows=168147 width=3) + Group By Operator [GBY_207] (rows=505213 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0 - Group By Operator [GBY_34] (rows=168147 width=3) + Group By Operator [GBY_34] (rows=505213 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_177] (rows=17104380 width=3) + Merge Join Operator [MERGEJOIN_177] (rows=51391963 width=3) Conds:RS_206._col0=RS_193._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_193] @@ -295,22 +295,22 @@ Stage-0 SHUFFLE [RS_151] Group By Operator [GBY_150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_149] (rows=148065 width=4) + Select Operator [SEL_149] (rows=1334622 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_179] <-Reducer 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_217] PartitionCols:_col1 - Select Operator [SEL_216] (rows=165374 width=7) + Select Operator [SEL_216] (rows=496881 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_215] (rows=165374 width=3) + Group By Operator [GBY_215] (rows=496881 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_48] (rows=165374 width=3) + Group By Operator [GBY_48] (rows=993762 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_178] (rows=33642830 width=3) + Merge Join Operator [MERGEJOIN_178] (rows=101083527 width=3) Conds:RS_214._col0=RS_194._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] @@ -333,7 +333,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_166] Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_164] (rows=62 width=4) + Select Operator [SEL_164] (rows=1663 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_180] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query37.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query37.q.out index 9d12a547c7..2f561c77c3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query37.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query37.q.out @@ -57,22 +57,22 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_100] - Limit [LIM_99] (rows=1 width=396) + Limit [LIM_99] (rows=4 width=396) Number of rows:100 - Select Operator [SEL_98] (rows=1 width=396) + Select Operator [SEL_98] (rows=4 width=396) Output:["_col0","_col1","_col2"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_97] - Group By Operator [GBY_96] (rows=1 width=396) + Group By Operator [GBY_96] (rows=4 width=396) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_22] (rows=2 width=396) + Group By Operator [GBY_22] (rows=8 width=396) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Top N Key Operator [TNK_42] (rows=2871 width=396) + Top N Key Operator [TNK_42] (rows=11627 width=396) keys:_col2, _col3, _col4,sort order:+++,top n:100 - Merge Join Operator [MERGEJOIN_78] (rows=2871 width=396) + Merge Join Operator [MERGEJOIN_78] (rows=11627 width=396) Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col2","_col3","_col4"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_77] (rows=463969 width=4) + Merge Join Operator [MERGEJOIN_77] (rows=1879072 width=4) Conds:RS_92._col0=RS_95._col0(Inner),Output:["_col1"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] @@ -125,9 +125,9 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] PartitionCols:_col0 - Select Operator [SEL_91] (rows=4176000 width=8) + Select Operator [SEL_91] (rows=16912800 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_90] (rows=4176000 width=11) + Filter Operator [FIL_90] (rows=16912800 width=11) predicate:inv_quantity_on_hand BETWEEN 100 AND 500 TableScan [TS_5] (rows=37584000 width=11) default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query66.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query66.q.out index 279a3cf374..3f84383308 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query66.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query66.q.out @@ -505,11 +505,11 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_61] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_60] (rows=5559759 width=3166) + Group By Operator [GBY_60] (rows=12905590 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_58] (rows=5559759 width=750) + Select Operator [SEL_58] (rows=12905590 width=750) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_202] (rows=5559759 width=750) + Merge Join Operator [MERGEJOIN_202] (rows=12905590 width=750) Conds:RS_55._col3=RS_240._col0(Inner),Output:["_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col22","_col23","_col24","_col25","_col26","_col27"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_240] @@ -521,7 +521,7 @@ Stage-0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_201] (rows=5559759 width=274) + Merge Join Operator [MERGEJOIN_201] (rows=12905590 width=275) Conds:RS_52._col2=RS_219._col0(Inner),Output:["_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_219] @@ -535,7 +535,7 @@ Stage-0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_200] (rows=11119518 width=278) + Merge Join Operator [MERGEJOIN_200] (rows=38716771 width=279) Conds:RS_49._col0=RS_237._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_237] @@ -549,14 +549,14 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_199] (rows=31363607 width=235) + Merge Join Operator [MERGEJOIN_199] (rows=109204159 width=235) Conds:RS_256._col1=RS_233._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_233] PartitionCols:_col0 - Select Operator [SEL_231] (rows=9600 width=4) + Select Operator [SEL_231] (rows=33426 width=4) Output:["_col0"] - Filter Operator [FIL_230] (rows=9600 width=8) + Filter Operator [FIL_230] (rows=33426 width=8) predicate:t_time BETWEEN 49530 AND 78330 TableScan [TS_3] (rows=86400 width=8) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_time"] @@ -596,9 +596,9 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_28] (rows=27 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_26] (rows=2853684 width=750) + Select Operator [SEL_26] (rows=6624114 width=750) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_198] (rows=2853684 width=750) + Merge Join Operator [MERGEJOIN_198] (rows=6624114 width=750) Conds:RS_23._col3=RS_239._col0(Inner),Output:["_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col22","_col23","_col24","_col25","_col26","_col27"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_239] @@ -607,7 +607,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_197] (rows=2853684 width=275) + Merge Join Operator [MERGEJOIN_197] (rows=6624114 width=275) Conds:RS_20._col2=RS_217._col0(Inner),Output:["_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_217] @@ -616,7 +616,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_196] (rows=5707369 width=279) + Merge Join Operator [MERGEJOIN_196] (rows=19872342 width=279) Conds:RS_17._col0=RS_236._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_236] @@ -625,7 +625,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_195] (rows=15984351 width=235) + Merge Join Operator [MERGEJOIN_195] (rows=55655511 width=235) Conds:RS_229._col1=RS_232._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_232] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query73.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query73.q.out index 7a1a4a2afb..f4ba2807ac 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query73.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query73.q.out @@ -102,16 +102,16 @@ Stage-0 PartitionCols:_col1 Filter Operator [FIL_121] (rows=5 width=12) predicate:_col2 BETWEEN 1L AND 5L - Select Operator [SEL_120] (rows=788766 width=12) + Select Operator [SEL_120] (rows=1893036 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_119] (rows=788766 width=12) + Group By Operator [GBY_119] (rows=1893036 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0, _col1 - Group By Operator [GBY_24] (rows=788766 width=12) + Group By Operator [GBY_24] (rows=1893036 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_98] (rows=788766 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=1893036 width=4) Conds:RS_20._col3=RS_118._col0(Inner),Output:["_col1","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_118] @@ -125,14 +125,14 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=2973700 width=4) + Merge Join Operator [MERGEJOIN_97] (rows=7136878 width=4) Conds:RS_17._col2=RS_115._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] PartitionCols:_col0 - Select Operator [SEL_114] (rows=480 width=4) + Select Operator [SEL_114] (rows=1152 width=4) Output:["_col0"] - Filter Operator [FIL_113] (rows=480 width=104) + Filter Operator [FIL_113] (rows=1152 width=104) predicate:((hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (false) END and (hd_buy_potential) IN ('>10000', 'unknown')) TableScan [TS_8] (rows=7200 width=104) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query79.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query79.q.out index a2b75fd723..ae34114103 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query79.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query79.q.out @@ -74,13 +74,13 @@ Stage-0 File Output Operator [FS_124] Limit [LIM_123] (rows=100 width=776) Number of rows:100 - Select Operator [SEL_122] (rows=43530621 width=776) + Select Operator [SEL_122] (rows=91407175 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_32] - Select Operator [SEL_31] (rows=43530621 width=776) + Select Operator [SEL_31] (rows=91407175 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_99] (rows=43530621 width=685) + Merge Join Operator [MERGEJOIN_99] (rows=91407175 width=685) Conds:RS_101._col0=RS_121._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_101] @@ -92,23 +92,23 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_121] PartitionCols:_col1 - Select Operator [SEL_120] (rows=43530621 width=507) + Select Operator [SEL_120] (rows=91407175 width=508) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_119] (rows=43530621 width=325) + Group By Operator [GBY_119] (rows=91407175 width=327) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_24] (rows=43530621 width=325) + Group By Operator [GBY_24] (rows=91407175 width=327) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col3, _col5, _col10 - Merge Join Operator [MERGEJOIN_98] (rows=43530621 width=214) + Merge Join Operator [MERGEJOIN_98] (rows=91407175 width=274) Conds:RS_20._col2=RS_118._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_118] PartitionCols:_col0 - Select Operator [SEL_117] (rows=3055 width=4) + Select Operator [SEL_117] (rows=6415 width=4) Output:["_col0"] - Filter Operator [FIL_116] (rows=3055 width=12) + Filter Operator [FIL_116] (rows=6415 width=12) predicate:((hd_vehicle_count > 0) or (hd_dep_count = 8)) TableScan [TS_11] (rows=7200 width=12) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query82.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query82.q.out index 041a3f90ad..9cb2546160 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query82.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query82.q.out @@ -70,9 +70,9 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_22] (rows=2 width=396) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Top N Key Operator [TNK_42] (rows=2871 width=396) + Top N Key Operator [TNK_42] (rows=11627 width=396) keys:_col2, _col3, _col4,sort order:+++,top n:100 - Merge Join Operator [MERGEJOIN_78] (rows=2871 width=396) + Merge Join Operator [MERGEJOIN_78] (rows=11627 width=396) Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col2","_col3","_col4"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_77] (rows=463969 width=4) + Merge Join Operator [MERGEJOIN_77] (rows=1879072 width=4) Conds:RS_92._col0=RS_95._col0(Inner),Output:["_col1"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] @@ -125,9 +125,9 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] PartitionCols:_col0 - Select Operator [SEL_91] (rows=4176000 width=8) + Select Operator [SEL_91] (rows=16912800 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_90] (rows=4176000 width=11) + Filter Operator [FIL_90] (rows=16912800 width=11) predicate:inv_quantity_on_hand BETWEEN 100 AND 500 TableScan [TS_5] (rows=37584000 width=11) default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out index dee99d1f08..5ce42b1907 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query84.q.out @@ -70,18 +70,18 @@ Stage-0 File Output Operator [FS_139] Limit [LIM_138] (rows=100 width=384) Number of rows:100 - Select Operator [SEL_137] (rows=264528 width=384) + Select Operator [SEL_137] (rows=793584 width=384) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_35] - Select Operator [SEL_34] (rows=264528 width=384) + Select Operator [SEL_34] (rows=793584 width=384) Output:["_col1","_col2"] - Merge Join Operator [MERGEJOIN_119] (rows=264528 width=284) + Merge Join Operator [MERGEJOIN_119] (rows=793584 width=284) Conds:RS_31._col4=RS_32._col0(Inner),Output:["_col2","_col6"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_117] (rows=721 width=4) + Merge Join Operator [MERGEJOIN_117] (rows=2161 width=4) Conds:RS_133._col1=RS_136._col0(Inner),Output:["_col0"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_133] @@ -95,9 +95,9 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_136] PartitionCols:_col0 - Select Operator [SEL_135] (rows=2 width=4) + Select Operator [SEL_135] (rows=6 width=4) Output:["_col0"] - Filter Operator [FIL_134] (rows=2 width=12) + Filter Operator [FIL_134] (rows=6 width=12) predicate:((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287)) TableScan [TS_18] (rows=20 width=12) default@income_band,income_band,Tbl:COMPLETE,Col:COMPLETE,Output:["ib_income_band_sk","ib_lower_bound","ib_upper_bound"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query88.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query88.q.out index 2e14bcc4e2..c86f38ba3d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query88.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query88.q.out @@ -284,7 +284,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_153] Group By Operator [GBY_152] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_592] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_592] (rows=2979630 width=8) Conds:RS_148._col2=RS_676._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_676] @@ -298,28 +298,28 @@ Stage-0 <-Reducer 31 [SIMPLE_EDGE] SHUFFLE [RS_148] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_591] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_591] (rows=4058523 width=0) Conds:RS_145._col0=RS_632._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_632] PartitionCols:_col0 - Select Operator [SEL_619] (rows=1515 width=4) + Select Operator [SEL_619] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_611] (rows=1515 width=12) + Filter Operator [FIL_611] (rows=2312 width=12) predicate:((t_hour = 10) and (t_minute < 30)) TableScan [TS_6] (rows=86400 width=12) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_145] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_590] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_590] (rows=82152686 width=5) Conds:RS_713._col1=RS_666._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_666] PartitionCols:_col0 - Select Operator [SEL_660] (rows=817 width=4) + Select Operator [SEL_660] (rows=1179 width=4) Output:["_col0"] - Filter Operator [FIL_659] (rows=817 width=12) + Filter Operator [FIL_659] (rows=1179 width=12) predicate:((hd_dep_count) IN (3, 0, 1) and (((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and ((hd_vehicle_count <= 5) or (hd_vehicle_count <= 2) or (hd_vehicle_count <= 3))) TableScan [TS_3] (rows=7200 width=12) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] @@ -340,7 +340,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_651] Group By Operator [GBY_643] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_633] (rows=1515 width=4) + Select Operator [SEL_633] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_619] <-Reducer 9 [CUSTOM_SIMPLE_EDGE] @@ -355,7 +355,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_127] Group By Operator [GBY_126] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_589] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_589] (rows=2880396 width=8) Conds:RS_122._col2=RS_675._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_675] @@ -364,20 +364,20 @@ Stage-0 <-Reducer 27 [SIMPLE_EDGE] SHUFFLE [RS_122] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_588] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_588] (rows=3923357 width=0) Conds:RS_119._col0=RS_630._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_630] PartitionCols:_col0 - Select Operator [SEL_618] (rows=1515 width=4) + Select Operator [SEL_618] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_610] (rows=1515 width=12) + Filter Operator [FIL_610] (rows=2235 width=12) predicate:((t_hour = 10) and (t_minute >= 30)) Please refer to the previous TableScan [TS_6] <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_119] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_587] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_587] (rows=82152686 width=5) Conds:RS_706._col1=RS_665._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_665] @@ -400,7 +400,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_650] Group By Operator [GBY_642] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_631] (rows=1515 width=4) + Select Operator [SEL_631] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_618] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] @@ -415,7 +415,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_101] Group By Operator [GBY_100] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_586] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_586] (rows=2979630 width=8) Conds:RS_96._col2=RS_674._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_674] @@ -424,20 +424,20 @@ Stage-0 <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_96] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_585] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_585] (rows=4058523 width=0) Conds:RS_93._col0=RS_628._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_628] PartitionCols:_col0 - Select Operator [SEL_617] (rows=1515 width=4) + Select Operator [SEL_617] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_609] (rows=1515 width=12) + Filter Operator [FIL_609] (rows=2312 width=12) predicate:((t_hour = 11) and (t_minute < 30)) Please refer to the previous TableScan [TS_6] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_584] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_584] (rows=82152686 width=5) Conds:RS_699._col1=RS_664._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_664] @@ -460,7 +460,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_649] Group By Operator [GBY_641] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_629] (rows=1515 width=4) + Select Operator [SEL_629] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_617] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] @@ -475,7 +475,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_75] Group By Operator [GBY_74] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_583] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_583] (rows=2880396 width=8) Conds:RS_70._col2=RS_673._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_673] @@ -484,20 +484,20 @@ Stage-0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_70] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_582] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_582] (rows=3923357 width=0) Conds:RS_67._col0=RS_626._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_626] PartitionCols:_col0 - Select Operator [SEL_616] (rows=1515 width=4) + Select Operator [SEL_616] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_608] (rows=1515 width=12) + Filter Operator [FIL_608] (rows=2235 width=12) predicate:((t_hour = 11) and (t_minute >= 30)) Please refer to the previous TableScan [TS_6] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_581] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_581] (rows=82152686 width=5) Conds:RS_692._col1=RS_663._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_663] @@ -520,7 +520,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_648] Group By Operator [GBY_640] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_627] (rows=1515 width=4) + Select Operator [SEL_627] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_616] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] @@ -535,7 +535,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_580] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_580] (rows=2979630 width=8) Conds:RS_44._col2=RS_672._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_672] @@ -544,20 +544,20 @@ Stage-0 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_579] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_579] (rows=4058523 width=0) Conds:RS_41._col0=RS_624._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_624] PartitionCols:_col0 - Select Operator [SEL_615] (rows=1515 width=4) + Select Operator [SEL_615] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_607] (rows=1515 width=12) + Filter Operator [FIL_607] (rows=2312 width=12) predicate:((t_hour = 12) and (t_minute < 30)) Please refer to the previous TableScan [TS_6] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_578] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_578] (rows=82152686 width=5) Conds:RS_685._col1=RS_662._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_662] @@ -580,7 +580,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_647] Group By Operator [GBY_639] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_625] (rows=1515 width=4) + Select Operator [SEL_625] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_615] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized @@ -591,7 +591,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_577] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_577] (rows=2880396 width=8) Conds:RS_18._col2=RS_671._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_671] @@ -600,20 +600,20 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_576] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_576] (rows=3923357 width=0) Conds:RS_15._col0=RS_622._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_622] PartitionCols:_col0 - Select Operator [SEL_614] (rows=1515 width=4) + Select Operator [SEL_614] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_606] (rows=1515 width=12) + Filter Operator [FIL_606] (rows=2235 width=12) predicate:((t_hour = 8) and (t_minute >= 30)) Please refer to the previous TableScan [TS_6] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_575] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_575] (rows=82152686 width=5) Conds:RS_658._col1=RS_661._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_661] @@ -636,7 +636,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_646] Group By Operator [GBY_638] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_623] (rows=1515 width=4) + Select Operator [SEL_623] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_614] <-Reducer 37 [CUSTOM_SIMPLE_EDGE] vectorized @@ -647,7 +647,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_179] Group By Operator [GBY_178] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_595] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_595] (rows=2880396 width=8) Conds:RS_174._col2=RS_677._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_677] @@ -656,20 +656,20 @@ Stage-0 <-Reducer 35 [SIMPLE_EDGE] SHUFFLE [RS_174] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_594] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_594] (rows=3923357 width=0) Conds:RS_171._col0=RS_634._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_634] PartitionCols:_col0 - Select Operator [SEL_620] (rows=1515 width=4) + Select Operator [SEL_620] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_612] (rows=1515 width=12) + Filter Operator [FIL_612] (rows=2235 width=12) predicate:((t_hour = 9) and (t_minute >= 30)) Please refer to the previous TableScan [TS_6] <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_171] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_593] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_593] (rows=82152686 width=5) Conds:RS_720._col1=RS_667._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_667] @@ -692,7 +692,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_652] Group By Operator [GBY_644] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_635] (rows=1515 width=4) + Select Operator [SEL_635] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_620] <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized @@ -703,7 +703,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_205] Group By Operator [GBY_204] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_598] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_598] (rows=2979630 width=8) Conds:RS_200._col2=RS_678._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_678] @@ -712,20 +712,20 @@ Stage-0 <-Reducer 39 [SIMPLE_EDGE] SHUFFLE [RS_200] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_597] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_597] (rows=4058523 width=0) Conds:RS_197._col0=RS_636._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_636] PartitionCols:_col0 - Select Operator [SEL_621] (rows=1515 width=4) + Select Operator [SEL_621] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_613] (rows=1515 width=12) + Filter Operator [FIL_613] (rows=2312 width=12) predicate:((t_hour = 9) and (t_minute < 30)) Please refer to the previous TableScan [TS_6] <-Reducer 38 [SIMPLE_EDGE] SHUFFLE [RS_197] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_596] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_596] (rows=82152686 width=5) Conds:RS_727._col1=RS_668._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_668] @@ -748,7 +748,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_653] Group By Operator [GBY_645] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_637] (rows=1515 width=4) + Select Operator [SEL_637] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_621] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query90.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query90.q.out index 48449ef8c2..8bae0a748b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query90.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query90.q.out @@ -83,7 +83,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_145] (rows=153010 width=8) + Merge Join Operator [MERGEJOIN_145] (rows=351832 width=8) Conds:RS_18._col1=RS_152._col0(Inner) <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_152] @@ -97,7 +97,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_144] (rows=1681936 width=3) + Merge Join Operator [MERGEJOIN_144] (rows=3867464 width=3) Conds:RS_15._col0=RS_169._col0(Inner),Output:["_col1"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_169] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_143] (rows=15977923 width=7) + Merge Join Operator [MERGEJOIN_143] (rows=36739842 width=7) Conds:RS_161._col2=RS_164._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_161] @@ -136,9 +136,9 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_164] PartitionCols:_col0 - Select Operator [SEL_163] (rows=511 width=4) + Select Operator [SEL_163] (rows=1175 width=4) Output:["_col0"] - Filter Operator [FIL_162] (rows=511 width=7) + Filter Operator [FIL_162] (rows=1175 width=7) predicate:wp_char_count BETWEEN 5000 AND 5200 TableScan [TS_3] (rows=4602 width=7) default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk","wp_char_count"] @@ -150,7 +150,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_148] (rows=153010 width=8) + Merge Join Operator [MERGEJOIN_148] (rows=351832 width=8) Conds:RS_44._col1=RS_154._col0(Inner) <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_154] @@ -159,7 +159,7 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_147] (rows=1681936 width=3) + Merge Join Operator [MERGEJOIN_147] (rows=3867464 width=3) Conds:RS_41._col0=RS_170._col0(Inner),Output:["_col1"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_170] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out index e5c25bfab0..3ca06dfb8e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out @@ -60,7 +60,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_72] (rows=1084713 width=8) + Merge Join Operator [MERGEJOIN_72] (rows=1600220 width=8) Conds:RS_18._col2=RS_89._col0(Inner) <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_89] @@ -74,7 +74,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_71] (rows=1477476 width=0) + Merge Join Operator [MERGEJOIN_71] (rows=2179643 width=0) Conds:RS_15._col1=RS_86._col0(Inner),Output:["_col2"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_86] @@ -88,14 +88,14 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_70] (rows=16240953 width=0) + Merge Join Operator [MERGEJOIN_70] (rows=23959428 width=0) Conds:RS_83._col0=RS_75._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_75] PartitionCols:_col0 - Select Operator [SEL_74] (rows=1515 width=4) + Select Operator [SEL_74] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_73] (rows=1515 width=12) + Filter Operator [FIL_73] (rows=2235 width=12) predicate:((t_hour = 8) and (t_minute >= 30)) TableScan [TS_3] (rows=86400 width=12) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] @@ -116,7 +116,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_78] Group By Operator [GBY_77] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_76] (rows=1515 width=4) + Select Operator [SEL_76] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_74] diff --git a/ql/src/test/results/clientpositive/perf/tez/query34.q.out b/ql/src/test/results/clientpositive/perf/tez/query34.q.out index 61e1951d7b..7edf1f895a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query34.q.out @@ -110,16 +110,16 @@ Stage-0 PartitionCols:_col1 Filter Operator [FIL_123] (rows=6 width=12) predicate:_col2 BETWEEN 15L AND 20L - Select Operator [SEL_122] (rows=5521356 width=12) + Select Operator [SEL_122] (rows=13251253 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_121] (rows=5521356 width=12) + Group By Operator [GBY_121] (rows=13251253 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1 - Group By Operator [GBY_25] (rows=5521356 width=12) + Group By Operator [GBY_25] (rows=13251253 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_99] (rows=5521356 width=4) + Merge Join Operator [MERGEJOIN_99] (rows=13251253 width=4) Conds:RS_21._col3=RS_120._col0(Inner),Output:["_col1","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_120] @@ -133,14 +133,14 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=10407948 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=24979074 width=5) Conds:RS_18._col2=RS_117._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_116] (rows=480 width=4) + Select Operator [SEL_116] (rows=1152 width=4) Output:["_col0"] - Filter Operator [FIL_115] (rows=480 width=104) + Filter Operator [FIL_115] (rows=1152 width=104) predicate:((hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (false) END and (hd_buy_potential) IN ('>10000', 'unknown') and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=104) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/query35.q.out index fd21fc9580..baf94f95e0 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query35.q.out @@ -129,20 +129,20 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 13 <- Reducer 16 (BROADCAST_EDGE) -Map 21 <- Reducer 10 (BROADCAST_EDGE) +Map 12 <- Reducer 15 (BROADCAST_EDGE) +Map 21 <- Reducer 18 (BROADCAST_EDGE) Map 22 <- Reducer 9 (BROADCAST_EDGE) -Reducer 10 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 18 <- Reducer 17 (SIMPLE_EDGE) -Reducer 19 <- Map 15 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 14 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 17 <- Reducer 16 (SIMPLE_EDGE) +Reducer 18 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 14 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) Reducer 20 <- Reducer 19 (SIMPLE_EDGE) -Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 18 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 20 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) @@ -153,76 +153,114 @@ Stage-0 limit:-1 Stage-1 Reducer 8 vectorized - File Output Operator [FS_226] - Limit [LIM_225] (rows=1 width=352) + File Output Operator [FS_229] + Limit [LIM_228] (rows=1 width=352) Number of rows:100 - Select Operator [SEL_224] (rows=1 width=352) + Select Operator [SEL_227] (rows=1 width=352) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] - Select Operator [SEL_222] (rows=1 width=352) + SHUFFLE [RS_226] + Select Operator [SEL_225] (rows=1 width=352) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - Group By Operator [GBY_221] (rows=1 width=336) + Group By Operator [GBY_224] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","count(VALUE._col2)","max(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","max(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","max(VALUE._col9)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_66] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_104] (rows=61 width=276) + Top N Key Operator [TNK_104] (rows=1635 width=276) keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 - Select Operator [SEL_65] (rows=61 width=276) + Select Operator [SEL_65] (rows=1635 width=276) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_64] (rows=61 width=276) + Filter Operator [FIL_64] (rows=1635 width=276) predicate:(_col11 is not null or _col13 is not null) - Merge Join Operator [MERGEJOIN_182] (rows=61 width=276) - Conds:RS_61._col0=RS_220._col1(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col13"] + Merge Join Operator [MERGEJOIN_182] (rows=1635 width=276) + Conds:RS_61._col0=RS_223._col1(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col13"] <-Reducer 5 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_181] (rows=62 width=276) - Conds:RS_58._col0=RS_212._col1(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col11"] + Merge Join Operator [MERGEJOIN_181] (rows=1663 width=276) + Conds:RS_58._col0=RS_215._col1(Left Outer),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10","_col11"] + <-Reducer 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_215] + PartitionCols:_col1 + Select Operator [SEL_214] (rows=505213 width=7) + Output:["_col0","_col1"] + Group By Operator [GBY_213] (rows=505213 width=3) + Output:["_col0"],keys:KEY._col0 + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col0 + Group By Operator [GBY_29] (rows=505213 width=3) + Output:["_col0"],keys:_col1 + Merge Join Operator [MERGEJOIN_178] (rows=51391963 width=3) + Conds:RS_212._col0=RS_196._col0(Inner),Output:["_col1"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_196] + PartitionCols:_col0 + Select Operator [SEL_193] (rows=652 width=4) + Output:["_col0"] + Filter Operator [FIL_192] (rows=652 width=12) + predicate:((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_212] + PartitionCols:_col0 + Select Operator [SEL_211] (rows=143930993 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_210] (rows=143930993 width=7) + predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null and ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) + TableScan [TS_19] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_209] + Group By Operator [GBY_208] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_202] + Group By Operator [GBY_200] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_197] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_193] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_58] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_180] (rows=148065 width=272) + Merge Join Operator [MERGEJOIN_180] (rows=1334622 width=272) Conds:RS_55._col0=RS_56._col0(Left Semi),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Reducer 14 [SIMPLE_EDGE] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0 - Group By Operator [GBY_54] (rows=153432 width=2) + Group By Operator [GBY_54] (rows=1383003 width=3) Output:["_col0"],keys:_col0 - Select Operator [SEL_18] (rows=62428523 width=2) + Select Operator [SEL_18] (rows=187573258 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_177] (rows=62428523 width=2) - Conds:RS_204._col0=RS_194._col0(Inner),Output:["_col1"] - <-Map 15 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_177] (rows=187573258 width=3) + Conds:RS_207._col0=RS_194._col0(Inner),Output:["_col1"] + <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 - Select Operator [SEL_193] (rows=217 width=4) - Output:["_col0"] - Filter Operator [FIL_192] (rows=217 width=12) - predicate:((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_204] + Please refer to the previous Select Operator [SEL_193] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_207] PartitionCols:_col0 - Select Operator [SEL_203] (rows=525327388 width=7) + Select Operator [SEL_206] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_202] (rows=525327388 width=7) + Filter Operator [FIL_205] (rows=525327388 width=7) predicate:(ss_sold_date_sk is not null and ss_customer_sk is not null and ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) TableScan [TS_9] (rows=575995635 width=7) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_201] - Group By Operator [GBY_200] (rows=1 width=12) + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_204] + Group By Operator [GBY_203] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_199] - Group By Operator [GBY_198] (rows=1 width=12) + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_201] + Group By Operator [GBY_199] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_195] (rows=217 width=4) + Select Operator [SEL_195] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_193] <-Reducer 3 [SIMPLE_EDGE] @@ -230,7 +268,7 @@ Stage-0 PartitionCols:_col0 Merge Join Operator [MERGEJOIN_176] (rows=78293105 width=272) Conds:RS_50._col1=RS_191._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Map 12 [SIMPLE_EDGE] vectorized + <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_191] PartitionCols:_col0 Select Operator [SEL_190] (rows=1861800 width=186) @@ -253,7 +291,7 @@ Stage-0 predicate:(c_current_cdemo_sk is not null and c_current_addr_sk is not null and c_customer_sk is not null) TableScan [TS_0] (rows=80000000 width=11) default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 11 [SIMPLE_EDGE] vectorized + <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_188] PartitionCols:_col0 Select Operator [SEL_187] (rows=40000000 width=90) @@ -262,80 +300,42 @@ Stage-0 predicate:ca_address_sk is not null TableScan [TS_3] (rows=40000000 width=90) default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] - <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_212] - PartitionCols:_col1 - Select Operator [SEL_211] (rows=168147 width=7) - Output:["_col0","_col1"] - Group By Operator [GBY_210] (rows=168147 width=3) - Output:["_col0"],keys:KEY._col0 - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col0 - Group By Operator [GBY_29] (rows=168147 width=3) - Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_178] (rows=17104380 width=3) - Conds:RS_209._col0=RS_196._col0(Inner),Output:["_col1"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_196] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_193] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_209] - PartitionCols:_col0 - Select Operator [SEL_208] (rows=143930993 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_207] (rows=143930993 width=7) - predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null and ws_bill_customer_sk BETWEEN DynamicValue(RS_58_c_c_customer_sk_min) AND DynamicValue(RS_58_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_58_c_c_customer_sk_bloom_filter))) - TableScan [TS_19] (rows=144002668 width=7) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_206] - Group By Operator [GBY_205] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 4 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_152] - Group By Operator [GBY_151] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=148065 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_180] <-Reducer 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_220] + SHUFFLE [RS_223] PartitionCols:_col1 - Select Operator [SEL_219] (rows=165374 width=7) + Select Operator [SEL_222] (rows=496881 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_218] (rows=165374 width=3) + Group By Operator [GBY_221] (rows=496881 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 - Group By Operator [GBY_43] (rows=165374 width=3) + Group By Operator [GBY_43] (rows=993762 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_179] (rows=33642830 width=3) - Conds:RS_217._col0=RS_197._col0(Inner),Output:["_col1"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_197] + Merge Join Operator [MERGEJOIN_179] (rows=101083527 width=3) + Conds:RS_220._col0=RS_198._col0(Inner),Output:["_col1"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_198] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_193] <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_217] + SHUFFLE [RS_220] PartitionCols:_col0 - Select Operator [SEL_216] (rows=285115246 width=7) + Select Operator [SEL_219] (rows=285115246 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_215] (rows=285115246 width=7) + Filter Operator [FIL_218] (rows=285115246 width=7) predicate:(cs_ship_customer_sk is not null and cs_sold_date_sk is not null and cs_ship_customer_sk BETWEEN DynamicValue(RS_61_c_c_customer_sk_min) AND DynamicValue(RS_61_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_61_c_c_customer_sk_bloom_filter))) TableScan [TS_33] (rows=287989836 width=7) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_214] - Group By Operator [GBY_213] (rows=1 width=12) + BROADCAST [RS_217] + Group By Operator [GBY_216] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_167] Group By Operator [GBY_166] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_165] (rows=62 width=4) + Select Operator [SEL_165] (rows=1663 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_181] diff --git a/ql/src/test/results/clientpositive/perf/tez/query37.q.out b/ql/src/test/results/clientpositive/perf/tez/query37.q.out index 82afde4b3a..29b8fe2a21 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query37.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query37.q.out @@ -57,22 +57,22 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_101] - Limit [LIM_100] (rows=1 width=396) + Limit [LIM_100] (rows=4 width=396) Number of rows:100 - Select Operator [SEL_99] (rows=1 width=396) + Select Operator [SEL_99] (rows=4 width=396) Output:["_col0","_col1","_col2"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_98] - Group By Operator [GBY_97] (rows=1 width=396) + Group By Operator [GBY_97] (rows=4 width=396) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_23] (rows=2 width=396) + Group By Operator [GBY_23] (rows=8 width=396) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Top N Key Operator [TNK_43] (rows=2871 width=396) + Top N Key Operator [TNK_43] (rows=11627 width=396) keys:_col2, _col3, _col4,sort order:+++,top n:100 - Merge Join Operator [MERGEJOIN_79] (rows=2871 width=396) + Merge Join Operator [MERGEJOIN_79] (rows=11627 width=396) Conds:RS_19._col1=RS_20._col1(Inner),Output:["_col2","_col3","_col4"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_19] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_78] (rows=463969 width=4) + Merge Join Operator [MERGEJOIN_78] (rows=1879072 width=4) Conds:RS_93._col0=RS_96._col0(Inner),Output:["_col1"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_96] @@ -125,9 +125,9 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_92] (rows=4176000 width=8) + Select Operator [SEL_92] (rows=16912800 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_91] (rows=4176000 width=11) + Filter Operator [FIL_91] (rows=16912800 width=11) predicate:(inv_quantity_on_hand BETWEEN 100 AND 500 and inv_item_sk is not null and inv_date_sk is not null) TableScan [TS_6] (rows=37584000 width=11) default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query66.q.out b/ql/src/test/results/clientpositive/perf/tez/query66.q.out index c25628a36e..57fa2d4979 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query66.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query66.q.out @@ -505,11 +505,11 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_62] (rows=5559759 width=3166) + Group By Operator [GBY_62] (rows=12905590 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_60] (rows=5559759 width=750) + Select Operator [SEL_60] (rows=12905590 width=750) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_204] (rows=5559759 width=750) + Merge Join Operator [MERGEJOIN_204] (rows=12905590 width=750) Conds:RS_57._col3=RS_243._col0(Inner),Output:["_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col22","_col23","_col24","_col25","_col26","_col27"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_243] @@ -523,7 +523,7 @@ Stage-0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_203] (rows=5559759 width=274) + Merge Join Operator [MERGEJOIN_203] (rows=12905590 width=275) Conds:RS_54._col2=RS_221._col0(Inner),Output:["_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] @@ -537,7 +537,7 @@ Stage-0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_54] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_202] (rows=11119518 width=278) + Merge Join Operator [MERGEJOIN_202] (rows=38716771 width=279) Conds:RS_51._col0=RS_239._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_239] @@ -551,14 +551,14 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_51] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_201] (rows=31363607 width=235) + Merge Join Operator [MERGEJOIN_201] (rows=109204159 width=235) Conds:RS_259._col1=RS_235._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_235] PartitionCols:_col0 - Select Operator [SEL_233] (rows=9600 width=4) + Select Operator [SEL_233] (rows=33426 width=4) Output:["_col0"] - Filter Operator [FIL_232] (rows=9600 width=8) + Filter Operator [FIL_232] (rows=33426 width=8) predicate:(t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) TableScan [TS_3] (rows=86400 width=8) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_time"] @@ -598,9 +598,9 @@ Stage-0 PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_29] (rows=27 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_27] (rows=2853684 width=750) + Select Operator [SEL_27] (rows=6624114 width=750) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_200] (rows=2853684 width=750) + Merge Join Operator [MERGEJOIN_200] (rows=6624114 width=750) Conds:RS_24._col3=RS_242._col0(Inner),Output:["_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col22","_col23","_col24","_col25","_col26","_col27"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_242] @@ -609,7 +609,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_199] (rows=2853684 width=275) + Merge Join Operator [MERGEJOIN_199] (rows=6624114 width=275) Conds:RS_21._col2=RS_219._col0(Inner),Output:["_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_219] @@ -618,7 +618,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_198] (rows=5707369 width=279) + Merge Join Operator [MERGEJOIN_198] (rows=19872342 width=279) Conds:RS_18._col0=RS_238._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_238] @@ -627,7 +627,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_197] (rows=15984351 width=235) + Merge Join Operator [MERGEJOIN_197] (rows=55655511 width=235) Conds:RS_231._col1=RS_234._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_234] diff --git a/ql/src/test/results/clientpositive/perf/tez/query73.q.out b/ql/src/test/results/clientpositive/perf/tez/query73.q.out index 7c37b6b68c..f601fec864 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query73.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query73.q.out @@ -104,16 +104,16 @@ Stage-0 PartitionCols:_col1 Filter Operator [FIL_123] (rows=5 width=12) predicate:_col2 BETWEEN 1L AND 5L - Select Operator [SEL_122] (rows=788766 width=12) + Select Operator [SEL_122] (rows=1893036 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_121] (rows=788766 width=12) + Group By Operator [GBY_121] (rows=1893036 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1 - Group By Operator [GBY_25] (rows=788766 width=12) + Group By Operator [GBY_25] (rows=1893036 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_99] (rows=788766 width=4) + Merge Join Operator [MERGEJOIN_99] (rows=1893036 width=4) Conds:RS_21._col3=RS_120._col0(Inner),Output:["_col1","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_120] @@ -127,14 +127,14 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=2973700 width=4) + Merge Join Operator [MERGEJOIN_98] (rows=7136878 width=4) Conds:RS_18._col2=RS_117._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_116] (rows=480 width=4) + Select Operator [SEL_116] (rows=1152 width=4) Output:["_col0"] - Filter Operator [FIL_115] (rows=480 width=104) + Filter Operator [FIL_115] (rows=1152 width=104) predicate:((hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (false) END and (hd_buy_potential) IN ('>10000', 'unknown') and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=104) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query79.q.out b/ql/src/test/results/clientpositive/perf/tez/query79.q.out index f94b4679b8..894f51400a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query79.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query79.q.out @@ -74,13 +74,13 @@ Stage-0 File Output Operator [FS_126] Limit [LIM_125] (rows=100 width=776) Number of rows:100 - Select Operator [SEL_124] (rows=43530621 width=776) + Select Operator [SEL_124] (rows=91407175 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_33] - Select Operator [SEL_32] (rows=43530621 width=776) + Select Operator [SEL_32] (rows=91407175 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_100] (rows=43530621 width=685) + Merge Join Operator [MERGEJOIN_100] (rows=91407175 width=685) Conds:RS_103._col0=RS_123._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_103] @@ -94,23 +94,23 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_123] PartitionCols:_col1 - Select Operator [SEL_122] (rows=43530621 width=507) + Select Operator [SEL_122] (rows=91407175 width=508) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_121] (rows=43530621 width=325) + Group By Operator [GBY_121] (rows=91407175 width=327) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_25] (rows=43530621 width=325) + Group By Operator [GBY_25] (rows=91407175 width=327) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col3, _col5, _col10 - Merge Join Operator [MERGEJOIN_99] (rows=43530621 width=214) + Merge Join Operator [MERGEJOIN_99] (rows=91407175 width=274) Conds:RS_21._col2=RS_120._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_120] PartitionCols:_col0 - Select Operator [SEL_119] (rows=3055 width=4) + Select Operator [SEL_119] (rows=6415 width=4) Output:["_col0"] - Filter Operator [FIL_118] (rows=3055 width=12) + Filter Operator [FIL_118] (rows=6415 width=12) predicate:(((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) TableScan [TS_12] (rows=7200 width=12) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query82.q.out b/ql/src/test/results/clientpositive/perf/tez/query82.q.out index 2db63b0edb..f377a9273b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query82.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query82.q.out @@ -70,9 +70,9 @@ Stage-0 PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_23] (rows=2 width=396) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Top N Key Operator [TNK_43] (rows=2871 width=396) + Top N Key Operator [TNK_43] (rows=11627 width=396) keys:_col2, _col3, _col4,sort order:+++,top n:100 - Merge Join Operator [MERGEJOIN_79] (rows=2871 width=396) + Merge Join Operator [MERGEJOIN_79] (rows=11627 width=396) Conds:RS_19._col1=RS_20._col1(Inner),Output:["_col2","_col3","_col4"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_19] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_78] (rows=463969 width=4) + Merge Join Operator [MERGEJOIN_78] (rows=1879072 width=4) Conds:RS_93._col0=RS_96._col0(Inner),Output:["_col1"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_96] @@ -125,9 +125,9 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_92] (rows=4176000 width=8) + Select Operator [SEL_92] (rows=16912800 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_91] (rows=4176000 width=11) + Filter Operator [FIL_91] (rows=16912800 width=11) predicate:(inv_quantity_on_hand BETWEEN 100 AND 500 and inv_item_sk is not null and inv_date_sk is not null) TableScan [TS_6] (rows=37584000 width=11) default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query84.q.out b/ql/src/test/results/clientpositive/perf/tez/query84.q.out index a3a91487aa..4905c0aa4f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query84.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query84.q.out @@ -70,13 +70,13 @@ Stage-0 File Output Operator [FS_141] Limit [LIM_140] (rows=100 width=384) Number of rows:100 - Select Operator [SEL_139] (rows=264534 width=384) + Select Operator [SEL_139] (rows=793602 width=384) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_36] - Select Operator [SEL_35] (rows=264534 width=384) + Select Operator [SEL_35] (rows=793602 width=384) Output:["_col1","_col2"] - Merge Join Operator [MERGEJOIN_120] (rows=264534 width=284) + Merge Join Operator [MERGEJOIN_120] (rows=793602 width=284) Conds:RS_32._col1=RS_33._col1(Inner),Output:["_col2","_col6"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_32] @@ -104,12 +104,12 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_119] (rows=8315 width=284) + Merge Join Operator [MERGEJOIN_119] (rows=24945 width=284) Conds:RS_25._col2=RS_26._col0(Inner),Output:["_col0","_col1","_col4"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_118] (rows=721 width=4) + Merge Join Operator [MERGEJOIN_118] (rows=2161 width=4) Conds:RS_135._col1=RS_138._col0(Inner),Output:["_col0"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_135] @@ -123,9 +123,9 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_138] PartitionCols:_col0 - Select Operator [SEL_137] (rows=2 width=4) + Select Operator [SEL_137] (rows=6 width=4) Output:["_col0"] - Filter Operator [FIL_136] (rows=2 width=12) + Filter Operator [FIL_136] (rows=6 width=12) predicate:((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) TableScan [TS_15] (rows=20 width=12) default@income_band,income_band,Tbl:COMPLETE,Col:COMPLETE,Output:["ib_income_band_sk","ib_lower_bound","ib_upper_bound"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query88.q.out b/ql/src/test/results/clientpositive/perf/tez/query88.q.out index 2c0e520479..c95c71de8d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query88.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query88.q.out @@ -284,7 +284,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_153] Group By Operator [GBY_152] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_592] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_592] (rows=2979630 width=8) Conds:RS_148._col2=RS_676._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_676] @@ -298,28 +298,28 @@ Stage-0 <-Reducer 31 [SIMPLE_EDGE] SHUFFLE [RS_148] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_591] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_591] (rows=4058523 width=0) Conds:RS_145._col0=RS_632._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_632] PartitionCols:_col0 - Select Operator [SEL_619] (rows=1515 width=4) + Select Operator [SEL_619] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_611] (rows=1515 width=12) + Filter Operator [FIL_611] (rows=2312 width=12) predicate:((t_hour = 10) and (t_minute < 30) and t_time_sk is not null) TableScan [TS_6] (rows=86400 width=12) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_145] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_590] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_590] (rows=82152686 width=5) Conds:RS_713._col1=RS_666._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_666] PartitionCols:_col0 - Select Operator [SEL_660] (rows=817 width=4) + Select Operator [SEL_660] (rows=1179 width=4) Output:["_col0"] - Filter Operator [FIL_659] (rows=817 width=12) + Filter Operator [FIL_659] (rows=1179 width=12) predicate:((hd_dep_count) IN (3, 0, 1) and (((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and ((hd_vehicle_count <= 5) or (hd_vehicle_count <= 2) or (hd_vehicle_count <= 3)) and hd_demo_sk is not null) TableScan [TS_3] (rows=7200 width=12) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] @@ -340,7 +340,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_651] Group By Operator [GBY_643] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_633] (rows=1515 width=4) + Select Operator [SEL_633] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_619] <-Reducer 9 [CUSTOM_SIMPLE_EDGE] @@ -355,7 +355,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_127] Group By Operator [GBY_126] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_589] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_589] (rows=2880396 width=8) Conds:RS_122._col2=RS_675._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_675] @@ -364,20 +364,20 @@ Stage-0 <-Reducer 27 [SIMPLE_EDGE] SHUFFLE [RS_122] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_588] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_588] (rows=3923357 width=0) Conds:RS_119._col0=RS_630._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_630] PartitionCols:_col0 - Select Operator [SEL_618] (rows=1515 width=4) + Select Operator [SEL_618] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_610] (rows=1515 width=12) + Filter Operator [FIL_610] (rows=2235 width=12) predicate:((t_hour = 10) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_119] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_587] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_587] (rows=82152686 width=5) Conds:RS_706._col1=RS_665._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_665] @@ -400,7 +400,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_650] Group By Operator [GBY_642] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_631] (rows=1515 width=4) + Select Operator [SEL_631] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_618] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] @@ -415,7 +415,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_101] Group By Operator [GBY_100] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_586] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_586] (rows=2979630 width=8) Conds:RS_96._col2=RS_674._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_674] @@ -424,20 +424,20 @@ Stage-0 <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_96] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_585] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_585] (rows=4058523 width=0) Conds:RS_93._col0=RS_628._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_628] PartitionCols:_col0 - Select Operator [SEL_617] (rows=1515 width=4) + Select Operator [SEL_617] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_609] (rows=1515 width=12) + Filter Operator [FIL_609] (rows=2312 width=12) predicate:((t_hour = 11) and (t_minute < 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_584] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_584] (rows=82152686 width=5) Conds:RS_699._col1=RS_664._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_664] @@ -460,7 +460,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_649] Group By Operator [GBY_641] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_629] (rows=1515 width=4) + Select Operator [SEL_629] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_617] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] @@ -475,7 +475,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_75] Group By Operator [GBY_74] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_583] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_583] (rows=2880396 width=8) Conds:RS_70._col2=RS_673._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_673] @@ -484,20 +484,20 @@ Stage-0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_70] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_582] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_582] (rows=3923357 width=0) Conds:RS_67._col0=RS_626._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_626] PartitionCols:_col0 - Select Operator [SEL_616] (rows=1515 width=4) + Select Operator [SEL_616] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_608] (rows=1515 width=12) + Filter Operator [FIL_608] (rows=2235 width=12) predicate:((t_hour = 11) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_581] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_581] (rows=82152686 width=5) Conds:RS_692._col1=RS_663._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_663] @@ -520,7 +520,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_648] Group By Operator [GBY_640] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_627] (rows=1515 width=4) + Select Operator [SEL_627] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_616] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] @@ -535,7 +535,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_580] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_580] (rows=2979630 width=8) Conds:RS_44._col2=RS_672._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_672] @@ -544,20 +544,20 @@ Stage-0 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_579] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_579] (rows=4058523 width=0) Conds:RS_41._col0=RS_624._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_624] PartitionCols:_col0 - Select Operator [SEL_615] (rows=1515 width=4) + Select Operator [SEL_615] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_607] (rows=1515 width=12) + Filter Operator [FIL_607] (rows=2312 width=12) predicate:((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_578] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_578] (rows=82152686 width=5) Conds:RS_685._col1=RS_662._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_662] @@ -580,7 +580,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_647] Group By Operator [GBY_639] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_625] (rows=1515 width=4) + Select Operator [SEL_625] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_615] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized @@ -591,7 +591,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_577] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_577] (rows=2880396 width=8) Conds:RS_18._col2=RS_671._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_671] @@ -600,20 +600,20 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_576] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_576] (rows=3923357 width=0) Conds:RS_15._col0=RS_622._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_622] PartitionCols:_col0 - Select Operator [SEL_614] (rows=1515 width=4) + Select Operator [SEL_614] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_606] (rows=1515 width=12) + Filter Operator [FIL_606] (rows=2235 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_575] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_575] (rows=82152686 width=5) Conds:RS_658._col1=RS_661._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_661] @@ -636,7 +636,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_646] Group By Operator [GBY_638] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_623] (rows=1515 width=4) + Select Operator [SEL_623] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_614] <-Reducer 37 [CUSTOM_SIMPLE_EDGE] vectorized @@ -647,7 +647,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_179] Group By Operator [GBY_178] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_595] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_595] (rows=2880396 width=8) Conds:RS_174._col2=RS_677._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_677] @@ -656,20 +656,20 @@ Stage-0 <-Reducer 35 [SIMPLE_EDGE] SHUFFLE [RS_174] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_594] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_594] (rows=3923357 width=0) Conds:RS_171._col0=RS_634._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_634] PartitionCols:_col0 - Select Operator [SEL_620] (rows=1515 width=4) + Select Operator [SEL_620] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_612] (rows=1515 width=12) + Filter Operator [FIL_612] (rows=2235 width=12) predicate:((t_hour = 9) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_171] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_593] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_593] (rows=82152686 width=5) Conds:RS_720._col1=RS_667._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_667] @@ -692,7 +692,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_652] Group By Operator [GBY_644] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_635] (rows=1515 width=4) + Select Operator [SEL_635] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_620] <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized @@ -703,7 +703,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_205] Group By Operator [GBY_204] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_598] (rows=1352994 width=8) + Merge Join Operator [MERGEJOIN_598] (rows=2979630 width=8) Conds:RS_200._col2=RS_678._col0(Inner) <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_678] @@ -712,20 +712,20 @@ Stage-0 <-Reducer 39 [SIMPLE_EDGE] SHUFFLE [RS_200] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_597] (rows=1842898 width=0) + Merge Join Operator [MERGEJOIN_597] (rows=4058523 width=0) Conds:RS_197._col0=RS_636._col0(Inner),Output:["_col2"] <-Map 42 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_636] PartitionCols:_col0 - Select Operator [SEL_621] (rows=1515 width=4) + Select Operator [SEL_621] (rows=2312 width=4) Output:["_col0"] - Filter Operator [FIL_613] (rows=1515 width=12) + Filter Operator [FIL_613] (rows=2312 width=12) predicate:((t_hour = 9) and (t_minute < 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 38 [SIMPLE_EDGE] SHUFFLE [RS_197] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_596] (rows=56928540 width=4) + Merge Join Operator [MERGEJOIN_596] (rows=82152686 width=5) Conds:RS_727._col1=RS_668._col0(Inner),Output:["_col0","_col2"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_668] @@ -748,7 +748,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_653] Group By Operator [GBY_645] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_637] (rows=1515 width=4) + Select Operator [SEL_637] (rows=2312 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_621] diff --git a/ql/src/test/results/clientpositive/perf/tez/query90.q.out b/ql/src/test/results/clientpositive/perf/tez/query90.q.out index fef3b11f55..e51653cbbb 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query90.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query90.q.out @@ -83,7 +83,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_145] (rows=153010 width=8) + Merge Join Operator [MERGEJOIN_145] (rows=351832 width=8) Conds:RS_18._col1=RS_152._col0(Inner) <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_152] @@ -97,7 +97,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_144] (rows=1681936 width=3) + Merge Join Operator [MERGEJOIN_144] (rows=3867464 width=3) Conds:RS_15._col0=RS_169._col0(Inner),Output:["_col1"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_169] @@ -111,7 +111,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_143] (rows=15977923 width=7) + Merge Join Operator [MERGEJOIN_143] (rows=36739842 width=7) Conds:RS_161._col2=RS_164._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_161] @@ -136,9 +136,9 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_164] PartitionCols:_col0 - Select Operator [SEL_163] (rows=511 width=4) + Select Operator [SEL_163] (rows=1175 width=4) Output:["_col0"] - Filter Operator [FIL_162] (rows=511 width=7) + Filter Operator [FIL_162] (rows=1175 width=7) predicate:(wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) TableScan [TS_3] (rows=4602 width=7) default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk","wp_char_count"] @@ -150,7 +150,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_148] (rows=153010 width=8) + Merge Join Operator [MERGEJOIN_148] (rows=351832 width=8) Conds:RS_44._col1=RS_154._col0(Inner) <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_154] @@ -159,7 +159,7 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_147] (rows=1681936 width=3) + Merge Join Operator [MERGEJOIN_147] (rows=3867464 width=3) Conds:RS_41._col0=RS_170._col0(Inner),Output:["_col1"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_170] diff --git a/ql/src/test/results/clientpositive/perf/tez/query96.q.out b/ql/src/test/results/clientpositive/perf/tez/query96.q.out index 2de80f92a4..54375515ce 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query96.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query96.q.out @@ -60,7 +60,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_72] (rows=1084713 width=8) + Merge Join Operator [MERGEJOIN_72] (rows=1600220 width=8) Conds:RS_18._col2=RS_89._col0(Inner) <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_89] @@ -74,7 +74,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_71] (rows=1477476 width=0) + Merge Join Operator [MERGEJOIN_71] (rows=2179643 width=0) Conds:RS_15._col1=RS_86._col0(Inner),Output:["_col2"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_86] @@ -88,14 +88,14 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_70] (rows=16240953 width=0) + Merge Join Operator [MERGEJOIN_70] (rows=23959428 width=0) Conds:RS_83._col0=RS_75._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_75] PartitionCols:_col0 - Select Operator [SEL_74] (rows=1515 width=4) + Select Operator [SEL_74] (rows=2235 width=4) Output:["_col0"] - Filter Operator [FIL_73] (rows=1515 width=12) + Filter Operator [FIL_73] (rows=2235 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) TableScan [TS_3] (rows=86400 width=12) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] @@ -116,7 +116,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_78] Group By Operator [GBY_77] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_76] (rows=1515 width=4) + Select Operator [SEL_76] (rows=2235 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_74] diff --git a/ql/src/test/results/clientpositive/remove_exprs_stats.q.out b/ql/src/test/results/clientpositive/remove_exprs_stats.q.out index 6a12ed63c7..3f7db2a093 100644 --- a/ql/src/test/results/clientpositive/remove_exprs_stats.q.out +++ b/ql/src/test/results/clientpositive/remove_exprs_stats.q.out @@ -216,14 +216,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid < 6) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -324,14 +324,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid >= 6) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -449,14 +449,14 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (locid <= 1) (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/sample7.q.out b/ql/src/test/results/clientpositive/sample7.q.out index c32105e21d..723b607c9c 100644 --- a/ql/src/test/results/clientpositive/sample7.q.out +++ b/ql/src/test/results/clientpositive/sample7.q.out @@ -42,17 +42,17 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: ((((hash(key) & 2147483647) % 4) = 0) and (key > 100)) (type: boolean) - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -83,7 +83,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') minReductionHashAggr: 0.99 diff --git a/ql/src/test/results/clientpositive/spark/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/spark/dynpart_sort_optimization.q.out index 0d3ec57a74..f6ef649dbe 100644 --- a/ql/src/test/results/clientpositive/spark/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/spark/dynpart_sort_optimization.q.out @@ -3241,16 +3241,16 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 27Y) or t is null) (type: boolean) - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: tinyint) sort order: + Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) Reducer 2 Reduce Operator Tree: @@ -3260,7 +3260,7 @@ STAGE PLANS: File Output Operator compressed: false Dp Sort State: PARTITION_SORTED - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3397,14 +3397,14 @@ STAGE PLANS: Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t > 27Y) or t is null) (type: boolean) - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 352 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 804 Data size: 19288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out index e3bf702e25..eb43b0565c 100644 --- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out @@ -2591,16 +2591,16 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_24] - Select Operator [SEL_23] (rows=41 width=223) + Select Operator [SEL_23] (rows=33 width=223) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_22] (rows=41 width=229) + Filter Operator [FIL_22] (rows=33 width=227) predicate:((_col7 is null or (_col4 = 0L) or _col4 is null) and ((_col5 < _col4) is not true or (_col4 = 0L) or _col4 is null or _col7 is not null or _col0 is null) and (_col0 is not null or (_col4 = 0L) or _col4 is null or _col7 is not null)) - Join Operator [JOIN_21] (rows=41 width=229) + Join Operator [JOIN_21] (rows=33 width=227) Output:["_col0","_col1","_col2","_col4","_col5","_col7"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col2"} <-Reducer 2 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_19] PartitionCols:_col0, _col1 - Join Operator [JOIN_18] (rows=36 width=227) + Join Operator [JOIN_18] (rows=31 width=226) Output:["_col0","_col1","_col2","_col4","_col5"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col1","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_16] @@ -2612,34 +2612,34 @@ Stage-0 <-Reducer 5 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_17] PartitionCols:_col0 - Group By Operator [GBY_7] (rows=2 width=114) + Group By Operator [GBY_7] (rows=1 width=114) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 4 [GROUP] GROUP [RS_6] PartitionCols:_col0 - Group By Operator [GBY_5] (rows=2 width=114) + Group By Operator [GBY_5] (rows=1 width=114) Output:["_col0","_col1","_col2"],aggregations:["count()","count(p_name)"],keys:p_mfgr - Select Operator [SEL_4] (rows=8 width=223) + Select Operator [SEL_4] (rows=5 width=223) Output:["p_name","p_mfgr"] - Filter Operator [FIL_25] (rows=8 width=223) + Filter Operator [FIL_25] (rows=5 width=223) predicate:((p_size < 10) and p_mfgr is not null) TableScan [TS_2] (rows=26 width=223) default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_name","p_mfgr","p_size"] <-Reducer 7 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_20] PartitionCols:_col0, _col2 - Select Operator [SEL_15] (rows=4 width=223) + Select Operator [SEL_15] (rows=2 width=223) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_14] (rows=4 width=219) + Group By Operator [GBY_14] (rows=2 width=219) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Map 6 [GROUP] GROUP [RS_13] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=4 width=219) + Group By Operator [GBY_12] (rows=2 width=219) Output:["_col0","_col1"],keys:p_name, p_mfgr - Select Operator [SEL_11] (rows=8 width=223) + Select Operator [SEL_11] (rows=5 width=223) Output:["p_name","p_mfgr"] - Filter Operator [FIL_26] (rows=8 width=223) + Filter Operator [FIL_26] (rows=5 width=223) predicate:((p_size < 10) and p_mfgr is not null and p_name is not null) TableScan [TS_9] (rows=26 width=223) default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_name","p_mfgr","p_size"] @@ -2715,7 +2715,7 @@ Stage-0 GROUP [RS_6] Group By Operator [GBY_5] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(p_size)","count(p_size)"] - Filter Operator [FIL_35] (rows=8 width=4) + Filter Operator [FIL_35] (rows=5 width=4) predicate:(p_size < 10) TableScan [TS_2] (rows=26 width=4) default@part,part,Tbl:COMPLETE,Col:COMPLETE,Output:["p_size"] diff --git a/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out b/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out index 0c46e6c7b3..fe47ac7de1 100644 --- a/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out +++ b/ql/src/test/results/clientpositive/tez/acid_vectorization_original_tez.q.out @@ -454,15 +454,15 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 41920 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t < 100Y) and (b = 4294967363L)) (type: boolean) - Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -470,10 +470,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -527,15 +527,15 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 41920 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t < 100Y) and (b = 4294967363L)) (type: boolean) - Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ROW__ID (type: struct), t (type: tinyint), si (type: smallint), i (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint), _col2 (type: smallint), _col3 (type: int) Execution mode: vectorized Reducer 2 @@ -544,10 +544,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 616 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -603,16 +603,16 @@ STAGE PLANS: Statistics: Num rows: 2098 Data size: 706986 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((b = 4294967363L) and (t < 100Y)) (type: boolean) - Statistics: Num rows: 2 Data size: 674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2022 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ROW__ID (type: struct), t (type: tinyint), si (type: smallint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) outputColumnNames: _col0, _col1, _col2, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint), _col2 (type: smallint), _col5 (type: float), _col6 (type: double), _col7 (type: boolean), _col8 (type: string), _col9 (type: timestamp), _col10 (type: decimal(4,2)), _col11 (type: binary) Execution mode: vectorized Reducer 2 @@ -621,10 +621,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), 0 (type: int), 4294967363L (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: boolean), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: decimal(4,2)), VALUE._col9 (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 834 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out index c512735c8a..16ecfaa9a6 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out @@ -48,27 +48,27 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_12] - Select Operator [SEL_11] (rows=2048/10 width=552) + Select Operator [SEL_11] (rows=4626/10 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_27] (rows=2048/10 width=552) + Merge Join Operator [MERGEJOIN_27] (rows=4626/10 width=552) Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] PartitionCols:_col2 - Select Operator [SEL_2] (rows=1365/10 width=251) + Select Operator [SEL_2] (rows=3078/10 width=251) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_15] (rows=1365/10 width=251) + Filter Operator [FIL_15] (rows=3078/10 width=251) predicate:cint BETWEEN 1000000 AND 3000000 TableScan [TS_0] (rows=12288/12288 width=251) default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] <-Map 4 [SIMPLE_EDGE] SHUFFLE [RS_7] PartitionCols:_col2 - Select Operator [SEL_5] (rows=1019/10 width=251) + Select Operator [SEL_5] (rows=2298/10 width=251) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_16] (rows=1019/10 width=251) + Filter Operator [FIL_16] (rows=2298/10 width=251) predicate:(cint BETWEEN 1000000 AND 3000000 and cbigint is not null) TableScan [TS_3] (rows=12288/12288 width=251) default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] @@ -151,23 +151,23 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_28] (rows=2048/10 width=8) + Merge Join Operator [MERGEJOIN_28] (rows=4626/10 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] PartitionCols:_col0 - Select Operator [SEL_2] (rows=1365/10 width=2) + Select Operator [SEL_2] (rows=3078/10 width=2) Output:["_col0"] - Filter Operator [FIL_16] (rows=1365/10 width=2) + Filter Operator [FIL_16] (rows=3078/10 width=2) predicate:cint BETWEEN 1000000 AND 3000000 TableScan [TS_0] (rows=12288/12288 width=2) default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["cint"] <-Map 4 [SIMPLE_EDGE] SHUFFLE [RS_7] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1019/10 width=2) + Select Operator [SEL_5] (rows=2298/10 width=2) Output:["_col0"] - Filter Operator [FIL_17] (rows=1019/10 width=8) + Filter Operator [FIL_17] (rows=2298/10 width=8) predicate:(cint BETWEEN 1000000 AND 3000000 and cbigint is not null) TableScan [TS_3] (rows=12288/12288 width=8) default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["cint","cbigint"] @@ -244,32 +244,32 @@ Stage-0 Stage-1 Reducer 4 File Output Operator [FS_15] - Select Operator [SEL_14] (rows=1366/5 width=11) + Select Operator [SEL_14] (rows=3079/5 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_13] - Group By Operator [GBY_11] (rows=1366/5 width=11) + Group By Operator [GBY_11] (rows=3079/5 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_30] (rows=2048/10 width=3) + Merge Join Operator [MERGEJOIN_30] (rows=4626/10 width=3) Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] PartitionCols:_col1 - Select Operator [SEL_2] (rows=1365/10 width=5) + Select Operator [SEL_2] (rows=3078/10 width=5) Output:["_col0","_col1"] - Filter Operator [FIL_18] (rows=1365/10 width=5) + Filter Operator [FIL_18] (rows=3078/10 width=5) predicate:cint BETWEEN 1000000 AND 3000000 TableScan [TS_0] (rows=12288/12288 width=5) default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["csmallint","cint"] <-Map 5 [SIMPLE_EDGE] SHUFFLE [RS_7] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1019/10 width=2) + Select Operator [SEL_5] (rows=2298/10 width=2) Output:["_col0"] - Filter Operator [FIL_19] (rows=1019/10 width=8) + Filter Operator [FIL_19] (rows=2298/10 width=8) predicate:(cint BETWEEN 1000000 AND 3000000 and cbigint is not null) TableScan [TS_3] (rows=12288/12288 width=8) default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["cint","cbigint"] diff --git a/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out b/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out index a786b6142b..cd25183e82 100644 --- a/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_non_string_partition.q.out @@ -67,7 +67,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 0) predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 @@ -75,7 +75,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 4] - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -83,7 +83,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: tinyint) Execution mode: vectorized @@ -112,7 +112,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: @@ -196,7 +196,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 0) predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 @@ -204,7 +204,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -212,7 +212,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -240,7 +240,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/union_pos_alias.q.out b/ql/src/test/results/clientpositive/union_pos_alias.q.out index 80d29379b8..fac08b26d0 100644 --- a/ql/src/test/results/clientpositive/union_pos_alias.q.out +++ b/ql/src/test/results/clientpositive/union_pos_alias.q.out @@ -401,16 +401,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -421,16 +421,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -488,23 +488,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int), _col1 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 8036 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 41 Data size: 8036 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -513,7 +513,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 8036 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -526,35 +526,35 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 82 Data size: 16072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col2), count(_col2) keys: _col0 (type: int), _col1 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 8364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 41 Data size: 8364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 82 Data size: 16072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col2), count(_col2) keys: _col0 (type: int), _col1 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 8364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 41 Data size: 8364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -562,7 +562,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 8364 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 = 2L) (type: boolean) Statistics: Num rows: 1 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE @@ -594,23 +594,23 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 0) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int), _col1 (type: string) minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 8036 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 41 Data size: 8036 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -619,7 +619,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 41 Data size: 8036 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out b/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out index 5580308c1e..40c2a43820 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out @@ -67,7 +67,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDecimalColGreaterDecimalScalar(col 1:decimal(20,10), val 0), FilterDecimalColLessDecimalScalar(col 1:decimal(20,10), val 12345.5678), FilterDecimalColGreaterDecimalScalar(col 2:decimal(23,14), val 1000), SelectColumnIsNotNull(col 0:double), FilterDecimalColNotEqualDecimalScalar(col 2:decimal(23,14), val 0)) predicate: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 > 1000) and cdouble is not null and (cdecimal2 <> 0)) (type: boolean) - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(26,14)), ((cdecimal1 + 2.34) / cdecimal2) (type: decimal(38,13)), (cdecimal1 * (cdecimal2 / 3.4)) (type: decimal(38,17)), (cdecimal1 % 10) (type: decimal(12,10)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), CAST( cdecimal2 AS STRING) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -76,7 +76,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] selectExpressions: DecimalColAddDecimalColumn(col 1:decimal(20,10), col 2:decimal(23,14)) -> 4:decimal(25,14), DecimalColSubtractDecimalColumn(col 1:decimal(20,10), col 5:decimal(25,14))(children: DecimalScalarMultiplyDecimalColumn(val 2, col 2:decimal(23,14)) -> 5:decimal(25,14)) -> 6:decimal(26,14), DecimalColDivideDecimalColumn(col 7:decimal(21,10), col 2:decimal(23,14))(children: DecimalColAddDecimalScalar(col 1:decimal(20,10), val 2.34) -> 7:decimal(21,10)) -> 8:decimal(38,13), DecimalColMultiplyDecimalColumn(col 1:decimal(20,10), col 9:decimal(27,17))(children: DecimalColDivideDecimalScalar(col 2:decimal(23,14), val 3.4) -> 9:decimal(27,17)) -> 10:decimal(38,17), DecimalColModuloDecimalScalar(col 1:decimal(20,10), val 10) -> 11:decimal(12,10), CastDecimalToLong(col 1:decimal(20,10)) -> 12:int, CastDecimalToLong(col 2:decimal(23,14)) -> 13:smallint, CastDecimalToLong(col 2:decimal(23,14)) -> 14:tinyint, CastDecimalToLong(col 1:decimal(20,10)) -> 15:bigint, CastDecimalToBoolean(col 1:decimal(20,10)) -> 16:boolean, CastDecimalToDouble(col 2:decimal(23,14)) -> 17:double, CastDecimalToFloat(col 1:decimal(20,10)) -> 18:float, CastDecimalToString(col 2:decimal(23,14)) -> 19:string, CastDecimalToTimestamp(col 1:decimal(20,10)) -> 20:timestamp - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(25,14)), _col1 (type: decimal(26,14)), _col2 (type: decimal(38,13)), _col3 (type: decimal(38,17)), _col4 (type: decimal(12,10)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) sort order: ++++++++++++++ @@ -85,7 +85,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -111,13 +111,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(25,14)), KEY.reducesinkkey1 (type: decimal(26,14)), KEY.reducesinkkey2 (type: decimal(38,13)), KEY.reducesinkkey3 (type: decimal(38,17)), KEY.reducesinkkey4 (type: decimal(12,10)), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: smallint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: string), KEY.reducesinkkey13 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,7 +216,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDecimal64ColGreaterDecimal64Scalar(col 1:decimal(10,3)/DECIMAL_64, val 0), FilterDecimalColLessDecimalScalar(col 4:decimal(10,3), val 12345.5678)(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)), FilterDecimal64ColGreaterDecimal64Scalar(col 2:decimal(7,2)/DECIMAL_64, val 100000), SelectColumnIsNotNull(col 0:double), FilterDecimal64ColNotEqualDecimal64Scalar(col 2:decimal(7,2)/DECIMAL_64, val 0)) predicate: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 > 1000) and cdouble is not null and (cdecimal2 <> 0)) (type: boolean) - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(11,3)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(11,3)), ((cdecimal1 + 2.34) / cdecimal2) (type: decimal(21,11)), (cdecimal1 * (cdecimal2 / 3.4)) (type: decimal(23,9)), (cdecimal1 % 10) (type: decimal(5,3)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), CAST( cdecimal2 AS STRING) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -225,7 +225,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [7, 11, 14, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36, 38] selectExpressions: DecimalColAddDecimalColumn(col 5:decimal(10,3), col 6:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 5:decimal(10,3), ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 6:decimal(7,2)) -> 7:decimal(11,3), DecimalColSubtractDecimalColumn(col 8:decimal(10,3), col 10:decimal(9,2))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 8:decimal(10,3), DecimalScalarMultiplyDecimalColumn(val 2, col 9:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 9:decimal(7,2)) -> 10:decimal(9,2)) -> 11:decimal(11,3), DecimalColDivideDecimalColumn(col 39:decimal(11,3), col 13:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 12:decimal(11,3)/DECIMAL_64)(children: Decimal64ColAddDecimal64Scalar(col 1:decimal(10,3)/DECIMAL_64, decimal64Val 2340, decimalVal 2.34) -> 12:decimal(11,3)/DECIMAL_64) -> 39:decimal(11,3), ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 13:decimal(7,2)) -> 14:decimal(21,11), DecimalColMultiplyDecimalColumn(col 15:decimal(10,3), col 17:decimal(12,6))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 15:decimal(10,3), DecimalColDivideDecimalScalar(col 16:decimal(7,2), val 3.4)(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 16:decimal(7,2)) -> 17:decimal(12,6)) -> 18:decimal(23,9), DecimalColModuloDecimalScalar(col 19:decimal(10,3), val 10)(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 19:decimal(10,3)) -> 20:decimal(5,3), CastDecimalToLong(col 21:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 21:decimal(10,3)) -> 22:int, CastDecimalToLong(col 23:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 23:decimal(7,2)) -> 24:smallint, CastDecimalToLong(col 25:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 25:decimal(7,2)) -> 26:tinyint, CastDecimalToLong(col 27:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 27:decimal(10,3)) -> 28:bigint, CastDecimalToBoolean(col 29:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 29:decimal(10,3)) -> 30:boolean, CastDecimalToDouble(col 31:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 31:decimal(7,2)) -> 32:double, CastDecimalToFloat(col 33:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 33:decimal(10,3)) -> 34:float, CastDecimalToString(col 35:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 35:decimal(7,2)) -> 36:string, CastDecimalToTimestamp(col 37:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 37:decimal(10,3)) -> 38:timestamp - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(11,3)), _col1 (type: decimal(11,3)), _col2 (type: decimal(21,11)), _col3 (type: decimal(23,9)), _col4 (type: decimal(5,3)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) sort order: ++++++++++++++ @@ -234,7 +234,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -260,13 +260,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(11,3)), KEY.reducesinkkey1 (type: decimal(11,3)), KEY.reducesinkkey2 (type: decimal(21,11)), KEY.reducesinkkey3 (type: decimal(23,9)), KEY.reducesinkkey4 (type: decimal(5,3)), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: smallint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: string), KEY.reducesinkkey13 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 751 Data size: 165540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_elt.q.out b/ql/src/test/results/clientpositive/vector_elt.q.out index a972ec713a..116e075d26 100644 --- a/ql/src/test/results/clientpositive/vector_elt.q.out +++ b/ql/src/test/results/clientpositive/vector_elt.q.out @@ -34,7 +34,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:tinyint, val 0) predicate: (ctinyint > 0Y) (type: boolean) - Statistics: Num rows: 4096 Data size: 312018 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6046 Data size: 460522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -43,7 +43,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [14, 6, 2, 18] selectExpressions: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 14:int, VectorElt(columns [16, 6, 17])(children: LongColAddLongScalar(col 15:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 15:int) -> 16:int, col 6:string, CastLongToString(col 2:int) -> 17:string) -> 18:string - Statistics: Num rows: 4096 Data size: 1069830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6046 Data size: 1579114 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/vector_non_string_partition.q.out b/ql/src/test/results/clientpositive/vector_non_string_partition.q.out index 88f45875c2..71d2a76f7b 100644 --- a/ql/src/test/results/clientpositive/vector_non_string_partition.q.out +++ b/ql/src/test/results/clientpositive/vector_non_string_partition.q.out @@ -61,7 +61,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 0) predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 @@ -69,7 +69,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 4] - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -78,7 +78,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: tinyint) Execution mode: vectorized @@ -99,7 +99,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 12296 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE @@ -171,7 +171,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 0) predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 @@ -179,7 +179,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -188,7 +188,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -208,7 +208,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1537 Data size: 156774 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/vectorization_10.q.out b/ql/src/test/results/clientpositive/vectorization_10.q.out index 81182cc361..d13536b560 100644 --- a/ql/src/test/results/clientpositive/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/vectorization_10.q.out @@ -75,7 +75,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a)))) predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 9557 Data size: 1937820 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -84,13 +84,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 8, 0, 10, 6, 16, 18, 21, 22, 24, 25, 26, 28, 31, 33] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleColAddDoubleColumn(col 5:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, DoubleColModuloDoubleScalar(col 20:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: CastLongToDouble(col 1:smallint) -> 19:double) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 5:double) -> 22:double, DoubleColModuloDoubleColumn(col 23:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 23:double) -> 24:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 25:smallint, DoubleColUnaryMinus(col 5:double) -> 26:double, LongColMultiplyLongColumn(col 3:bigint, col 27:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 27:smallint) -> 28:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 30:double)(children: DoubleColAddDoubleColumn(col 5:double, col 29:double)(children: CastLongToDouble(col 1:smallint) -> 29:double) -> 30:double) -> 31:double, DoubleColUnaryMinus(col 32:double)(children: DoubleColUnaryMinus(col 5:double) -> 32:double) -> 33:double - Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2434654 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12288 Data size: 2434654 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out index 77af1addc9..3552007f8d 100644 --- a/ql/src/test/results/clientpositive/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/vectorization_13.q.out @@ -94,7 +94,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 15:decimal(11,4)))) predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -103,7 +103,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -118,7 +118,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -128,7 +128,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -156,11 +156,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 64822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -183,7 +183,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -209,7 +209,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE @@ -430,7 +430,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimalColLessDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 15:decimal(11,4)))) predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -439,7 +439,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1386 Data size: 228984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -454,7 +454,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -464,7 +464,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 693 Data size: 129752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -486,11 +486,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 64822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -512,7 +512,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -532,7 +532,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 346 Data size: 113262 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/vectorization_14.q.out b/ql/src/test/results/clientpositive/vectorization_14.q.out index a1c4b26650..c73cf60821 100644 --- a/ql/src/test/results/clientpositive/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/vectorization_14.q.out @@ -94,7 +94,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 14:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 14:float)), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 15:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 15:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp))) predicate: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 758 Data size: 132082 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -103,7 +103,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 4, 6, 10, 5, 17, 22, 4, 23] selectExpressions: DoubleColUnaryMinus(col 16:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 19:double, col 21:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 20:double) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 23:double - Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 758 Data size: 132082 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) Group By Vectorization: @@ -118,7 +118,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 379 Data size: 66108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -128,7 +128,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 379 Data size: 66108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -156,11 +156,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 151 Data size: 26432 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 33008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -183,7 +183,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Execution mode: vectorized Map Vectorization: @@ -209,10 +209,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 189 Data size: 45860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out index 695a05ace5..2dfcc775ad 100644 --- a/ql/src/test/results/clientpositive/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/vectorization_16.q.out @@ -67,7 +67,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -76,7 +76,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -91,7 +91,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -101,7 +101,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -129,14 +129,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 227586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_17.q.out b/ql/src/test/results/clientpositive/vectorization_17.q.out index c9d106c9d2..ea65db132a 100644 --- a/ql/src/test/results/clientpositive/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/vectorization_17.q.out @@ -75,7 +75,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)))) predicate: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) - Statistics: Num rows: 4096 Data size: 549274 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 823456 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -84,7 +84,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 17, 20, 22, 24, 26, 29] selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 17:double, DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 18:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 18:double) -> 19:double) -> 20:double, DoubleColDivideDoubleColumn(col 5:double, col 21:double)(children: CastLongToDouble(col 2:int) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColUnaryMinus(col 5:double) -> 23:double) -> 24:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 25:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 25:decimal(19,0)) -> 26:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 28:double)(children: DoubleColUnaryMinus(col 27:double)(children: DoubleColUnaryMinus(col 5:double) -> 27:double) -> 28:double) -> 29:double - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -93,7 +93,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -119,10 +119,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6141 Data size: 1818460 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_7.q.out b/ql/src/test/results/clientpositive/vectorization_7.q.out index 85cb01bce8..880a4c3fd1 100644 --- a/ql/src/test/results/clientpositive/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/vectorization_7.q.out @@ -81,7 +81,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 2711364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -90,7 +90,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -99,7 +99,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -125,7 +125,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE @@ -306,7 +306,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 2711364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -315,7 +315,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -324,7 +324,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -344,7 +344,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11033 Data size: 1865892 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out index 695a05ace5..2dfcc775ad 100644 --- a/ql/src/test/results/clientpositive/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/vectorization_9.q.out @@ -67,7 +67,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -76,7 +76,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6144 Data size: 1154088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -91,7 +91,7 @@ STAGE PLANS: minReductionHashAggr: 0.99 mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -101,7 +101,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3072 Data size: 455172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -129,14 +129,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 227586 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1536 Data size: 461058 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_limit.q.out b/ql/src/test/results/clientpositive/vectorization_limit.q.out index d91fa77341..43612a4c9b 100644 --- a/ql/src/test/results/clientpositive/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -27,15 +27,15 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -55,7 +55,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out index 90ab966d3c..4b43c94585 100644 --- a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out @@ -25,11 +25,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 2 Offset of rows: 3