HIVE-16022: BloomFilter check not showing up in MERGE statement queries (Jason Dere reviewed by Gunt her Hagleitner)
Change-Id: Ie773cdb3ac5cac2174b06b7d64f8c72d6a17cb06 Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/c3d311f4 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/c3d311f4 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/c3d311f4 Branch: refs/heads/branch-2.2 Commit: c3d311f43eee59adaf6806cb366480e39e7cffb0 Parents: 127deb2 Author: Jason Dere <jd...@hortonworks.com> Authored: Wed Mar 1 11:40:40 2017 -0800 Committer: Owen O'Malley <omal...@apache.org> Committed: Tue Mar 28 15:27:54 2017 -0700 ---------------------------------------------------------------------- .../test/resources/testconfiguration.properties | 1 + .../hadoop/hive/ql/exec/OperatorUtils.java | 7 + .../DynamicPartitionPruningOptimization.java | 11 +- .../dynamic_semijoin_reduction_3.q | 37 + .../llap/dynamic_partition_pruning.q.out | 4 +- .../llap/dynamic_semijoin_reduction.q.out | 28 +- .../llap/dynamic_semijoin_reduction_2.q.out | 4 +- .../llap/dynamic_semijoin_reduction_3.q.out | 765 +++++++++++++++++++ .../results/clientpositive/llap/orc_llap.q.out | 8 +- .../vectorized_dynamic_partition_pruning.q.out | 4 +- .../vectorized_dynamic_semijoin_reduction.q.out | 28 +- ...vectorized_dynamic_semijoin_reduction2.q.out | 32 +- .../tez/dynamic_partition_pruning.q.out | 4 +- .../clientpositive/tez/explainuser_3.q.out | 4 +- .../results/clientpositive/tez/mergejoin.q.out | 48 +- .../vectorized_dynamic_partition_pruning.q.out | 4 +- 16 files changed, 900 insertions(+), 89 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/itests/src/test/resources/testconfiguration.properties ---------------------------------------------------------------------- diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties index 9720f76..891bf11 100644 --- a/itests/src/test/resources/testconfiguration.properties +++ b/itests/src/test/resources/testconfiguration.properties @@ -510,6 +510,7 @@ minillap.query.files=cross_prod_1.q,\ cross_prod_3.q,\ dynamic_semijoin_reduction.q,\ dynamic_semijoin_reduction_2.q,\ + dynamic_semijoin_reduction_3.q,\ except_distinct.q,\ intersect_all.q,\ intersect_distinct.q,\ http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/java/org/apache/hadoop/hive/ql/exec/OperatorUtils.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/OperatorUtils.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/OperatorUtils.java index d294e25..51faf1d 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/OperatorUtils.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/OperatorUtils.java @@ -346,4 +346,11 @@ public class OperatorUtils { } } } + + public static String getOpNamePretty(Operator<?> op) { + if (op instanceof TableScanOperator) { + return op.toString() + " (" + ((TableScanOperator) op).getConf().getAlias() + ")"; + } + return op.toString(); + } } http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java index 3085f5d..e6f21e9 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/DynamicPartitionPruningOptimization.java @@ -239,7 +239,6 @@ public class DynamicPartitionPruningOptimization implements NodeProcessor { betweenArgs.add(new ExprNodeDynamicValueDesc(new DynamicValue(keyBaseAlias + "_max", ctx.desc.getTypeInfo()))); ExprNodeDesc betweenNode = ExprNodeGenericFuncDesc.newInstance( FunctionRegistry.getFunctionInfo("between").getGenericUDF(), betweenArgs); - replaceExprNode(ctx, desc, betweenNode); // add column expression for bloom filter List<ExprNodeDesc> bloomFilterArgs = new ArrayList<ExprNodeDesc>(); bloomFilterArgs.add(ctx.parent.getChildren().get(0)); @@ -249,10 +248,12 @@ public class DynamicPartitionPruningOptimization implements NodeProcessor { ExprNodeDesc bloomFilterNode = ExprNodeGenericFuncDesc.newInstance( FunctionRegistry.getFunctionInfo("in_bloom_filter"). getGenericUDF(), bloomFilterArgs); - // ctx may not have the grandparent but it is set in filterDesc by now. - ExprNodeDesc grandParent = ctx.grandParent == null ? - desc.getPredicate() : ctx.grandParent; - grandParent.getChildren().add(bloomFilterNode); + List<ExprNodeDesc> andArgs = new ArrayList<ExprNodeDesc>(); + andArgs.add(betweenNode); + andArgs.add(bloomFilterNode); + ExprNodeDesc andExpr = ExprNodeGenericFuncDesc.newInstance( + FunctionRegistry.getFunctionInfo("and").getGenericUDF(), andArgs); + replaceExprNode(ctx, desc, andExpr); } else { ExprNodeDesc replaceNode = new ExprNodeConstantDesc(ctx.parent.getTypeInfo(), true); replaceExprNode(ctx, desc, replaceNode); http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/queries/clientpositive/dynamic_semijoin_reduction_3.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/dynamic_semijoin_reduction_3.q b/ql/src/test/queries/clientpositive/dynamic_semijoin_reduction_3.q new file mode 100644 index 0000000..adfc7a6 --- /dev/null +++ b/ql/src/test/queries/clientpositive/dynamic_semijoin_reduction_3.q @@ -0,0 +1,37 @@ +set hive.mapred.mode=nonstrict; +set hive.support.concurrency=true; +set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager; +set hive.explain.user=false; +set hive.merge.cardinality.check=true; + +set hive.compute.query.using.stats=false; +set hive.mapred.mode=nonstrict; +set hive.optimize.ppd=true; +set hive.ppd.remove.duplicatefilters=true; +set hive.tez.dynamic.partition.pruning=true; +set hive.tez.dynamic.semijoin.reduction=true; +set hive.optimize.metadataonly=false; +set hive.optimize.index.filter=true; + +-- Try with merge statements +create table acidTbl(a int, b int) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true'); +create table nonAcidOrcTbl(a int, b int) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='false'); + +--expect a cardinality check because there is update and hive.merge.cardinality.check=true by default +explain merge into acidTbl as t using nonAcidOrcTbl s ON t.a = s.a +WHEN MATCHED AND s.a > 8 THEN DELETE +WHEN MATCHED THEN UPDATE SET b = 7 +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b); + +--now we expect no cardinality check since only have insert clause +explain merge into acidTbl as t using nonAcidOrcTbl s ON t.a = s.a +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b); + +explain merge into acidTbl as t using ( + select * from nonAcidOrcTbl where a > 0 + union all + select * from nonAcidOrcTbl where b > 0 +) s ON t.a = s.a +WHEN MATCHED AND s.a > 8 THEN DELETE +WHEN MATCHED THEN UPDATE SET b = 7 +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b); http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out index b2955ed..d28bafb 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out @@ -3187,10 +3187,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hr) = 13.0) and hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter))) (type: boolean) + filterExpr: ((UDFToDouble(hr) = 13.0) and (hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter)))) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter))) (type: boolean) + predicate: ((UDFToDouble(hr) = 13.0) and (hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter)))) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out index 385b5cf..c9cf19a 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out @@ -242,10 +242,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date - filterExpr: (key is not null and key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter))) (type: boolean) + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter))) (type: boolean) + predicate: (key is not null and (key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -659,10 +659,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date - filterExpr: (key is not null and key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter))) (type: boolean) + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter))) (type: boolean) + predicate: (key is not null and (key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -738,10 +738,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_int - filterExpr: (cstring is not null and cstring BETWEEN DynamicValue(RS_9_srcpart_date_cstring_min) AND DynamicValue(RS_9_srcpart_date_cstring_max) and cstring BETWEEN DynamicValue(RS_10_srcpart_small_cstring_min) AND DynamicValue(RS_10_srcpart_small_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_9_srcpart_date_cstring_bloom_filter)) and in_bloom_filter(cstring, DynamicValue(RS_10_srcpart_small_cstring_bloom_filter))) (type: boolean) + filterExpr: (cstring is not null and (cstring BETWEEN DynamicValue(RS_9_srcpart_date_cstring_min) AND DynamicValue(RS_9_srcpart_date_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_9_srcpart_date_cstring_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_10_srcpart_small_cstring_min) AND DynamicValue(RS_10_srcpart_small_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_10_srcpart_small_cstring_bloom_filter)))) (type: boolean) Statistics: Num rows: 12288 Data size: 926570 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cstring is not null and cstring BETWEEN DynamicValue(RS_9_srcpart_date_cstring_min) AND DynamicValue(RS_9_srcpart_date_cstring_max) and cstring BETWEEN DynamicValue(RS_10_srcpart_small_cstring_min) AND DynamicValue(RS_10_srcpart_small_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_9_srcpart_date_cstring_bloom_filter)) and in_bloom_filter(cstring, DynamicValue(RS_10_srcpart_small_cstring_bloom_filter))) (type: boolean) + predicate: (cstring is not null and (cstring BETWEEN DynamicValue(RS_9_srcpart_date_cstring_min) AND DynamicValue(RS_9_srcpart_date_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_9_srcpart_date_cstring_bloom_filter))) and (cstring BETWEEN DynamicValue(RS_10_srcpart_small_cstring_min) AND DynamicValue(RS_10_srcpart_small_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_10_srcpart_small_cstring_bloom_filter)))) (type: boolean) Statistics: Num rows: 12288 Data size: 926570 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring (type: string) @@ -1014,10 +1014,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date - filterExpr: (key is not null and value is not null and key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and value BETWEEN DynamicValue(RS_7_srcpart_small_value_min) AND DynamicValue(RS_7_srcpart_small_value_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter)) and in_bloom_filter(value, DynamicValue(RS_7_srcpart_small_value_bloom_filter))) (type: boolean) + filterExpr: (key is not null and value is not null and (key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter))) and (value BETWEEN DynamicValue(RS_7_srcpart_small_value_min) AND DynamicValue(RS_7_srcpart_small_value_max) and in_bloom_filter(value, DynamicValue(RS_7_srcpart_small_value_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null and key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and value BETWEEN DynamicValue(RS_7_srcpart_small_value_min) AND DynamicValue(RS_7_srcpart_small_value_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter)) and in_bloom_filter(value, DynamicValue(RS_7_srcpart_small_value_bloom_filter))) (type: boolean) + predicate: (key is not null and value is not null and (key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter))) and (value BETWEEN DynamicValue(RS_7_srcpart_small_value_min) AND DynamicValue(RS_7_srcpart_small_value_max) and in_bloom_filter(value, DynamicValue(RS_7_srcpart_small_value_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -1324,10 +1324,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date - filterExpr: (key is not null and value is not null and key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter))) (type: boolean) + filterExpr: (key is not null and value is not null and (key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and value is not null and key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter))) (type: boolean) + predicate: (key is not null and value is not null and (key BETWEEN DynamicValue(RS_10_srcpart_small_key_min) AND DynamicValue(RS_10_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_10_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -1378,10 +1378,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_int - filterExpr: (cstring is not null and cstring BETWEEN DynamicValue(RS_12_srcpart_date_cstring_min) AND DynamicValue(RS_12_srcpart_date_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_12_srcpart_date_cstring_bloom_filter))) (type: boolean) + filterExpr: (cstring is not null and (cstring BETWEEN DynamicValue(RS_12_srcpart_date_cstring_min) AND DynamicValue(RS_12_srcpart_date_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_12_srcpart_date_cstring_bloom_filter)))) (type: boolean) Statistics: Num rows: 12288 Data size: 926570 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cstring is not null and cstring BETWEEN DynamicValue(RS_12_srcpart_date_cstring_min) AND DynamicValue(RS_12_srcpart_date_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_12_srcpart_date_cstring_bloom_filter))) (type: boolean) + predicate: (cstring is not null and (cstring BETWEEN DynamicValue(RS_12_srcpart_date_cstring_min) AND DynamicValue(RS_12_srcpart_date_cstring_max) and in_bloom_filter(cstring, DynamicValue(RS_12_srcpart_date_cstring_bloom_filter)))) (type: boolean) Statistics: Num rows: 12288 Data size: 926570 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring (type: string) @@ -1642,10 +1642,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date - filterExpr: (key is not null and key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter))) (type: boolean) + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter))) (type: boolean) + predicate: (key is not null and (key BETWEEN DynamicValue(RS_7_srcpart_small_key_min) AND DynamicValue(RS_7_srcpart_small_key_max) and in_bloom_filter(key, DynamicValue(RS_7_srcpart_small_key_bloom_filter)))) (type: boolean) Statistics: Num rows: 2000 Data size: 352000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out index 401e558..e91795b 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_2.q.out @@ -105,10 +105,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tt2 - filterExpr: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null and timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter))) (type: boolean) + filterExpr: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null and (timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter)))) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null and timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter))) (type: boolean) + predicate: ((timestamp_col_18 = timestamp_col_18) and decimal1911_col_16 is not null and (timestamp_col_18 BETWEEN DynamicValue(RS_23_t1_timestamp_col_18_min) AND DynamicValue(RS_23_t1_timestamp_col_18_max) and in_bloom_filter(timestamp_col_18, DynamicValue(RS_23_t1_timestamp_col_18_bloom_filter)))) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_18 (type: timestamp) http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out new file mode 100644 index 0000000..7ea25d0 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out @@ -0,0 +1,765 @@ +PREHOOK: query: create table acidTbl(a int, b int) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@acidTbl +POSTHOOK: query: create table acidTbl(a int, b int) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@acidTbl +PREHOOK: query: create table nonAcidOrcTbl(a int, b int) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='false') +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nonAcidOrcTbl +POSTHOOK: query: create table nonAcidOrcTbl(a int, b int) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='false') +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nonAcidOrcTbl +PREHOOK: query: explain merge into acidTbl as t using nonAcidOrcTbl s ON t.a = s.a +WHEN MATCHED AND s.a > 8 THEN DELETE +WHEN MATCHED THEN UPDATE SET b = 7 +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b) +PREHOOK: type: QUERY +POSTHOOK: query: explain merge into acidTbl as t using nonAcidOrcTbl s ON t.a = s.a +WHEN MATCHED AND s.a > 8 THEN DELETE +WHEN MATCHED THEN UPDATE SET b = 7 +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-5 + Stage-8 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Reducer 8 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (SIMPLE_EDGE) + Reducer 6 <- Reducer 2 (SIMPLE_EDGE) + Reducer 8 <- Map 7 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (a BETWEEN DynamicValue(RS_3_s_a_min) AND DynamicValue(RS_3_s_a_max) and in_bloom_filter(a, DynamicValue(RS_3_s_a_bloom_filter))) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + Execution mode: llap + LLAP IO: may be used (ACID table) + Map 7 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: b (type: int) + Select Operator + expressions: a (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 a (type: int) + 1 a (type: int) + outputColumnNames: _col0, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((_col5 > 8) and (_col0 = _col5)) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + sort order: + + Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((_col5 <= 8) and (_col0 = _col5)) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + sort order: + + Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: int) + Filter Operator + predicate: (_col0 = _col5) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + outputColumnNames: _col4 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count() + keys: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + sort order: + + Map-reduce partition columns: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: bigint) + Filter Operator + predicate: _col0 is null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col5 (type: int), _col6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: int), 7 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (_col1 > 1) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: cardinality_violation(_col0) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.merge_tmp_table + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + + Stage: Stage-5 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-6 + Stats-Aggr Operator + + Stage: Stage-2 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-7 + Stats-Aggr Operator + + Stage: Stage-3 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.merge_tmp_table + + Stage: Stage-8 + Stats-Aggr Operator + + Stage: Stage-1 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-9 + Stats-Aggr Operator + +PREHOOK: query: explain merge into acidTbl as t using nonAcidOrcTbl s ON t.a = s.a +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b) +PREHOOK: type: QUERY +POSTHOOK: query: explain merge into acidTbl as t using nonAcidOrcTbl s ON t.a = s.a +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (a BETWEEN DynamicValue(RS_3_s_a_min) AND DynamicValue(RS_3_s_a_max) and in_bloom_filter(a, DynamicValue(RS_3_s_a_bloom_filter))) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Execution mode: llap + LLAP IO: may be used (ACID table) + Map 4 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: b (type: int) + Select Operator + expressions: a (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 a (type: int) + 1 a (type: int) + outputColumnNames: _col0, _col5, _col6 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: _col0 is null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col5 (type: int), _col6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: explain merge into acidTbl as t using ( + select * from nonAcidOrcTbl where a > 0 + union all + select * from nonAcidOrcTbl where b > 0 +) s ON t.a = s.a +WHEN MATCHED AND s.a > 8 THEN DELETE +WHEN MATCHED THEN UPDATE SET b = 7 +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b) +PREHOOK: type: QUERY +POSTHOOK: query: explain merge into acidTbl as t using ( + select * from nonAcidOrcTbl where a > 0 + union all + select * from nonAcidOrcTbl where b > 0 +) s ON t.a = s.a +WHEN MATCHED AND s.a > 8 THEN DELETE +WHEN MATCHED THEN UPDATE SET b = 7 +WHEN NOT MATCHED THEN INSERT VALUES(s.a, s.b) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-5 + Stage-8 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 10 <- Reducer 8 (BROADCAST_EDGE) + Map 9 <- Union 2 (CONTAINS) + Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 5 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Reducer 3 (SIMPLE_EDGE) + Reducer 7 <- Reducer 3 (SIMPLE_EDGE) + Reducer 8 <- Union 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nonacidorctbl + filterExpr: (a > 0) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (a > 0) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: a (type: int), b (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: int) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Execution mode: llap + LLAP IO: all inputs + Map 10 + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (a BETWEEN DynamicValue(RS_10_nonacidorctbl_a_min) AND DynamicValue(RS_10_nonacidorctbl_a_max) and in_bloom_filter(a, DynamicValue(RS_10_nonacidorctbl_a_bloom_filter))) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + Execution mode: llap + LLAP IO: may be used (ACID table) + Map 9 + Map Operator Tree: + TableScan + alias: nonacidorctbl + filterExpr: (b > 0) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (b > 0) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: a (type: int), b (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: int) + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=2) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Execution mode: llap + LLAP IO: all inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 a (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col4, _col5, _col6 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((_col5 > 8) and (_col0 = _col5)) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + sort order: + + Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((_col5 <= 8) and (_col0 = _col5)) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + sort order: + + Map-reduce partition columns: UDFToInteger(_col0) (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: int) + Filter Operator + predicate: (_col0 = _col5) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + outputColumnNames: _col4 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: count() + keys: _col4 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + sort order: + + Map-reduce partition columns: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: bigint) + Filter Operator + predicate: _col0 is null (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col5 (type: int), _col6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: int), 7 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (_col1 > 1) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: cardinality_violation(_col0) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.merge_tmp_table + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=2) + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Union 2 + Vertex: Union 2 + + Stage: Stage-5 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-6 + Stats-Aggr Operator + + Stage: Stage-2 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-7 + Stats-Aggr Operator + + Stage: Stage-3 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.merge_tmp_table + + Stage: Stage-8 + Stats-Aggr Operator + + Stage: Stage-1 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.acidtbl + + Stage: Stage-9 + Stats-Aggr Operator + http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/orc_llap.q.out ---------------------------------------------------------------------- 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 aa1dd96..0b12725 100644 --- a/ql/src/test/results/clientpositive/llap/orc_llap.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_llap.q.out @@ -563,10 +563,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: o2 - filterExpr: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean) + filterExpr: (csmallint is not null and cbigint is not null and (csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter)))) (type: boolean) Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean) + predicate: (csmallint is not null and cbigint is not null and (csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter)))) (type: boolean) Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cstring2 (type: string) @@ -1016,10 +1016,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: o2 - filterExpr: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean) + filterExpr: (csmallint is not null and cbigint is not null and (csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter)))) (type: boolean) Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (csmallint is not null and cbigint is not null and csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter))) (type: boolean) + predicate: (csmallint is not null and cbigint is not null and (csmallint BETWEEN DynamicValue(RS_6_o1_csmallint_min) AND DynamicValue(RS_6_o1_csmallint_max) and in_bloom_filter(csmallint, DynamicValue(RS_6_o1_csmallint_bloom_filter)))) (type: boolean) Statistics: Num rows: 245760 Data size: 58159880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cstring2 (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index 99e5a42..0d73623 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -2944,10 +2944,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hr) = 13.0) and hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter))) (type: boolean) + filterExpr: ((UDFToDouble(hr) = 13.0) and (hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter)))) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter))) (type: boolean) + predicate: ((UDFToDouble(hr) = 13.0) and (hr BETWEEN DynamicValue(RS_12_srcpart_hr_min) AND DynamicValue(RS_12_srcpart_hr_max) and in_bloom_filter(hr, DynamicValue(RS_12_srcpart_hr_bloom_filter)))) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/c3d311f4/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out index 62a6779..0bf5e85 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out @@ -47,10 +47,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_int is not null and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_int is not null and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + predicate: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_int (type: int) @@ -183,10 +183,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_str is not null and key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) (type: boolean) + filterExpr: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_str is not null and key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) (type: boolean) + predicate: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_str (type: string) @@ -319,10 +319,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_str is not null and key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) (type: boolean) + filterExpr: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_str is not null and key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) (type: boolean) + predicate: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_str (type: string) @@ -456,10 +456,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_int is not null and key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and key_int BETWEEN DynamicValue(RS_11_c_key_int_min) AND DynamicValue(RS_11_c_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter)) and in_bloom_filter(key_int, DynamicValue(RS_11_c_key_int_bloom_filter))) (type: boolean) + filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter))) and (key_int BETWEEN DynamicValue(RS_11_c_key_int_min) AND DynamicValue(RS_11_c_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_11_c_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_int is not null and key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and key_int BETWEEN DynamicValue(RS_11_c_key_int_min) AND DynamicValue(RS_11_c_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter)) and in_bloom_filter(key_int, DynamicValue(RS_11_c_key_int_bloom_filter))) (type: boolean) + predicate: (key_int is not null and (key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter))) and (key_int BETWEEN DynamicValue(RS_11_c_key_int_min) AND DynamicValue(RS_11_c_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_11_c_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_int (type: int) @@ -640,10 +640,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_str is not null and key_int is not null and key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + filterExpr: (key_str is not null and key_int is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_str is not null and key_int is not null and key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + predicate: (key_str is not null and key_int is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_str (type: string), key_int (type: int) @@ -801,10 +801,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_int is not null and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_int is not null and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + predicate: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_int (type: int) @@ -953,10 +953,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - filterExpr: (key_int is not null and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key_int is not null and key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) (type: boolean) + predicate: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean) Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key_int (type: int)
