diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java index 7b2a1a9..a3a35ff 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java @@ -31,6 +31,7 @@ import org.apache.hadoop.hive.common.StatsSetupConst; import org.apache.hadoop.hive.common.type.HiveDecimal; +import org.apache.hadoop.hive.metastore.MetaStoreUtils; import org.apache.hadoop.hive.metastore.api.ColumnStatisticsData; import org.apache.hadoop.hive.metastore.api.ColumnStatisticsObj; import org.apache.hadoop.hive.metastore.api.DoubleColumnStatsData; @@ -272,6 +273,10 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, return null; } Table tbl = tsOp.getConf().getTableMetadata(); + if (MetaStoreUtils.isExternalTable(tbl.getTTable())) { + Logger.info("Table " + tbl.getTableName() + " is external. Skip StatsOptimizer."); + return null; + } if (AcidUtils.isAcidTable(tbl)) { Logger.info("Table " + tbl.getTableName() + " is ACID table. Skip StatsOptimizer."); return null; diff --git ql/src/test/queries/clientpositive/stats_noscan_2.q ql/src/test/queries/clientpositive/stats_noscan_2.q index 8639ab7..d473081 100644 --- ql/src/test/queries/clientpositive/stats_noscan_2.q +++ ql/src/test/queries/clientpositive/stats_noscan_2.q @@ -16,6 +16,7 @@ create table texternal(key string, val string) partitioned by (insertdate string dfs ${system:test.dfs.mkdir} ${system:test.tmp.dir}/texternal/2008-01-01; alter table texternal add partition (insertdate='2008-01-01') location 'pfile://${system:test.tmp.dir}/texternal/2008-01-01'; from src insert overwrite table texternal partition (insertdate='2008-01-01') select *; +explain select count(*) from texternal where insertdate='2008-01-01'; select count(*) from texternal where insertdate='2008-01-01'; -- create external table CREATE EXTERNAL TABLE anaylyze_external (key string, val string) partitioned by (insertdate string) LOCATION "pfile://${system:test.tmp.dir}/texternal"; @@ -27,6 +28,8 @@ describe formatted anaylyze_external PARTITION (insertdate='2008-01-01'); analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics; describe formatted anaylyze_external PARTITION (insertdate='2008-01-01'); dfs -rmr ${system:test.tmp.dir}/texternal; +explain select count(*) from anaylyze_external where insertdate='2008-01-01'; +select count(*) from anaylyze_external where insertdate='2008-01-01'; drop table anaylyze_external; diff --git ql/src/test/results/clientpositive/stats_noscan_2.q.out ql/src/test/results/clientpositive/stats_noscan_2.q.out index 14e131c..ef397c3 100644 --- ql/src/test/results/clientpositive/stats_noscan_2.q.out +++ ql/src/test/results/clientpositive/stats_noscan_2.q.out @@ -139,6 +139,20 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@texternal@insertdate=2008-01-01 POSTHOOK: Lineage: texternal PARTITION(insertdate=2008-01-01).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: texternal PARTITION(insertdate=2008-01-01).val SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain select count(*) from texternal where insertdate='2008-01-01' +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*) from texternal where insertdate='2008-01-01' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from texternal where insertdate='2008-01-01' PREHOOK: type: QUERY PREHOOK: Input: default@texternal @@ -275,6 +289,63 @@ Sort Columns: [] Storage Desc Params: serialization.format 1 #### A masked pattern was here #### +PREHOOK: query: explain select count(*) from anaylyze_external where insertdate='2008-01-01' +PREHOOK: type: QUERY +POSTHOOK: query: explain select count(*) from anaylyze_external where insertdate='2008-01-01' +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: anaylyze_external + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) from anaylyze_external where insertdate='2008-01-01' +PREHOOK: type: QUERY +PREHOOK: Input: default@anaylyze_external +PREHOOK: Input: default@anaylyze_external@insertdate=2008-01-01 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from anaylyze_external where insertdate='2008-01-01' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@anaylyze_external +POSTHOOK: Input: default@anaylyze_external@insertdate=2008-01-01 +#### A masked pattern was here #### +0 PREHOOK: query: drop table anaylyze_external PREHOOK: type: DROPTABLE PREHOOK: Input: default@anaylyze_external