Repository: hive Updated Branches: refs/heads/master 075077d3c -> 1733a3712
http://git-wip-us.apache.org/repos/asf/hive/blob/1733a371/ql/src/test/results/clientpositive/results_cache_temptable.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/results_cache_temptable.q.out b/ql/src/test/results/clientpositive/results_cache_temptable.q.out new file mode 100644 index 0000000..5350dba --- /dev/null +++ b/ql/src/test/results/clientpositive/results_cache_temptable.q.out @@ -0,0 +1,293 @@ +PREHOOK: query: create table rct (key string, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@rct +POSTHOOK: query: create table rct (key string, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@rct +PREHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table rct +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@rct +POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table rct +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@rct +PREHOOK: query: create table rct_part (key string, value string) partitioned by (ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@rct_part +POSTHOOK: query: create table rct_part (key string, value string) partitioned by (ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@rct_part +PREHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table rct_part partition (ds="2008-04-08") +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@rct_part +POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table rct_part partition (ds="2008-04-08") +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@rct_part +POSTHOOK: Output: default@rct_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table rct_part partition (ds="2008-04-09") +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@rct_part +POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' overwrite into table rct_part partition (ds="2008-04-09") +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@rct_part +POSTHOOK: Output: default@rct_part@ds=2008-04-09 +PREHOOK: query: create temporary table tmptab as select * from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@tmptab +POSTHOOK: query: create temporary table tmptab as select * from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmptab +PREHOOK: query: select count(*) from tmptab where key = 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmptab +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from tmptab where key = 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmptab +#### A masked pattern was here #### +3 +test.comment="Query involving temp tables should not be added to the cache" +PREHOOK: query: explain +select count(*) from tmptab where key = 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from tmptab where key = 0 +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: tmptab + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) = 0.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 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 rct where key = 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@rct +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from rct where key = 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@rct +#### A masked pattern was here #### +3 +test.comment="Query should use the cache" +PREHOOK: query: explain +select count(*) from rct where key = 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from rct where key = 0 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + Cached Query Result: true + +PREHOOK: query: create temporary table rct as select * from tmptab +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@tmptab +PREHOOK: Output: database:default +PREHOOK: Output: default@rct +POSTHOOK: query: create temporary table rct as select * from tmptab +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@tmptab +POSTHOOK: Output: database:default +POSTHOOK: Output: default@rct +test.comment="Cached query does not get used now that it resolves to a temp table" +PREHOOK: query: explain +select count(*) from rct where key = 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from rct where key = 0 +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: rct + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) = 0.0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 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 rct_part where ds="2008-04-08" and key = 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@rct_part +PREHOOK: Input: default@rct_part@ds=2008-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from rct_part where ds="2008-04-08" and key = 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@rct_part +POSTHOOK: Input: default@rct_part@ds=2008-04-08 +#### A masked pattern was here #### +3 +test.comment="Query should use the cache" +PREHOOK: query: explain +select count(*) from rct_part where ds="2008-04-08" and key = 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from rct_part where ds="2008-04-08" and key = 0 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + Cached Query Result: true + +PREHOOK: query: create temporary table rct_part as select key, value, "2008-04-08" as ds from tmptab +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@tmptab +PREHOOK: Output: database:default +PREHOOK: Output: default@rct_part +POSTHOOK: query: create temporary table rct_part as select key, value, "2008-04-08" as ds from tmptab +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@tmptab +POSTHOOK: Output: database:default +POSTHOOK: Output: default@rct_part +test.comment="Cached query does not get used now that it resolves to a temp table" +PREHOOK: query: explain +select count(*) from rct_part where ds="2008-04-08" and key = 0 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from rct_part where ds="2008-04-08" and key = 0 +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: rct_part + Statistics: Num rows: 500 Data size: 10812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((UDFToDouble(key) = 0.0) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 125 Data size: 2703 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 125 Data size: 2703 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 + http://git-wip-us.apache.org/repos/asf/hive/blob/1733a371/ql/src/test/results/clientpositive/results_cache_with_masking.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/results_cache_with_masking.q.out b/ql/src/test/results/clientpositive/results_cache_with_masking.q.out new file mode 100644 index 0000000..3a0b2cc --- /dev/null +++ b/ql/src/test/results/clientpositive/results_cache_with_masking.q.out @@ -0,0 +1,106 @@ +PREHOOK: query: create table masking_test as select cast(key as int) as key, value from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@masking_test +POSTHOOK: query: create table masking_test as select cast(key as int) as key, value from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@masking_test +POSTHOOK: Lineage: masking_test.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: masking_test.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain +select key, count(*) from masking_test group by key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key, count(*) from masking_test group by key +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: masking_test + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 41 Data size: 435 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 key, count(*) from masking_test group by key +PREHOOK: type: QUERY +PREHOOK: Input: default@masking_test +#### A masked pattern was here #### +POSTHOOK: query: select key, count(*) from masking_test group by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@masking_test +#### A masked pattern was here #### +0 3 +2 1 +4 1 +8 1 +PREHOOK: query: explain +select key, count(*) from masking_test group by key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key, count(*) from masking_test group by key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + Cached Query Result: true + +PREHOOK: query: select key, count(*) from masking_test group by key +PREHOOK: type: QUERY +PREHOOK: Input: default@masking_test +#### A masked pattern was here #### +POSTHOOK: query: select key, count(*) from masking_test group by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@masking_test +#### A masked pattern was here #### +0 3 +2 1 +4 1 +8 1 http://git-wip-us.apache.org/repos/asf/hive/blob/1733a371/service/src/java/org/apache/hive/service/server/HiveServer2.java ---------------------------------------------------------------------- diff --git a/service/src/java/org/apache/hive/service/server/HiveServer2.java b/service/src/java/org/apache/hive/service/server/HiveServer2.java index 2a528cd..2e57b60 100644 --- a/service/src/java/org/apache/hive/service/server/HiveServer2.java +++ b/service/src/java/org/apache/hive/service/server/HiveServer2.java @@ -61,6 +61,7 @@ import org.apache.hadoop.hive.metastore.api.WMFullResourcePlan; import org.apache.hadoop.hive.metastore.api.WMPool; import org.apache.hadoop.hive.metastore.api.WMResourcePlan; import org.apache.hadoop.hive.metastore.cache.CachedStore; +import org.apache.hadoop.hive.ql.cache.results.QueryResultsCache; import org.apache.hadoop.hive.ql.exec.spark.session.SparkSessionManagerImpl; import org.apache.hadoop.hive.ql.exec.tez.TezSessionPoolManager; import org.apache.hadoop.hive.ql.exec.tez.WorkloadManager; @@ -191,6 +192,15 @@ public class HiveServer2 extends CompositeService { // Create views registry HiveMaterializedViewsRegistry.get().init(); + // Setup cache if enabled. + if (hiveConf.getBoolVar(HiveConf.ConfVars.HIVE_QUERY_RESULTS_CACHE_ENABLED)) { + try { + QueryResultsCache.initialize(hiveConf); + } catch (Exception err) { + throw new RuntimeException("Error initializing the query results cache", err); + } + } + // Setup web UI try { int webUIPort =
