PREHOOK: query: -- try the query without indexing, with manual indexing, and with automatic indexing -- SORT_QUERY_RESULTS -- without indexing SELECT key, value FROM src WHERE key > 80 AND key < 100 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: -- try the query without indexing, with manual indexing, and with automatic indexing -- SORT_QUERY_RESULTS -- without indexing SELECT key, value FROM src WHERE key > 80 AND key < 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### 82 val_82 83 val_83 83 val_83 84 val_84 84 val_84 85 val_85 86 val_86 87 val_87 90 val_90 90 val_90 90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 PREHOOK: query: CREATE INDEX src_index ON TABLE src(key) as 'COMPACT' WITH DEFERRED REBUILD PREHOOK: type: CREATEINDEX PREHOOK: Input: default@src POSTHOOK: query: CREATE INDEX src_index ON TABLE src(key) as 'COMPACT' WITH DEFERRED REBUILD POSTHOOK: type: CREATEINDEX POSTHOOK: Input: default@src POSTHOOK: Output: default@default__src_src_index__ PREHOOK: query: ALTER INDEX src_index ON src REBUILD PREHOOK: type: ALTERINDEX_REBUILD PREHOOK: Input: default@src PREHOOK: Output: default@default__src_src_index__ POSTHOOK: query: ALTER INDEX src_index ON src REBUILD POSTHOOK: type: ALTERINDEX_REBUILD POSTHOOK: Input: default@src POSTHOOK: Output: default@default__src_src_index__ POSTHOOK: Lineage: default__src_src_index__._bucketname SIMPLE [(src)src.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), ] POSTHOOK: Lineage: default__src_src_index__._offsets EXPRESSION [(src)src.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), ] POSTHOOK: Lineage: default__src_src_index__.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: -- manual indexing #### A masked pattern was here #### PREHOOK: type: QUERY PREHOOK: Input: default@default__src_src_index__ #### A masked pattern was here #### POSTHOOK: query: -- manual indexing #### A masked pattern was here #### POSTHOOK: type: QUERY POSTHOOK: Input: default@default__src_src_index__ #### A masked pattern was here #### PREHOOK: query: EXPLAIN SELECT key, value FROM src WHERE key > 80 AND key < 100 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT key, value FROM src WHERE key > 80 AND key < 100 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: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: SELECT key, value FROM src WHERE key > 80 AND key < 100 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: SELECT key, value FROM src WHERE key > 80 AND key < 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### 82 val_82 83 val_83 83 val_83 84 val_84 84 val_84 85 val_85 86 val_86 87 val_87 90 val_90 90 val_90 90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 PREHOOK: query: -- automatic indexing EXPLAIN SELECT key, value FROM src WHERE key > 80 AND key < 100 PREHOOK: type: QUERY POSTHOOK: query: -- automatic indexing EXPLAIN SELECT key, value FROM src WHERE key > 80 AND key < 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-3 is a root stage Stage-8 depends on stages: Stage-3 , consists of Stage-5, Stage-4, Stage-6 Stage-5 Stage-2 depends on stages: Stage-5, Stage-4, Stage-7 Stage-1 depends on stages: Stage-2 Stage-4 Stage-6 Stage-7 depends on stages: Stage-6 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-3 Map Reduce Map Operator Tree: TableScan alias: default__src_src_index__ filterExpr: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Filter Operator predicate: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Select Operator expressions: _bucketname (type: string), _offsets (type: array) outputColumnNames: _col0, _col1 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Conditional Operator Stage: Stage-5 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-2 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: src filterExpr: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 80.0) and (UDFToDouble(key) < 100.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-4 Map Reduce Map Operator Tree: TableScan File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-6 Map Reduce Map Operator Tree: TableScan File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-7 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: SELECT key, value FROM src WHERE key > 80 AND key < 100 PREHOOK: type: QUERY PREHOOK: Input: default@default__src_src_index__ PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: SELECT key, value FROM src WHERE key > 80 AND key < 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@default__src_src_index__ POSTHOOK: Input: default@src #### A masked pattern was here #### 82 val_82 83 val_83 83 val_83 84 val_84 84 val_84 85 val_85 86 val_86 87 val_87 90 val_90 90 val_90 90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 PREHOOK: query: DROP INDEX src_index on src PREHOOK: type: DROPINDEX PREHOOK: Input: default@src POSTHOOK: query: DROP INDEX src_index on src POSTHOOK: type: DROPINDEX POSTHOOK: Input: default@src