hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ser...@apache.org
Subject [23/40] hive git commit: HIVE-14921: Move slow CliDriver tests to MiniLlap - part 2 (Prasanth Jayachandran reviewed by Siddharth Seth)
Date Wed, 19 Oct 2016 18:17:50 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out b/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out
new file mode 100644
index 0000000..53e52ee
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out
@@ -0,0 +1,838 @@
+PREHOOK: query: explain select key, count(*) from src b group by b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select key, count(*) from src b group by b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                keys: KEY._col0 (type: string)
+                mode: complete
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select b.key, count(*) from src b group by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select b.key, count(*) from src b 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
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                keys: KEY._col0 (type: string)
+                mode: complete
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select key, count(*) from src b group by b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select key, count(*) from src b group by b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: rand() (type: double)
+                      Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                keys: KEY._col0 (type: string)
+                mode: partial1
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats:
COMPLETE
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
+                  Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  value expressions: _col1 (type: bigint)
+        Reducer 3 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: final
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select b.key, count(*) from src b group by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select b.key, count(*) from src b 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
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: rand() (type: double)
+                      Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                keys: KEY._col0 (type: string)
+                mode: partial1
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats:
COMPLETE
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
+                  Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  value expressions: _col1 (type: bigint)
+        Reducer 3 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: final
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select key, count(*) from src b group by b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select key, count(*) from src b group by b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Group By Operator
+                      aggregations: count()
+                      keys: key (type: string)
+                      mode: hash
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE
Column stats: COMPLETE
+                        value expressions: _col1 (type: bigint)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select b.key, count(*) from src b group by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select b.key, count(*) from src b 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
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Group By Operator
+                      aggregations: count()
+                      keys: key (type: string)
+                      mode: hash
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE
Column stats: COMPLETE
+                        value expressions: _col1 (type: bigint)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select key, count(*) from src b group by b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select key, count(*) from src b group by b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Group By Operator
+                      aggregations: count()
+                      keys: key (type: string)
+                      mode: hash
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: rand() (type: double)
+                        Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE
Column stats: COMPLETE
+                        value expressions: _col1 (type: bigint)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: partials
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  value expressions: _col1 (type: bigint)
+        Reducer 3 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: final
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: explain select b.key, count(*) from src b group by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select b.key, count(*) from src b 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
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: key
+                    Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Group By Operator
+                      aggregations: count()
+                      keys: key (type: string)
+                      mode: hash
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: rand() (type: double)
+                        Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE
Column stats: COMPLETE
+                        value expressions: _col1 (type: bigint)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: partials
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  value expressions: _col1 (type: bigint)
+        Reducer 3 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: final
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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: -- windowing after group by
+select key, count(*), rank() over(order by count(*))
+from src b
+where key < '12'
+group by b.key
+order by b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: -- windowing after group by
+select key, count(*), rank() over(order by count(*))
+from src b
+where key < '12'
+group by b.key
+order by b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0	3	12
+10	1	1
+100	2	7
+103	2	7
+104	2	7
+105	1	1
+11	1	1
+111	1	1
+113	2	7
+114	1	1
+116	1	1
+118	2	7
+119	3	12
+PREHOOK: query: -- having after group by
+select key, count(*)
+from src b
+group by b.key
+having key < '12'
+order by b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: -- having after group by
+select key, count(*)
+from src b
+group by b.key
+having key < '12'
+order by b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0	3
+10	1
+100	2
+103	2
+104	2
+105	1
+11	1
+111	1
+113	2
+114	1
+116	1
+118	2
+119	3
+PREHOOK: query: -- having and windowing
+select key, count(*), rank() over(order by count(*))
+from src b
+group by b.key
+having key < '12'
+order by b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: -- having and windowing
+select key, count(*), rank() over(order by count(*))
+from src b
+group by b.key
+having key < '12'
+order by b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0	3	12
+10	1	1
+100	2	7
+103	2	7
+104	2	7
+105	1	1
+11	1	1
+111	1	1
+113	2	7
+114	1	1
+116	1	1
+118	2	7
+119	3	12
+PREHOOK: query: explain
+select key, count(*), rank() over(order by count(*))
+from src b
+group by b.key
+having key < '12'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key, count(*), rank() over(order by count(*))
+from src b
+group by b.key
+having key < '12'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+        Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Filter Operator
+                    predicate: (key < '12') (type: boolean)
+                    Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Group By Operator
+                      aggregations: count()
+                      keys: key (type: string)
+                      mode: hash
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column
stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: rand() (type: double)
+                        Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column
stats: COMPLETE
+                        value expressions: _col1 (type: bigint)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: partials
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats:
COMPLETE
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
+                  Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats:
COMPLETE
+                  value expressions: _col1 (type: bigint)
+        Reducer 3 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: final
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats:
COMPLETE
+                Reduce Output Operator
+                  key expressions: 0 (type: int), _col1 (type: bigint)
+                  sort order: ++
+                  Map-reduce partition columns: 0 (type: int)
+                  Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats:
COMPLETE
+                  value expressions: _col0 (type: string)
+        Reducer 4 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Select Operator
+                expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: bigint)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats:
COMPLETE
+                PTF Operator
+                  Function definitions:
+                      Input definition
+                        input alias: ptf_0
+                        output shape: _col0: string, _col1: bigint
+                        type: WINDOWING
+                      Windowing table definition
+                        input alias: ptf_1
+                        name: windowingtablefunction
+                        order by: _col1 ASC NULLS FIRST
+                        partition by: 0
+                        raw input shape:
+                        window functions:
+                            window function definition
+                              alias: rank_window_0
+                              arguments: _col1
+                              name: rank
+                              window function: GenericUDAFRankEvaluator
+                              window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+                              isPivotResult: true
+                  Statistics: Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats:
COMPLETE
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: bigint), rank_window_0
(type: int)
+                    outputColumnNames: _col0, _col1, _col2
+                    Statistics: Num rows: 69 Data size: 6831 Basic stats: COMPLETE Column
stats: COMPLETE
+                    File Output Operator
+                      compressed: false
+                      Statistics: Num rows: 69 Data size: 6831 Basic stats: COMPLETE Column
stats: COMPLETE
+                      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: -- order by
+select key 
+from src t 
+where key < '12'
+group by t.key 
+order by t.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: -- order by
+select key 
+from src t 
+where key < '12'
+group by t.key 
+order by t.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0
+10
+100
+103
+104
+105
+11
+111
+113
+114
+116
+118
+119
+PREHOOK: query: -- cluster by
+EXPLAIN
+SELECT x.key, x.value as key FROM SRC x CLUSTER BY key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- cluster by
+EXPLAIN
+SELECT x.key, x.value as key FROM SRC x CLUSTER 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
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: x
+                  Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column
stats: COMPLETE
+                  Select Operator
+                    expressions: key (type: string), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column
stats: COMPLETE
+                    Reduce Output Operator
+                      key expressions: _col1 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col1 (type: string)
+                      Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column
stats: COMPLETE
+                      value expressions: _col0 (type: string)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Select Operator
+                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column
stats: COMPLETE
+                  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
+


Mime
View raw message