http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/explainuser_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/explainuser_4.q.out b/ql/src/test/results/clientpositive/tez/explainuser_4.q.out deleted file mode 100644 index f870e52..0000000 --- a/ql/src/test/results/clientpositive/tez/explainuser_4.q.out +++ /dev/null @@ -1,482 +0,0 @@ -PREHOOK: query: -- First try with regular mergejoin -explain -select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -PREHOOK: type: QUERY -POSTHOOK: query: -- First try with regular mergejoin -explain -select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -POSTHOOK: type: QUERY -Plan optimized by CBO. - -Vertex dependency in root stage -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 3 - File Output Operator [FS_12] - Select Operator [SEL_11] (rows=7286 width=620) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_17] (rows=7286 width=620) - Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_6] - PartitionCols:_col2 - Select Operator [SEL_2] (rows=6144 width=251) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_15] (rows=6144 width=251) - predicate:cint BETWEEN 1000000 AND 3000000 - TableScan [TS_0] (rows=12288 width=251) - default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] - <-Map 4 [SIMPLE_EDGE] - SHUFFLE [RS_7] - PartitionCols:_col2 - Select Operator [SEL_5] (rows=3424 width=251) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_16] (rows=3424 width=251) - predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) - TableScan [TS_3] (rows=12288 width=251) - default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] - -PREHOOK: query: select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -POSTHOOK: query: select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -11 NULL 1000828 1531084669 11.0 NULL wM316f6NqGIkoP388j3F6 poWQQo3Upvt3Wh 1969-12-31 16:00:02.351 NULL false true 11 NULL 1000828 1531084669 11.0 NULL wM316f6NqGIkoP388j3F6 poWQQo3Upvt3Wh 1969-12-31 16:00:02.351 NULL false true -NULL -3799 1248059 1864027286 NULL -3799.0 Uhps6mMh3IfHB3j7yH62K 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:54.622 false true NULL -3799 1248059 1864027286 NULL -3799.0 Uhps6mMh3IfHB3j7yH62K 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:54.622 false true -NULL 10782 1286921 1864027286 NULL 10782.0 ODLrXI8882q8LS8 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:52.138 true true NULL 10782 1286921 1864027286 NULL 10782.0 ODLrXI8882q8LS8 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:52.138 true true -NULL -13036 1288927 -1645852809 NULL -13036.0 yinBY725P7V2 xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:00.763 true false NULL -13036 1288927 -1645852809 NULL -13036.0 yinBY725P7V2 xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:00.763 true false -11 NULL 1310786 -413875656 11.0 NULL W0rvA4H1xn0xMG4uk0 8yVVjG 1969-12-31 16:00:02.351 NULL false true 11 NULL 1310786 -413875656 11.0 NULL W0rvA4H1xn0xMG4uk0 8yVVjG 1969-12-31 16:00:02.351 NULL false true --51 NULL 2089466 -240556350 -51.0 NULL cXX24dH7tblSj46j2g C31eea0wrHHqvj 1969-12-31 16:00:08.451 NULL true true -51 NULL 2089466 -240556350 -51.0 NULL cXX24dH7tblSj46j2g C31eea0wrHHqvj 1969-12-31 16:00:08.451 NULL true true -NULL -8915 2101183 1864027286 NULL -8915.0 x7By66525 4KWs6gw7lv2WYd66P NULL 1969-12-31 16:00:05.831 false true NULL -8915 2101183 1864027286 NULL -8915.0 x7By66525 4KWs6gw7lv2WYd66P NULL 1969-12-31 16:00:05.831 false true -8 NULL 2229621 -381406148 8.0 NULL q7onkS7QRPh5ghOK oKb0bi 1969-12-31 16:00:15.892 NULL true false 8 NULL 2229621 -381406148 8.0 NULL q7onkS7QRPh5ghOK oKb0bi 1969-12-31 16:00:15.892 NULL true false -8 NULL 2433892 -1611863517 8.0 NULL 674ILv3V2TxFqXP6wSbL VLprkK2XfX 1969-12-31 16:00:15.892 NULL false true 8 NULL 2433892 -1611863517 8.0 NULL 674ILv3V2TxFqXP6wSbL VLprkK2XfX 1969-12-31 16:00:15.892 NULL false true --51 NULL 2949963 -1580871111 -51.0 NULL 0K68k3bdl7jO7 TPPAu 1969-12-31 16:00:08.451 NULL true false -51 NULL 2949963 -1580871111 -51.0 NULL 0K68k3bdl7jO7 TPPAu 1969-12-31 16:00:08.451 NULL true false -PREHOOK: query: explain -select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -PREHOOK: type: QUERY -POSTHOOK: query: explain -select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -POSTHOOK: type: QUERY -Plan optimized by CBO. - -Vertex dependency in root stage -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 3 - File Output Operator [FS_14] - Group By Operator [GBY_12] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - Group By Operator [GBY_10] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_19] (rows=7286 width=8) - Conds:RS_6._col0=RS_7._col0(Inner) - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_6] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=6144 width=2) - Output:["_col0"] - Filter Operator [FIL_17] (rows=6144 width=2) - predicate:cint BETWEEN 1000000 AND 3000000 - TableScan [TS_0] (rows=12288 width=2) - default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["cint"] - <-Map 4 [SIMPLE_EDGE] - SHUFFLE [RS_7] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=3424 width=8) - Output:["_col0"] - Filter Operator [FIL_18] (rows=3424 width=8) - predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) - TableScan [TS_3] (rows=12288 width=8) - default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["cint","cbigint"] - -PREHOOK: query: select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -POSTHOOK: query: select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -10 -PREHOOK: query: explain -select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -PREHOOK: type: QUERY -POSTHOOK: query: explain -select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -POSTHOOK: type: QUERY -Plan optimized by CBO. - -Vertex dependency in root stage -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) - -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 4 - File Output Operator [FS_16] - Select Operator [SEL_15] (rows=2765 width=12) - Output:["_col0","_col1"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_14] - Group By Operator [GBY_12] (rows=2765 width=12) - Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col0 - Group By Operator [GBY_10] (rows=2765 width=12) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_21] (rows=7286 width=4) - Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_6] - PartitionCols:_col1 - Select Operator [SEL_2] (rows=6144 width=5) - Output:["_col0","_col1"] - Filter Operator [FIL_19] (rows=6144 width=5) - predicate:cint BETWEEN 1000000 AND 3000000 - TableScan [TS_0] (rows=12288 width=5) - default@alltypesorc,a,Tbl:COMPLETE,Col:COMPLETE,Output:["csmallint","cint"] - <-Map 5 [SIMPLE_EDGE] - SHUFFLE [RS_7] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=3424 width=8) - Output:["_col0"] - Filter Operator [FIL_20] (rows=3424 width=8) - predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) - TableScan [TS_3] (rows=12288 width=8) - default@alltypesorc,b,Tbl:COMPLETE,Col:COMPLETE,Output:["cint","cbigint"] - -PREHOOK: query: select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -POSTHOOK: query: select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -#### A masked pattern was here #### --13036 1 --8915 1 --3799 1 -10782 1 -NULL 6 -PREHOOK: query: -- Try with dynamically partitioned hashjoin -explain -select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -PREHOOK: type: QUERY -POSTHOOK: query: -- Try with dynamically partitioned hashjoin -explain -select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -POSTHOOK: type: QUERY -Plan optimized by CBO. - -Vertex dependency in root stage -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 4 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 3 - File Output Operator [FS_12] - Select Operator [SEL_11] (rows=6758 width=215) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_10] - Map Join Operator [MAPJOIN_17] (rows=6758 width=215) - Conds:RS_6.KEY.reducesinkkey0=RS_7.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] - <-Map 4 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_7] - PartitionCols:_col2 - Select Operator [SEL_5] (rows=6144 width=215) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_16] (rows=6144 width=215) - predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) - TableScan [TS_3] (rows=12288 width=215) - default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_6] - PartitionCols:_col2 - Select Operator [SEL_2] (rows=6144 width=215) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_15] (rows=6144 width=215) - predicate:cint BETWEEN 1000000 AND 3000000 - TableScan [TS_0] (rows=12288 width=215) - default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"] - -PREHOOK: query: select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -POSTHOOK: query: select - * -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -order by a.cint -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -11 NULL 1000828 1531084669 11.0 NULL wM316f6NqGIkoP388j3F6 poWQQo3Upvt3Wh 1969-12-31 16:00:02.351 NULL false true 11 NULL 1000828 1531084669 11.0 NULL wM316f6NqGIkoP388j3F6 poWQQo3Upvt3Wh 1969-12-31 16:00:02.351 NULL false true -NULL -3799 1248059 1864027286 NULL -3799.0 Uhps6mMh3IfHB3j7yH62K 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:54.622 false true NULL -3799 1248059 1864027286 NULL -3799.0 Uhps6mMh3IfHB3j7yH62K 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:54.622 false true -NULL 10782 1286921 1864027286 NULL 10782.0 ODLrXI8882q8LS8 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:52.138 true true NULL 10782 1286921 1864027286 NULL 10782.0 ODLrXI8882q8LS8 4KWs6gw7lv2WYd66P NULL 1969-12-31 15:59:52.138 true true -NULL -13036 1288927 -1645852809 NULL -13036.0 yinBY725P7V2 xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:00.763 true false NULL -13036 1288927 -1645852809 NULL -13036.0 yinBY725P7V2 xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:00.763 true false -11 NULL 1310786 -413875656 11.0 NULL W0rvA4H1xn0xMG4uk0 8yVVjG 1969-12-31 16:00:02.351 NULL false true 11 NULL 1310786 -413875656 11.0 NULL W0rvA4H1xn0xMG4uk0 8yVVjG 1969-12-31 16:00:02.351 NULL false true --51 NULL 2089466 -240556350 -51.0 NULL cXX24dH7tblSj46j2g C31eea0wrHHqvj 1969-12-31 16:00:08.451 NULL true true -51 NULL 2089466 -240556350 -51.0 NULL cXX24dH7tblSj46j2g C31eea0wrHHqvj 1969-12-31 16:00:08.451 NULL true true -NULL -8915 2101183 1864027286 NULL -8915.0 x7By66525 4KWs6gw7lv2WYd66P NULL 1969-12-31 16:00:05.831 false true NULL -8915 2101183 1864027286 NULL -8915.0 x7By66525 4KWs6gw7lv2WYd66P NULL 1969-12-31 16:00:05.831 false true -8 NULL 2229621 -381406148 8.0 NULL q7onkS7QRPh5ghOK oKb0bi 1969-12-31 16:00:15.892 NULL true false 8 NULL 2229621 -381406148 8.0 NULL q7onkS7QRPh5ghOK oKb0bi 1969-12-31 16:00:15.892 NULL true false -8 NULL 2433892 -1611863517 8.0 NULL 674ILv3V2TxFqXP6wSbL VLprkK2XfX 1969-12-31 16:00:15.892 NULL false true 8 NULL 2433892 -1611863517 8.0 NULL 674ILv3V2TxFqXP6wSbL VLprkK2XfX 1969-12-31 16:00:15.892 NULL false true --51 NULL 2949963 -1580871111 -51.0 NULL 0K68k3bdl7jO7 TPPAu 1969-12-31 16:00:08.451 NULL true false -51 NULL 2949963 -1580871111 -51.0 NULL 0K68k3bdl7jO7 TPPAu 1969-12-31 16:00:08.451 NULL true false -PREHOOK: query: explain -select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -PREHOOK: type: QUERY -POSTHOOK: query: explain -select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -POSTHOOK: type: QUERY -Plan optimized by CBO. - -Vertex dependency in root stage -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 4 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) - -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 3 - File Output Operator [FS_14] - Group By Operator [GBY_12] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - Group By Operator [GBY_10] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Map Join Operator [MAPJOIN_19] (rows=6758 width=215) - Conds:RS_6.KEY.reducesinkkey0=RS_7.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true - <-Map 4 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_7] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=6144 width=215) - Output:["_col0"] - Filter Operator [FIL_18] (rows=6144 width=215) - predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) - TableScan [TS_3] (rows=12288 width=215) - default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_6] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=6144 width=215) - Output:["_col0"] - Filter Operator [FIL_17] (rows=6144 width=215) - predicate:cint BETWEEN 1000000 AND 3000000 - TableScan [TS_0] (rows=12288 width=215) - default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["cint"] - -PREHOOK: query: select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -POSTHOOK: query: select - count(*) -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -10 -PREHOOK: query: explain -select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -PREHOOK: type: QUERY -POSTHOOK: query: explain -select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -POSTHOOK: type: QUERY -Plan optimized by CBO. - -Vertex dependency in root stage -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 5 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE) - -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 4 - File Output Operator [FS_16] - Select Operator [SEL_15] (rows=3379 width=215) - Output:["_col0","_col1"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_14] - Group By Operator [GBY_12] (rows=3379 width=215) - Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col0 - Group By Operator [GBY_10] (rows=6758 width=215) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Map Join Operator [MAPJOIN_21] (rows=6758 width=215) - Conds:RS_6.KEY.reducesinkkey0=RS_7.KEY.reducesinkkey0(Inner),HybridGraceHashJoin:true,Output:["_col0"] - <-Map 5 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_7] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=6144 width=215) - Output:["_col0"] - Filter Operator [FIL_20] (rows=6144 width=215) - predicate:(cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) - TableScan [TS_3] (rows=12288 width=215) - default@alltypesorc,b,Tbl:COMPLETE,Col:NONE,Output:["cint","cbigint"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_6] - PartitionCols:_col1 - Select Operator [SEL_2] (rows=6144 width=215) - Output:["_col0","_col1"] - Filter Operator [FIL_19] (rows=6144 width=215) - predicate:cint BETWEEN 1000000 AND 3000000 - TableScan [TS_0] (rows=12288 width=215) - default@alltypesorc,a,Tbl:COMPLETE,Col:NONE,Output:["csmallint","cint"] - -PREHOOK: query: select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -#### A masked pattern was here #### -POSTHOOK: query: select - a.csmallint, count(*) c1 -from alltypesorc a join alltypesorc b on a.cint = b.cint -where - a.cint between 1000000 and 3000000 and b.cbigint is not null -group by a.csmallint -order by c1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -#### A masked pattern was here #### --8915 1 --3799 1 -10782 1 --13036 1 -NULL 6
http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out deleted file mode 100644 index 7655d5d..0000000 --- a/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out +++ /dev/null @@ -1,356 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS - -CREATE TABLE filter_join_breaktask(key int, value string) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@filter_join_breaktask -POSTHOOK: query: -- SORT_QUERY_RESULTS - -CREATE TABLE filter_join_breaktask(key int, value string) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@filter_join_breaktask -PREHOOK: query: INSERT OVERWRITE TABLE filter_join_breaktask PARTITION(ds='2008-04-08') -SELECT key, value from src1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -PREHOOK: Output: default@filter_join_breaktask@ds=2008-04-08 -POSTHOOK: query: INSERT OVERWRITE TABLE filter_join_breaktask PARTITION(ds='2008-04-08') -SELECT key, value from src1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -POSTHOOK: Output: default@filter_join_breaktask@ds=2008-04-08 -POSTHOOK: Lineage: filter_join_breaktask PARTITION(ds=2008-04-08).key EXPRESSION [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: filter_join_breaktask PARTITION(ds=2008-04-08).value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN EXTENDED -SELECT f.key, g.value -FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) -JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN EXTENDED -SELECT f.key, g.value -FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) -JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') -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), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: f - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: true - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.filter_join_breaktask - numFiles 1 - numRows 25 - partition_columns ds - partition_columns.types string - rawDataSize 211 - serialization.ddl struct filter_join_breaktask { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 236 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.filter_join_breaktask - partition_columns ds - partition_columns.types string - serialization.ddl struct filter_join_breaktask { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.filter_join_breaktask - name: default.filter_join_breaktask - Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [f] - Map 4 - Map Operator Tree: - TableScan - alias: m - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: true - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.filter_join_breaktask - numFiles 1 - numRows 25 - partition_columns ds - partition_columns.types string - rawDataSize 211 - serialization.ddl struct filter_join_breaktask { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 236 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.filter_join_breaktask - partition_columns ds - partition_columns.types string - serialization.ddl struct filter_join_breaktask { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.filter_join_breaktask - name: default.filter_join_breaktask - Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [m] - Map 5 - Map Operator Tree: - TableScan - alias: g - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (value <> '') (type: boolean) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 411 Basic stats: COMPLETE Column stats: NONE - tag: 1 - auto parallelism: true - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2008-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.filter_join_breaktask - numFiles 1 - numRows 25 - partition_columns ds - partition_columns.types string - rawDataSize 211 - serialization.ddl struct filter_join_breaktask { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 236 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.filter_join_breaktask - partition_columns ds - partition_columns.types string - serialization.ddl struct filter_join_breaktask { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.filter_join_breaktask - name: default.filter_join_breaktask - Truncated Path -> Alias: - /filter_join_breaktask/ds=2008-04-08 [g] - Reducer 2 - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 - Position of Big Table: 0 - Statistics: Num rows: 27 Data size: 452 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 27 Data size: 452 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col0 (type: int) - auto parallelism: true - Reducer 3 - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col5 - Position of Big Table: 0 - Statistics: Num rows: 29 Data size: 497 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col5 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 497 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 29 Data size: 497 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT f.key, g.value -FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) -JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') -PREHOOK: type: QUERY -PREHOOK: Input: default@filter_join_breaktask -PREHOOK: Input: default@filter_join_breaktask@ds=2008-04-08 -#### A masked pattern was here #### -POSTHOOK: query: SELECT f.key, g.value -FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) -JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') -POSTHOOK: type: QUERY -POSTHOOK: Input: default@filter_join_breaktask -POSTHOOK: Input: default@filter_join_breaktask@ds=2008-04-08 -#### A masked pattern was here #### -146 val_146 -150 val_150 -213 val_213 -238 val_238 -255 val_255 -273 val_273 -278 val_278 -311 val_311 -401 val_401 -406 val_406 -66 val_66 -98 val_98 http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/filter_join_breaktask2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/filter_join_breaktask2.q.out b/ql/src/test/results/clientpositive/tez/filter_join_breaktask2.q.out deleted file mode 100644 index af85af9..0000000 --- a/ql/src/test/results/clientpositive/tez/filter_join_breaktask2.q.out +++ /dev/null @@ -1,272 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS - -create table T1(c1 string, c2 string, c3 string, c4 string, c5 string, c6 string, c7 string) -partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1 -POSTHOOK: query: -- SORT_QUERY_RESULTS - -create table T1(c1 string, c2 string, c3 string, c4 string, c5 string, c6 string, c7 string) -partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1 -PREHOOK: query: create table T2(c1 string, c2 string, c3 string, c0 string, c4 string, c5 string, c6 string, c7 string, c8 string, c9 string, c10 string, c11 string, c12 string, c13 string, c14 string, c15 string, c16 string, c17 string, c18 string, c19 string, c20 string, c21 string, c22 string, c23 string, c24 string, c25 string) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2 -POSTHOOK: query: create table T2(c1 string, c2 string, c3 string, c0 string, c4 string, c5 string, c6 string, c7 string, c8 string, c9 string, c10 string, c11 string, c12 string, c13 string, c14 string, c15 string, c16 string, c17 string, c18 string, c19 string, c20 string, c21 string, c22 string, c23 string, c24 string, c25 string) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2 -PREHOOK: query: create table T3 (c0 bigint, c1 bigint, c2 int) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T3 -POSTHOOK: query: create table T3 (c0 bigint, c1 bigint, c2 int) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T3 -PREHOOK: query: create table T4 (c0 bigint, c1 string, c2 string, c3 string, c4 string, c5 string, c6 string, c7 string, c8 string, c9 string, c10 string, c11 string, c12 string, c13 string, c14 string, c15 string, c16 string, c17 string, c18 string, c19 string, c20 string, c21 string, c22 string, c23 string, c24 string, c25 string, c26 string, c27 string, c28 string, c29 string, c30 string, c31 string, c32 string, c33 string, c34 string, c35 string, c36 string, c37 string, c38 string, c39 string, c40 string, c41 string, c42 string, c43 string, c44 string, c45 string, c46 string, c47 string, c48 string, c49 string, c50 string, c51 string, c52 string, c53 string, c54 string, c55 string, c56 string, c57 string, c58 string, c59 string, c60 string, c61 string, c62 string, c63 string, c64 string, c65 string, c66 string, c67 bigint, c68 string, c69 string, c70 bigint, c71 bigint, c72 bigint, c73 string, c74 string, c75 string, c76 string, c77 string, c78 string, c79 string, c80 string, c8 1 bigint, c82 bigint, c83 bigint) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T4 -POSTHOOK: query: create table T4 (c0 bigint, c1 string, c2 string, c3 string, c4 string, c5 string, c6 string, c7 string, c8 string, c9 string, c10 string, c11 string, c12 string, c13 string, c14 string, c15 string, c16 string, c17 string, c18 string, c19 string, c20 string, c21 string, c22 string, c23 string, c24 string, c25 string, c26 string, c27 string, c28 string, c29 string, c30 string, c31 string, c32 string, c33 string, c34 string, c35 string, c36 string, c37 string, c38 string, c39 string, c40 string, c41 string, c42 string, c43 string, c44 string, c45 string, c46 string, c47 string, c48 string, c49 string, c50 string, c51 string, c52 string, c53 string, c54 string, c55 string, c56 string, c57 string, c58 string, c59 string, c60 string, c61 string, c62 string, c63 string, c64 string, c65 string, c66 string, c67 bigint, c68 string, c69 string, c70 bigint, c71 bigint, c72 bigint, c73 string, c74 string, c75 string, c76 string, c77 string, c78 string, c79 string, c80 string, c 81 bigint, c82 bigint, c83 bigint) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T4 -PREHOOK: query: insert overwrite table T1 partition (ds='2010-04-17') select '5', '1', '1', '1', 0, 0,4 from src tablesample (1 rows) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@t1@ds=2010-04-17 -POSTHOOK: query: insert overwrite table T1 partition (ds='2010-04-17') select '5', '1', '1', '1', 0, 0,4 from src tablesample (1 rows) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@t1@ds=2010-04-17 -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c1 SIMPLE [] -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c2 SIMPLE [] -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c3 SIMPLE [] -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c4 SIMPLE [] -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c5 SIMPLE [] -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c6 SIMPLE [] -POSTHOOK: Lineage: t1 PARTITION(ds=2010-04-17).c7 SIMPLE [] -PREHOOK: query: insert overwrite table T2 partition(ds='2010-04-17') select '5','name', NULL, '2', 'kavin',NULL, '9', 'c', '8', '0', '0', '7', '1','2', '0', '3','2', NULL, '1', NULL, '3','2','0','0','5','10' from src tablesample (1 rows) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@t2@ds=2010-04-17 -POSTHOOK: query: insert overwrite table T2 partition(ds='2010-04-17') select '5','name', NULL, '2', 'kavin',NULL, '9', 'c', '8', '0', '0', '7', '1','2', '0', '3','2', NULL, '1', NULL, '3','2','0','0','5','10' from src tablesample (1 rows) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@t2@ds=2010-04-17 -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c0 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c1 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c10 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c11 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c12 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c13 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c14 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c15 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c16 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c17 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c18 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c19 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c2 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c20 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c21 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c22 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c23 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c24 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c25 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c3 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c4 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c5 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c6 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c7 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c8 SIMPLE [] -POSTHOOK: Lineage: t2 PARTITION(ds=2010-04-17).c9 SIMPLE [] -PREHOOK: query: insert overwrite table T3 partition (ds='2010-04-17') select 4,5,0 from src tablesample (1 rows) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@t3@ds=2010-04-17 -POSTHOOK: query: insert overwrite table T3 partition (ds='2010-04-17') select 4,5,0 from src tablesample (1 rows) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@t3@ds=2010-04-17 -POSTHOOK: Lineage: t3 PARTITION(ds=2010-04-17).c0 EXPRESSION [] -POSTHOOK: Lineage: t3 PARTITION(ds=2010-04-17).c1 EXPRESSION [] -POSTHOOK: Lineage: t3 PARTITION(ds=2010-04-17).c2 SIMPLE [] -PREHOOK: query: insert overwrite table T4 partition(ds='2010-04-17') -select 4,'1','1','8','4','5','1','0','9','U','2','2', '0','2','1','1','J','C','A','U', '2','s', '2',NULL, NULL, NULL,NULL, NULL, NULL,'1','j', 'S', '6',NULL,'1', '2', 'J', 'g', '1', 'e', '2', '1', '2', 'U', 'P', 'p', '3', '0', '0', '0', '1', '1', '1', '0', '0', '0', '6', '2', 'j',NULL, NULL, NULL,NULL,NULL, NULL, '5',NULL, 'j', 'j', 2, 2, 1, '2', '2', '1', '1', '1', '1', '1', '1', 1, 1, 32,NULL from src limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@t4@ds=2010-04-17 -POSTHOOK: query: insert overwrite table T4 partition(ds='2010-04-17') -select 4,'1','1','8','4','5','1','0','9','U','2','2', '0','2','1','1','J','C','A','U', '2','s', '2',NULL, NULL, NULL,NULL, NULL, NULL,'1','j', 'S', '6',NULL,'1', '2', 'J', 'g', '1', 'e', '2', '1', '2', 'U', 'P', 'p', '3', '0', '0', '0', '1', '1', '1', '0', '0', '0', '6', '2', 'j',NULL, NULL, NULL,NULL,NULL, NULL, '5',NULL, 'j', 'j', 2, 2, 1, '2', '2', '1', '1', '1', '1', '1', '1', 1, 1, 32,NULL from src limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@t4@ds=2010-04-17 -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c0 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c1 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c10 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c11 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c12 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c13 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c14 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c15 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c16 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c17 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c18 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c19 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c2 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c20 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c21 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c22 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c23 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c24 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c25 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c26 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c27 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c28 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c29 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c3 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c30 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c31 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c32 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c33 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c34 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c35 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c36 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c37 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c38 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c39 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c4 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c40 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c41 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c42 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c43 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c44 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c45 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c46 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c47 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c48 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c49 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c5 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c50 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c51 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c52 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c53 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c54 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c55 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c56 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c57 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c58 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c59 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c6 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c60 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c61 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c62 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c63 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c64 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c65 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c66 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c67 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c68 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c69 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c7 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c70 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c71 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c72 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c73 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c74 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c75 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c76 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c77 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c78 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c79 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c8 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c80 SIMPLE [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c81 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c82 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c83 EXPRESSION [] -POSTHOOK: Lineage: t4 PARTITION(ds=2010-04-17).c9 SIMPLE [] -PREHOOK: query: select * from T2 -PREHOOK: type: QUERY -PREHOOK: Input: default@t2 -PREHOOK: Input: default@t2@ds=2010-04-17 -#### A masked pattern was here #### -POSTHOOK: query: select * from T2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t2 -POSTHOOK: Input: default@t2@ds=2010-04-17 -#### A masked pattern was here #### -5 name NULL 2 kavin NULL 9 c 8 0 0 7 1 2 0 3 2 NULL 1 NULL 3 2 0 0 5 10 2010-04-17 -PREHOOK: query: select * from T1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t1@ds=2010-04-17 -#### A masked pattern was here #### -POSTHOOK: query: select * from T1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -POSTHOOK: Input: default@t1@ds=2010-04-17 -#### A masked pattern was here #### -5 1 1 1 0 0 4 2010-04-17 -PREHOOK: query: select * from T3 -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -PREHOOK: Input: default@t3@ds=2010-04-17 -#### A masked pattern was here #### -POSTHOOK: query: select * from T3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -POSTHOOK: Input: default@t3@ds=2010-04-17 -#### A masked pattern was here #### -4 5 0 2010-04-17 -PREHOOK: query: select * from T4 -PREHOOK: type: QUERY -PREHOOK: Input: default@t4 -PREHOOK: Input: default@t4@ds=2010-04-17 -#### A masked pattern was here #### -POSTHOOK: query: select * from T4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t4 -POSTHOOK: Input: default@t4@ds=2010-04-17 -#### A masked pattern was here #### -4 1 1 8 4 5 1 0 9 U 2 2 0 2 1 1 J C A U 2 s 2 NULL NULL NULL NULL NULL NULL 1 j S 6 NULL 1 2 J g 1 e 2 1 2 U P p 3 0 0 0 1 1 1 0 0 0 6 2 j NULL NULL NULL NULL NULL NULL 5 NULL NULL j 2 2 1 2 2 1 1 1 1 1 1 1 1 32 NULL 2010-04-17 -WARNING: Comparing a bigint and a string may result in a loss of precision. -PREHOOK: query: SELECT a.c1 as a_c1, b.c1 b_c1, d.c0 as d_c0 -FROM T1 a JOIN T2 b - ON (a.c1 = b.c1 AND a.ds='2010-04-17' AND b.ds='2010-04-17') - JOIN T3 c - ON (a.c1 = c.c1 AND a.ds='2010-04-17' AND c.ds='2010-04-17') - JOIN T4 d - ON (c.c0 = d.c0 AND c.ds='2010-04-17' AND d.ds='2010-04-17') -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t1@ds=2010-04-17 -PREHOOK: Input: default@t2 -PREHOOK: Input: default@t2@ds=2010-04-17 -PREHOOK: Input: default@t3 -PREHOOK: Input: default@t3@ds=2010-04-17 -PREHOOK: Input: default@t4 -PREHOOK: Input: default@t4@ds=2010-04-17 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.c1 as a_c1, b.c1 b_c1, d.c0 as d_c0 -FROM T1 a JOIN T2 b - ON (a.c1 = b.c1 AND a.ds='2010-04-17' AND b.ds='2010-04-17') - JOIN T3 c - ON (a.c1 = c.c1 AND a.ds='2010-04-17' AND c.ds='2010-04-17') - JOIN T4 d - ON (c.c0 = d.c0 AND c.ds='2010-04-17' AND d.ds='2010-04-17') -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -POSTHOOK: Input: default@t1@ds=2010-04-17 -POSTHOOK: Input: default@t2 -POSTHOOK: Input: default@t2@ds=2010-04-17 -POSTHOOK: Input: default@t3 -POSTHOOK: Input: default@t3@ds=2010-04-17 -POSTHOOK: Input: default@t4 -POSTHOOK: Input: default@t4@ds=2010-04-17 -#### A masked pattern was here #### -5 5 4 http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/groupby1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/groupby1.q.out b/ql/src/test/results/clientpositive/tez/groupby1.q.out deleted file mode 100644 index 3abc60f..0000000 --- a/ql/src/test/results/clientpositive/tez/groupby1.q.out +++ /dev/null @@ -1,426 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS - -CREATE TABLE dest_g1(key INT, value DOUBLE) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest_g1 -POSTHOOK: query: -- SORT_QUERY_RESULTS - -CREATE TABLE dest_g1(key INT, value DOUBLE) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest_g1 -PREHOOK: query: EXPLAIN -FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key -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: - 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: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 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: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reducer 2 - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - 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: double) - Reducer 3 - Reduce Operator Tree: - Group By Operator - aggregations: sum(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 - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 205 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 205 Data size: 2460 Basic stats: COMPLETE Column stats: COMPLETE - 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.dest_g1 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - 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.dest_g1 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest_g1 -POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest_g1 SELECT src.key, sum(substr(src.value,5)) GROUP BY src.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest_g1 -POSTHOOK: Lineage: dest_g1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g1.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: SELECT dest_g1.* FROM dest_g1 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest_g1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest_g1.* FROM dest_g1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest_g1 -#### A masked pattern was here #### -0 0.0 -10 10.0 -100 200.0 -103 206.0 -104 208.0 -105 105.0 -11 11.0 -111 111.0 -113 226.0 -114 114.0 -116 116.0 -118 236.0 -119 357.0 -12 24.0 -120 240.0 -125 250.0 -126 126.0 -128 384.0 -129 258.0 -131 131.0 -133 133.0 -134 268.0 -136 136.0 -137 274.0 -138 552.0 -143 143.0 -145 145.0 -146 292.0 -149 298.0 -15 30.0 -150 150.0 -152 304.0 -153 153.0 -155 155.0 -156 156.0 -157 157.0 -158 158.0 -160 160.0 -162 162.0 -163 163.0 -164 328.0 -165 330.0 -166 166.0 -167 501.0 -168 168.0 -169 676.0 -17 17.0 -170 170.0 -172 344.0 -174 348.0 -175 350.0 -176 352.0 -177 177.0 -178 178.0 -179 358.0 -18 36.0 -180 180.0 -181 181.0 -183 183.0 -186 186.0 -187 561.0 -189 189.0 -19 19.0 -190 190.0 -191 382.0 -192 192.0 -193 579.0 -194 194.0 -195 390.0 -196 196.0 -197 394.0 -199 597.0 -2 2.0 -20 20.0 -200 400.0 -201 201.0 -202 202.0 -203 406.0 -205 410.0 -207 414.0 -208 624.0 -209 418.0 -213 426.0 -214 214.0 -216 432.0 -217 434.0 -218 218.0 -219 438.0 -221 442.0 -222 222.0 -223 446.0 -224 448.0 -226 226.0 -228 228.0 -229 458.0 -230 1150.0 -233 466.0 -235 235.0 -237 474.0 -238 476.0 -239 478.0 -24 48.0 -241 241.0 -242 484.0 -244 244.0 -247 247.0 -248 248.0 -249 249.0 -252 252.0 -255 510.0 -256 512.0 -257 257.0 -258 258.0 -26 52.0 -260 260.0 -262 262.0 -263 263.0 -265 530.0 -266 266.0 -27 27.0 -272 544.0 -273 819.0 -274 274.0 -275 275.0 -277 1108.0 -278 556.0 -28 28.0 -280 560.0 -281 562.0 -282 564.0 -283 283.0 -284 284.0 -285 285.0 -286 286.0 -287 287.0 -288 576.0 -289 289.0 -291 291.0 -292 292.0 -296 296.0 -298 894.0 -30 30.0 -302 302.0 -305 305.0 -306 306.0 -307 614.0 -308 308.0 -309 618.0 -310 310.0 -311 933.0 -315 315.0 -316 948.0 -317 634.0 -318 954.0 -321 642.0 -322 644.0 -323 323.0 -325 650.0 -327 981.0 -33 33.0 -331 662.0 -332 332.0 -333 666.0 -335 335.0 -336 336.0 -338 338.0 -339 339.0 -34 34.0 -341 341.0 -342 684.0 -344 688.0 -345 345.0 -348 1740.0 -35 105.0 -351 351.0 -353 706.0 -356 356.0 -360 360.0 -362 362.0 -364 364.0 -365 365.0 -366 366.0 -367 734.0 -368 368.0 -369 1107.0 -37 74.0 -373 373.0 -374 374.0 -375 375.0 -377 377.0 -378 378.0 -379 379.0 -382 764.0 -384 1152.0 -386 386.0 -389 389.0 -392 392.0 -393 393.0 -394 394.0 -395 790.0 -396 1188.0 -397 794.0 -399 798.0 -4 4.0 -400 400.0 -401 2005.0 -402 402.0 -403 1209.0 -404 808.0 -406 1624.0 -407 407.0 -409 1227.0 -41 41.0 -411 411.0 -413 826.0 -414 828.0 -417 1251.0 -418 418.0 -419 419.0 -42 84.0 -421 421.0 -424 848.0 -427 427.0 -429 858.0 -43 43.0 -430 1290.0 -431 1293.0 -432 432.0 -435 435.0 -436 436.0 -437 437.0 -438 1314.0 -439 878.0 -44 44.0 -443 443.0 -444 444.0 -446 446.0 -448 448.0 -449 449.0 -452 452.0 -453 453.0 -454 1362.0 -455 455.0 -457 457.0 -458 916.0 -459 918.0 -460 460.0 -462 924.0 -463 926.0 -466 1398.0 -467 467.0 -468 1872.0 -469 2345.0 -47 47.0 -470 470.0 -472 472.0 -475 475.0 -477 477.0 -478 956.0 -479 479.0 -480 1440.0 -481 481.0 -482 482.0 -483 483.0 -484 484.0 -485 485.0 -487 487.0 -489 1956.0 -490 490.0 -491 491.0 -492 984.0 -493 493.0 -494 494.0 -495 495.0 -496 496.0 -497 497.0 -498 1494.0 -5 15.0 -51 102.0 -53 53.0 -54 54.0 -57 57.0 -58 116.0 -64 64.0 -65 65.0 -66 66.0 -67 134.0 -69 69.0 -70 210.0 -72 144.0 -74 74.0 -76 152.0 -77 77.0 -78 78.0 -8 8.0 -80 80.0 -82 82.0 -83 166.0 -84 168.0 -85 85.0 -86 86.0 -87 87.0 -9 9.0 -90 270.0 -92 92.0 -95 190.0 -96 96.0 -97 194.0 -98 196.0 http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/groupby2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/groupby2.q.out b/ql/src/test/results/clientpositive/tez/groupby2.q.out deleted file mode 100644 index f6ddf39..0000000 --- a/ql/src/test/results/clientpositive/tez/groupby2.q.out +++ /dev/null @@ -1,131 +0,0 @@ -PREHOOK: query: CREATE TABLE dest_g2(key STRING, c1 INT, c2 STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest_g2 -POSTHOOK: query: CREATE TABLE dest_g2(key STRING, c1 INT, c2 STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest_g2 -PREHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1) -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1) -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: - 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: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0) - keys: KEY._col0 (type: string) - mode: partial1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 100000 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: 100000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: double) - Reducer 3 - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: string) - mode: final - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 205 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 205 Data size: 76260 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 205 Data size: 76260 Basic stats: COMPLETE Column stats: COMPLETE - 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.dest_g2 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - 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.dest_g2 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest_g2 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest_g2 -POSTHOOK: Lineage: dest_g2.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g2.c2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_g2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: -- SORT_QUERY_RESULTS - -SELECT dest_g2.* FROM dest_g2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest_g2 -#### A masked pattern was here #### -POSTHOOK: query: -- SORT_QUERY_RESULTS - -SELECT dest_g2.* FROM dest_g2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest_g2 -#### A masked pattern was here #### -0 1 00.0 -1 71 116414.0 -2 69 225571.0 -3 62 332004.0 -4 74 452763.0 -5 6 5397.0 -6 5 6398.0 -7 6 7735.0 -8 8 8762.0 -9 7 91047.0 http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/groupby3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/groupby3.q.out b/ql/src/test/results/clientpositive/tez/groupby3.q.out deleted file mode 100644 index d9e974f..0000000 --- a/ql/src/test/results/clientpositive/tez/groupby3.q.out +++ /dev/null @@ -1,156 +0,0 @@ -PREHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(c1 DOUBLE, c2 DOUBLE, c3 DOUBLE, c4 DOUBLE, c5 DOUBLE, c6 DOUBLE, c7 DOUBLE, c8 DOUBLE, c9 DOUBLE) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1 -PREHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest1 SELECT - sum(substr(src.value,5)), - avg(substr(src.value,5)), - avg(DISTINCT substr(src.value,5)), - max(substr(src.value,5)), - min(substr(src.value,5)), - std(substr(src.value,5)), - stddev_samp(substr(src.value,5)), - variance(substr(src.value,5)), - var_samp(substr(src.value,5)) -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest1 SELECT - sum(substr(src.value,5)), - avg(substr(src.value,5)), - avg(DISTINCT substr(src.value,5)), - max(substr(src.value,5)), - min(substr(src.value,5)), - std(substr(src.value,5)), - stddev_samp(substr(src.value,5)), - variance(substr(src.value,5)), - var_samp(substr(src.value,5)) -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: - 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: src - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: substr(value, 5) (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 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: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Reduce Operator Tree: - Group By Operator - aggregations: sum(KEY._col0:0._col0), avg(KEY._col0:0._col0), avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), std(KEY._col0:0._col0), stddev_samp(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) - mode: partial1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double), _col1 (type: struct<count:bigint,sum:double,input:string>), _col2 (type: struct<count:bigint,sum:double,input:string>), _col3 (type: string), _col4 (type: string), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>) - Reducer 3 - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) - mode: final - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - 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.dest1 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - 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.dest1 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE dest1 SELECT - sum(substr(src.value,5)), - avg(substr(src.value,5)), - avg(DISTINCT substr(src.value,5)), - max(substr(src.value,5)), - min(substr(src.value,5)), - std(substr(src.value,5)), - stddev_samp(substr(src.value,5)), - variance(substr(src.value,5)), - var_samp(substr(src.value,5)) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE dest1 SELECT - sum(substr(src.value,5)), - avg(substr(src.value,5)), - avg(DISTINCT substr(src.value,5)), - max(substr(src.value,5)), - min(substr(src.value,5)), - std(substr(src.value,5)), - stddev_samp(substr(src.value,5)), - variance(substr(src.value,5)), - var_samp(substr(src.value,5)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c5 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c6 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c7 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c8 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.c9 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: SELECT dest1.* FROM dest1 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest1.* FROM dest1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1 -#### A masked pattern was here #### -130091.0 260.182 256.10355987055016 98.0 0.0 142.92680950752379 143.06995106518903 20428.07287599999 20469.010897795582
