You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vg...@apache.org on 2017/05/18 20:29:53 UTC
hive git commit: HIVE-16636: Add TPC-DS query24 to TestPerCli
driver.(Vineet Garg, reviewed by Ashutosh Chauhan)
Repository: hive
Updated Branches:
refs/heads/master 1dfe101a7 -> 189d45429
HIVE-16636: Add TPC-DS query24 to TestPerCli driver.(Vineet Garg, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/189d4542
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/189d4542
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/189d4542
Branch: refs/heads/master
Commit: 189d45429e1f7b1908bafa65989055565e826216
Parents: 1dfe101
Author: Vineet Garg <vg...@hortonworks.com>
Authored: Thu May 18 13:29:22 2017 -0700
Committer: Vineet Garg <vg...@hortonworks.com>
Committed: Thu May 18 13:29:22 2017 -0700
----------------------------------------------------------------------
.../test/queries/clientpositive/perf/query24.q | 51 +++
.../results/clientpositive/perf/query24.q.out | 314 +++++++++++++++++++
2 files changed, 365 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/189d4542/ql/src/test/queries/clientpositive/perf/query24.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/perf/query24.q b/ql/src/test/queries/clientpositive/perf/query24.q
new file mode 100644
index 0000000..b9b747f
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/perf/query24.q
@@ -0,0 +1,51 @@
+set hive.mapred.mode=nonstrict;
+
+explain with ssales as
+ (select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size
+ ,sum(ss_sales_price) netpaid
+ from store_sales
+ ,store_returns
+ ,store
+ ,item
+ ,customer
+ ,customer_address
+ where ss_ticket_number = sr_ticket_number
+ and ss_item_sk = sr_item_sk
+ and ss_customer_sk = c_customer_sk
+ and ss_item_sk = i_item_sk
+ and ss_store_sk = s_store_sk
+ and c_birth_country = upper(ca_country)
+ and s_zip = ca_zip
+ and s_market_id=7
+ group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size)
+ select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,sum(netpaid) paid
+ from ssales
+ where i_color = 'orchid'
+ group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ having sum(netpaid) > (select 0.05*avg(netpaid)
+ from ssales)
+ ;
+
http://git-wip-us.apache.org/repos/asf/hive/blob/189d4542/ql/src/test/results/clientpositive/perf/query24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query24.q.out b/ql/src/test/results/clientpositive/perf/query24.q.out
new file mode 100644
index 0000000..3e43dad
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/query24.q.out
@@ -0,0 +1,314 @@
+Warning: Shuffle Join MERGEJOIN[154][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product
+PREHOOK: query: explain with ssales as
+ (select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size
+ ,sum(ss_sales_price) netpaid
+ from store_sales
+ ,store_returns
+ ,store
+ ,item
+ ,customer
+ ,customer_address
+ where ss_ticket_number = sr_ticket_number
+ and ss_item_sk = sr_item_sk
+ and ss_customer_sk = c_customer_sk
+ and ss_item_sk = i_item_sk
+ and ss_store_sk = s_store_sk
+ and c_birth_country = upper(ca_country)
+ and s_zip = ca_zip
+ and s_market_id=7
+ group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size)
+ select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,sum(netpaid) paid
+ from ssales
+ where i_color = 'orchid'
+ group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ having sum(netpaid) > (select 0.05*avg(netpaid)
+ from ssales)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain with ssales as
+ (select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size
+ ,sum(ss_sales_price) netpaid
+ from store_sales
+ ,store_returns
+ ,store
+ ,item
+ ,customer
+ ,customer_address
+ where ss_ticket_number = sr_ticket_number
+ and ss_item_sk = sr_item_sk
+ and ss_customer_sk = c_customer_sk
+ and ss_item_sk = i_item_sk
+ and ss_store_sk = s_store_sk
+ and c_birth_country = upper(ca_country)
+ and s_zip = ca_zip
+ and s_market_id=7
+ group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size)
+ select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,sum(netpaid) paid
+ from ssales
+ where i_color = 'orchid'
+ group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ having sum(netpaid) > (select 0.05*avg(netpaid)
+ from ssales)
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE)
+Reducer 16 <- Map 23 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+Reducer 17 <- Map 24 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE)
+Reducer 18 <- Map 25 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE)
+Reducer 19 <- Map 26 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
+Reducer 20 <- Reducer 19 (SIMPLE_EDGE)
+Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE)
+Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Map 13 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+Reducer 8 <- Reducer 21 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 8
+ File Output Operator [FS_91]
+ Select Operator [SEL_90] (rows=77303902 width=489)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_89] (rows=77303902 width=489)
+ predicate:(_col3 > _col4)
+ Merge Join Operator [MERGEJOIN_154] (rows=231911707 width=489)
+ Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"]
+ <-Reducer 21 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_87]
+ Select Operator [SEL_85] (rows=1 width=400)
+ Output:["_col0"]
+ Group By Operator [GBY_84] (rows=1 width=400)
+ Output:["_col0"],aggregations:["avg(VALUE._col0)"]
+ <-Reducer 20 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_83]
+ Group By Operator [GBY_82] (rows=1 width=400)
+ Output:["_col0"],aggregations:["avg(_col10)"]
+ Select Operator [SEL_80] (rows=463823414 width=88)
+ Output:["_col10"]
+ Group By Operator [GBY_79] (rows=463823414 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9
+ <-Reducer 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_78]
+ PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Group By Operator [GBY_77] (rows=927646829 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col22, _col17, _col18, _col19, _col20, _col21, _col13, _col14, _col8, _col10
+ Merge Join Operator [MERGEJOIN_153] (rows=927646829 width=88)
+ Conds:RS_73._col11, _col15=RS_74._col1, upper(_col2)(Inner),Output:["_col4","_col8","_col10","_col13","_col14","_col17","_col18","_col19","_col20","_col21","_col22"]
+ <-Map 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_74]
+ PartitionCols:_col1, upper(_col2)
+ Select Operator [SEL_60] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_143] (rows=40000000 width=1014)
+ predicate:(ca_zip is not null and ca_country is not null)
+ TableScan [TS_58] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_state","ca_zip","ca_country"]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_73]
+ PartitionCols:_col11, _col15
+ Merge Join Operator [MERGEJOIN_152] (rows=843315281 width=88)
+ Conds:RS_70._col0=RS_71._col0(Inner),Output:["_col4","_col8","_col10","_col11","_col13","_col14","_col15","_col17","_col18","_col19","_col20","_col21"]
+ <-Map 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_71]
+ PartitionCols:_col0
+ Select Operator [SEL_57] (rows=462000 width=1436)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_142] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_55] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"]
+ <-Reducer 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_70]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_151] (rows=766650239 width=88)
+ Conds:RS_67._col1=RS_68._col0(Inner),Output:["_col0","_col4","_col8","_col10","_col11","_col13","_col14","_col15"]
+ <-Map 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_68]
+ PartitionCols:_col0
+ Select Operator [SEL_54] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_141] (rows=80000000 width=860)
+ predicate:(c_customer_sk is not null and c_birth_country is not null)
+ TableScan [TS_52] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"]
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_67]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_150] (rows=696954748 width=88)
+ Conds:RS_64._col2=RS_65._col0(Inner),Output:["_col0","_col1","_col4","_col8","_col10","_col11"]
+ <-Map 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_65]
+ PartitionCols:_col0
+ Select Operator [SEL_51] (rows=852 width=1910)
+ Output:["_col0","_col1","_col3","_col4"]
+ Filter Operator [FIL_140] (rows=852 width=1910)
+ predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null)
+ TableScan [TS_49] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_64]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_149] (rows=633595212 width=88)
+ Conds:RS_61._col0, _col3=RS_62._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col4"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_61]
+ PartitionCols:_col0, _col3
+ Select Operator [SEL_45] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_138] (rows=575995635 width=88)
+ predicate:(ss_item_sk is not null and ss_ticket_number is not null and ss_store_sk is not null and ss_customer_sk is not null)
+ TableScan [TS_43] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"]
+ <-Map 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_62]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_48] (rows=57591150 width=77)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_139] (rows=57591150 width=77)
+ predicate:(sr_item_sk is not null and sr_ticket_number is not null)
+ TableScan [TS_46] (rows=57591150 width=77)
+ default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"]
+ <-Reducer 7 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_86]
+ Select Operator [SEL_42] (rows=231911707 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Group By Operator [GBY_41] (rows=231911707 width=88)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col1, _col2, _col7
+ Select Operator [SEL_37] (rows=463823414 width=88)
+ Output:["_col1","_col2","_col7","_col9"]
+ Group By Operator [GBY_36] (rows=463823414 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8
+ <-Reducer 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_35]
+ PartitionCols:_col0, _col1, _col2
+ Group By Operator [GBY_34] (rows=927646829 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col19, _col20, _col14, _col22, _col8, _col9, _col11, _col12, _col16
+ Merge Join Operator [MERGEJOIN_148] (rows=927646829 width=88)
+ Conds:RS_30._col17, _col21=RS_31._col1, upper(_col2)(Inner),Output:["_col4","_col8","_col9","_col11","_col12","_col14","_col16","_col19","_col20","_col22"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_31]
+ PartitionCols:_col1, upper(_col2)
+ Select Operator [SEL_17] (rows=40000000 width=1014)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_137] (rows=40000000 width=1014)
+ predicate:(ca_zip is not null and ca_country is not null)
+ TableScan [TS_15] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_state","ca_zip","ca_country"]
+ <-Reducer 5 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col17, _col21
+ Merge Join Operator [MERGEJOIN_147] (rows=843315281 width=88)
+ Conds:RS_27._col1=RS_28._col0(Inner),Output:["_col4","_col8","_col9","_col11","_col12","_col14","_col16","_col17","_col19","_col20","_col21"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_28]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_136] (rows=80000000 width=860)
+ predicate:(c_customer_sk is not null and c_birth_country is not null)
+ TableScan [TS_12] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_27]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_146] (rows=766650239 width=88)
+ Conds:RS_24._col2=RS_25._col0(Inner),Output:["_col1","_col4","_col8","_col9","_col11","_col12","_col14","_col16","_col17"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=852 width=1910)
+ Output:["_col0","_col1","_col3","_col4"]
+ Filter Operator [FIL_135] (rows=852 width=1910)
+ predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null)
+ TableScan [TS_9] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_145] (rows=696954748 width=88)
+ Conds:RS_21._col0=RS_22._col0(Inner),Output:["_col1","_col2","_col4","_col8","_col9","_col11","_col12"]
+ <-Map 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_22]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=231000 width=1436)
+ Output:["_col0","_col1","_col2","_col4","_col5"]
+ Filter Operator [FIL_134] (rows=231000 width=1436)
+ predicate:((i_color = 'orchid') and i_item_sk is not null)
+ TableScan [TS_6] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_144] (rows=633595212 width=88)
+ Conds:RS_18._col0, _col3=RS_19._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col4"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col0, _col3
+ Select Operator [SEL_2] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_132] (rows=575995635 width=88)
+ predicate:(ss_item_sk is not null and ss_ticket_number is not null and ss_store_sk is not null and ss_customer_sk is not null)
+ TableScan [TS_0] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"]
+ <-Map 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_5] (rows=57591150 width=77)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_133] (rows=57591150 width=77)
+ predicate:(sr_item_sk is not null and sr_ticket_number is not null)
+ TableScan [TS_3] (rows=57591150 width=77)
+ default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"]
+