You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by dj...@apache.org on 2018/05/08 18:42:52 UTC

[47/58] [abbrv] hive git commit: HIVE-18910 : Migrate to Murmur hash for shuffle and bucketing (Deepak Jaiswal, reviewed by Jasone Dere)

http://git-wip-us.apache.org/repos/asf/hive/blob/091fd962/ql/src/test/results/clientpositive/llap/bucket5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/bucket5.q.out b/ql/src/test/results/clientpositive/llap/bucket5.q.out
index 6649344..953353a 100644
--- a/ql/src/test/results/clientpositive/llap/bucket5.q.out
+++ b/ql/src/test/results/clientpositive/llap/bucket5.q.out
@@ -93,6 +93,7 @@ STAGE PLANS:
                   properties:
                     COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                     bucket_count -1
+                    bucketing_version 2
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 'default','default'
@@ -115,6 +116,7 @@ STAGE PLANS:
                     properties:
                       COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                       bucket_count -1
+                      bucketing_version 2
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 'default','default'
@@ -158,6 +160,7 @@ STAGE PLANS:
                         SORTBUCKETCOLSPREFIX TRUE
                         bucket_count 2
                         bucket_field_name key
+                        bucketing_version 2
                         column.name.delimiter ,
                         columns key,value
                         columns.comments 
@@ -246,6 +249,7 @@ STAGE PLANS:
                       properties:
                         COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                         bucket_count -1
+                        bucketing_version 2
                         column.name.delimiter ,
                         columns key,value
                         columns.comments 
@@ -330,6 +334,7 @@ STAGE PLANS:
                 SORTBUCKETCOLSPREFIX TRUE
                 bucket_count 2
                 bucket_field_name key
+                bucketing_version 2
                 column.name.delimiter ,
                 columns key,value
                 columns.comments 
@@ -369,6 +374,7 @@ STAGE PLANS:
               properties:
                 COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                 bucket_count -1
+                bucketing_version 2
                 column.name.delimiter ,
                 columns key,value
                 columns.comments 
@@ -426,6 +432,7 @@ STAGE PLANS:
                         properties:
                           COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                           bucket_count -1
+                          bucketing_version 2
                           column.name.delimiter ,
                           columns key,value
                           columns.comments 
@@ -457,6 +464,7 @@ STAGE PLANS:
                   properties:
                     COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                     bucket_count -1
+                    bucketing_version 2
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
@@ -479,6 +487,7 @@ STAGE PLANS:
                     properties:
                       COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                       bucket_count -1
+                      bucketing_version 2
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
@@ -519,6 +528,7 @@ STAGE PLANS:
                         properties:
                           COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                           bucket_count -1
+                          bucketing_version 2
                           column.name.delimiter ,
                           columns key,value
                           columns.comments 
@@ -550,6 +560,7 @@ STAGE PLANS:
                   properties:
                     COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                     bucket_count -1
+                    bucketing_version 2
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
@@ -572,6 +583,7 @@ STAGE PLANS:
                     properties:
                       COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                       bucket_count -1
+                      bucketing_version 2
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
@@ -637,6 +649,7 @@ Table Type:         	MANAGED_TABLE
 Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	{\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
 	SORTBUCKETCOLSPREFIX	TRUE                
+	bucketing_version   	2                   
 	numFiles            	2                   
 	numRows             	500                 
 	rawDataSize         	5312                
@@ -661,16 +674,16 @@ POSTHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 1 OUT OF 2) s
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@bucketed_table
 POSTHOOK: Output: hdfs://### HDFS PATH ###
-0	val_0
-0	val_0
-0	val_0
 2	val_2
-4	val_4
-8	val_8
 10	val_10
-12	val_12
-12	val_12
-18	val_18
+17	val_17
+19	val_19
+20	val_20
+27	val_27
+30	val_30
+41	val_41
+43	val_43
+51	val_51
 PREHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 2 OUT OF 2) s LIMIT 10
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bucketed_table
@@ -679,16 +692,16 @@ POSTHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 2 OUT OF 2) s
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@bucketed_table
 POSTHOOK: Output: hdfs://### HDFS PATH ###
+0	val_0
+0	val_0
+0	val_0
+4	val_4
 5	val_5
 5	val_5
 5	val_5
+8	val_8
 9	val_9
 11	val_11
-15	val_15
-15	val_15
-17	val_17
-19	val_19
-27	val_27
 PREHOOK: query: SELECT COUNT(DISTINCT INPUT__FILE__NAME) FROM bucketed_table
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bucketed_table

http://git-wip-us.apache.org/repos/asf/hive/blob/091fd962/ql/src/test/results/clientpositive/llap/bucket6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/bucket6.q.out b/ql/src/test/results/clientpositive/llap/bucket6.q.out
index 1994aeb..fe74066 100644
--- a/ql/src/test/results/clientpositive/llap/bucket6.q.out
+++ b/ql/src/test/results/clientpositive/llap/bucket6.q.out
@@ -135,42 +135,18 @@ POSTHOOK: query: select * from src_bucket limit 100
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@src_bucket
 POSTHOOK: Output: hdfs://### HDFS PATH ###
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-0	val_0
-103	val_103
-103	val_103
-103	val_103
-103	val_103
-103	val_103
-103	val_103
-103	val_103
-103	val_103
-105	val_105
-105	val_105
-105	val_105
-105	val_105
-11	val_11
-11	val_11
-11	val_11
-11	val_11
-114	val_114
-114	val_114
-114	val_114
-114	val_114
-116	val_116
-116	val_116
-116	val_116
-116	val_116
+10	val_10
+10	val_10
+10	val_10
+10	val_10
+104	val_104
+104	val_104
+104	val_104
+104	val_104
+104	val_104
+104	val_104
+104	val_104
+104	val_104
 118	val_118
 118	val_118
 118	val_118
@@ -179,34 +155,50 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
 118	val_118
 118	val_118
 118	val_118
-125	val_125
-125	val_125
-125	val_125
-125	val_125
-125	val_125
-125	val_125
-125	val_125
-125	val_125
-129	val_129
-129	val_129
-129	val_129
-129	val_129
-129	val_129
-129	val_129
-129	val_129
-129	val_129
-134	val_134
-134	val_134
-134	val_134
-134	val_134
-134	val_134
-134	val_134
-134	val_134
-134	val_134
-136	val_136
-136	val_136
-136	val_136
-136	val_136
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+119	val_119
+120	val_120
+120	val_120
+120	val_120
+120	val_120
+120	val_120
+120	val_120
+120	val_120
+120	val_120
+126	val_126
+126	val_126
+126	val_126
+126	val_126
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+128	val_128
+131	val_131
+131	val_131
+131	val_131
+131	val_131
+133	val_133
+133	val_133
+133	val_133
+133	val_133
 138	val_138
 138	val_138
 138	val_138
@@ -223,10 +215,6 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
 138	val_138
 138	val_138
 138	val_138
-143	val_143
-143	val_143
-143	val_143
-143	val_143
 145	val_145
 145	val_145
 145	val_145
@@ -235,3 +223,15 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
 149	val_149
 149	val_149
 149	val_149
+149	val_149
+149	val_149
+149	val_149
+149	val_149
+15	val_15
+15	val_15
+15	val_15
+15	val_15
+15	val_15
+15	val_15
+15	val_15
+15	val_15

http://git-wip-us.apache.org/repos/asf/hive/blob/091fd962/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out b/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out
index 26024b0..3a7d744 100644
--- a/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out
+++ b/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out
@@ -347,8 +347,8 @@ POSTHOOK: Input: default@clustergroupby
 POSTHOOK: Input: default@clustergroupby@ds=101
 #### A masked pattern was here ####
 1	10
-2	74
 3	416
+2	74
 PREHOOK: query: explain
 select abs(length(key)), count(1) from clustergroupby  where ds='101'  group by abs(length(key)) limit 10
 PREHOOK: type: QUERY
@@ -428,8 +428,8 @@ POSTHOOK: Input: default@clustergroupby
 POSTHOOK: Input: default@clustergroupby@ds=101
 #### A masked pattern was here ####
 1	10
-2	74
 3	416
+2	74
 PREHOOK: query: explain
 select key, count(1) from clustergroupby  where ds='101'  group by key,'a' order by key,'a' limit 10
 PREHOOK: type: QUERY
@@ -712,312 +712,312 @@ POSTHOOK: Input: default@clustergroupby@ds=101
 #### A masked pattern was here ####
 10	2
 100	4
+103	4
 104	4
-111	2
-114	2
-116	2
+105	2
+11	2
 126	2
 128	6
-131	2
+129	4
+133	2
 134	4
+136	2
+143	2
+149	4
 152	4
-155	2
+153	2
+157	2
+162	2
+166	2
 169	8
-17	2
 170	2
-172	4
-178	2
-179	4
-189	2
-19	2
-192	2
-194	2
-195	4
-199	6
-20	2
-207	4
+174	4
+176	4
+193	6
+196	2
+201	2
+205	4
+209	4
 213	4
 218	2
+221	4
 223	4
-229	4
 233	4
-235	2
+239	4
 24	4
-256	4
-257	2
+241	2
+242	4
+247	2
+248	2
 26	4
-265	4
-266	2
-27	2
-278	4
-280	4
-284	2
-291	2
-30	2
+263	2
+272	4
+275	2
+285	2
+296	2
+298	6
 302	2
-305	2
-316	6
-321	4
+307	4
+310	2
 323	2
-33	2
+325	4
 333	4
+335	2
 338	2
-344	4
-353	4
-356	2
-364	2
-368	2
-369	6
-37	4
+360	2
+362	2
+367	4
+375	2
 377	2
-378	2
-386	2
+384	6
 392	2
-397	4
-404	4
-407	2
-411	2
-418	2
+399	4
+401	10
+402	2
+403	6
+413	4
+417	6
 419	2
-424	4
-430	6
-432	2
-436	2
-437	2
-448	2
-454	6
-457	2
-468	8
-477	2
+42	4
+427	2
+438	6
+44	2
+458	4
+459	4
+466	6
+469	10
+472	2
+475	2
+478	4
 479	2
-490	2
-492	4
-493	2
+483	2
+489	8
 495	2
 496	2
-497	2
+5	6
 57	2
-67	4
-8	2
-80	2
-85	2
+58	4
+64	2
+66	2
+69	2
+72	4
+76	4
+77	2
 9	2
-92	2
-97	4
-105	2
-11	2
+90	6
+0	6
 113	4
-136	2
+114	2
+116	2
+118	4
 137	4
 138	8
-143	2
-150	2
+145	2
+146	4
+155	2
 158	2
-160	2
-162	2
+164	4
 165	4
-166	2
-174	4
-177	2
-18	4
-180	2
+178	2
+181	2
+183	2
 186	2
-196	2
-197	4
-217	4
-219	4
-226	2
+189	2
+190	2
+191	4
+194	2
+195	4
+199	6
+2	2
+207	4
+208	6
+214	2
+216	4
+222	2
+224	4
+229	4
 230	10
 238	4
-242	4
-248	2
-252	2
+244	2
+258	2
 260	2
-263	2
-274	2
-277	8
-296	2
-307	4
-308	2
-325	4
-327	6
+262	2
+266	2
+27	2
+273	6
+28	2
+284	2
+288	4
+30	2
+315	2
+321	4
+33	2
 342	4
-348	10
 35	6
-351	2
-367	4
+364	2
+365	2
+366	2
+368	2
+386	2
 389	2
-393	2
 394	2
+396	6
+397	4
 4	2
-403	6
-409	6
+41	2
 414	4
 421	2
-427	2
-429	4
-435	2
-438	6
-439	4
+444	2
+446	2
+448	2
+452	2
+454	6
 455	2
-458	4
 460	2
-462	4
-475	2
-478	4
-480	6
-484	2
-487	2
-53	2
-58	4
-66	2
-69	2
-77	2
+463	4
+482	2
+492	4
+493	2
+65	2
 78	2
-83	4
-90	6
-95	4
-103	4
+80	2
+97	4
+111	2
+12	4
 120	4
-129	4
-133	2
-145	2
-146	4
-149	4
-15	4
-157	2
-181	2
-187	6
-191	4
-2	2
-200	4
-201	2
-202	2
+131	2
+150	2
+156	2
+160	2
+163	2
+167	6
+168	2
+17	2
+175	4
+180	2
+20	2
 203	4
-208	6
-214	2
-216	4
-222	2
-224	4
-228	2
+226	2
 237	4
-239	4
-241	2
-244	2
 255	4
-258	2
-262	2
-273	6
-275	2
-28	2
+256	4
+274	2
+277	8
+281	4
 282	4
-285	2
 286	2
 287	2
-288	4
+289	2
 292	2
-298	6
-310	2
-311	6
+308	2
+309	4
+318	6
+327	6
 332	2
-335	2
-336	2
 339	2
-360	2
-362	2
-373	2
-384	6
-395	4
-396	6
-402	2
-417	6
-42	4
+34	2
+341	2
+348	10
+356	2
+37	4
+374	2
+379	2
+382	4
+409	6
+429	4
 43	2
-444	2
-449	2
-453	2
-459	4
-47	2
+430	6
+431	6
+432	2
+435	2
+437	2
+439	4
+443	2
+457	2
+462	4
+467	2
+470	2
 481	2
-482	2
-483	2
-485	2
-489	8
+487	2
 494	2
-65	2
-72	4
+51	4
+70	6
 74	2
-76	4
 82	2
-86	2
-87	2
-96	2
-0	6
-118	4
+83	4
+84	4
 119	6
-12	4
 125	4
-153	2
-156	2
-163	2
-164	4
-167	6
-168	2
-175	4
-176	4
-183	2
-190	2
-193	6
-205	4
-209	4
-221	4
-247	2
+15	4
+172	4
+177	2
+179	4
+18	4
+187	6
+19	2
+192	2
+197	4
+200	4
+202	2
+217	4
+219	4
+228	2
+235	2
 249	2
-272	4
-281	4
+252	2
+257	2
+265	4
+278	4
+280	4
 283	2
-289	2
+291	2
+305	2
 306	2
-309	4
-315	2
+311	6
+316	6
 317	4
-318	6
 322	4
 331	4
-34	2
-341	2
+336	2
+344	4
 345	2
-365	2
-366	2
-374	2
-375	2
-379	2
-382	4
-399	4
+351	2
+353	4
+369	6
+373	2
+378	2
+393	2
+395	4
 400	2
-401	10
+404	4
 406	8
-41	2
-413	4
-431	6
-44	2
-443	2
-446	2
-452	2
-463	4
-466	6
-467	2
-469	10
-470	2
-472	2
+407	2
+411	2
+418	2
+424	4
+436	2
+449	2
+453	2
+468	8
+47	2
+477	2
+480	6
+484	2
+485	2
+490	2
 491	2
+497	2
 498	6
-5	6
-51	4
+53	2
 54	2
-64	2
-70	6
-84	4
+67	4
+8	2
+85	2
+86	2
+87	2
+92	2
+95	4
+96	2
 98	4
 PREHOOK: query: explain
 select key, count(1) from clustergroupby  group by key, 3

http://git-wip-us.apache.org/repos/asf/hive/blob/091fd962/ql/src/test/results/clientpositive/llap/bucket_many.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/bucket_many.q.out b/ql/src/test/results/clientpositive/llap/bucket_many.q.out
index 2202745..d1fb481 100644
--- a/ql/src/test/results/clientpositive/llap/bucket_many.q.out
+++ b/ql/src/test/results/clientpositive/llap/bucket_many.q.out
@@ -60,6 +60,7 @@ STAGE PLANS:
                   properties:
                     COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                     bucket_count -1
+                    bucketing_version 2
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 'default','default'
@@ -81,6 +82,7 @@ STAGE PLANS:
                     properties:
                       COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                       bucket_count -1
+                      bucketing_version 2
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 'default','default'
@@ -122,6 +124,7 @@ STAGE PLANS:
                         COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                         bucket_count 256
                         bucket_field_name key
+                        bucketing_version 2
                         column.name.delimiter ,
                         columns key,value
                         columns.comments 
@@ -204,6 +207,7 @@ STAGE PLANS:
                 COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
                 bucket_count 256
                 bucket_field_name key
+                bucketing_version 2
                 column.name.delimiter ,
                 columns key,value
                 columns.comments 
@@ -244,10 +248,10 @@ POSTHOOK: Output: default@bucket_many
 POSTHOOK: Lineage: bucket_many.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
 POSTHOOK: Lineage: bucket_many.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
 PREHOOK: query: explain
-select * from bucket_many tablesample (bucket 1 out of 256) s
+select * from bucket_many tablesample (bucket 2 out of 256) s
 PREHOOK: type: QUERY
 POSTHOOK: query: explain
-select * from bucket_many tablesample (bucket 1 out of 256) s
+select * from bucket_many tablesample (bucket 2 out of 256) s
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-0 is a root stage
@@ -260,22 +264,25 @@ STAGE PLANS:
         TableScan
           alias: s
           Filter Operator
-            predicate: (((hash(key) & 2147483647) % 256) = 0) (type: boolean)
+            predicate: (((hash(key) & 2147483647) % 256) = 1) (type: boolean)
             Select Operator
               expressions: key (type: int), value (type: string)
               outputColumnNames: _col0, _col1
               ListSink
 
-PREHOOK: query: select * from bucket_many tablesample (bucket 1 out of 256) s
+PREHOOK: query: select * from bucket_many tablesample (bucket 2 out of 256) s
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bucket_many
 #### A masked pattern was here ####
-POSTHOOK: query: select * from bucket_many tablesample (bucket 1 out of 256) s
+POSTHOOK: query: select * from bucket_many tablesample (bucket 2 out of 256) s
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@bucket_many
 #### A masked pattern was here ####
-256	val_256
-256	val_256
-0	val_0
-0	val_0
-0	val_0
+462	val_462
+462	val_462
+309	val_309
+282	val_282
+282	val_282
+176	val_176
+176	val_176
+309	val_309