You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2016/08/12 22:54:35 UTC
hive git commit: HIVE-14504: tez_join_hash.q test is slow (Prasanth
Jayachandran reviewed by Siddharth Seth)
Repository: hive
Updated Branches:
refs/heads/master bff1b9e9e -> bfdc74ff2
HIVE-14504: tez_join_hash.q test is slow (Prasanth Jayachandran reviewed by Siddharth Seth)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/bfdc74ff
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/bfdc74ff
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/bfdc74ff
Branch: refs/heads/master
Commit: bfdc74ff2a966ed8ff13afa453b59d56032670a4
Parents: bff1b9e
Author: Prasanth Jayachandran <pr...@apache.org>
Authored: Fri Aug 12 15:54:25 2016 -0700
Committer: Prasanth Jayachandran <pr...@apache.org>
Committed: Fri Aug 12 15:54:25 2016 -0700
----------------------------------------------------------------------
.../test/resources/testconfiguration.properties | 2 +-
.../test/queries/clientpositive/tez_join_hash.q | 11 +-
.../clientpositive/llap/tez_join_hash.q.out | 341 +------
.../clientpositive/tez/tez_join_hash.q.out | 405 +-------
.../results/clientpositive/tez_join_hash.q.out | 920 +++++++++++++++++++
5 files changed, 962 insertions(+), 717 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/bfdc74ff/itests/src/test/resources/testconfiguration.properties
----------------------------------------------------------------------
diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties
index 5aeca9c..1cc7de1 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -204,6 +204,7 @@ minitez.query.files.shared=acid_globallimit.q,\
stats_only_null.q,\
subquery_exists.q,\
subquery_in.q,\
+ tez_join_hash.q,\
temp_table.q,\
transform1.q,\
transform2.q,\
@@ -424,7 +425,6 @@ minitez.query.files=acid_vectorization_missing_cols.q,\
tez_dynpart_hashjoin_3.q,\
tez_vector_dynpart_hashjoin_1.q,\
tez_vector_dynpart_hashjoin_2.q,\
- tez_join_hash.q,\
tez_join_result_complex.q,\
tez_join_tests.q,\
tez_joins_explain.q,\
http://git-wip-us.apache.org/repos/asf/hive/blob/bfdc74ff/ql/src/test/queries/clientpositive/tez_join_hash.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/tez_join_hash.q b/ql/src/test/queries/clientpositive/tez_join_hash.q
index f2808b8..158c99b 100644
--- a/ql/src/test/queries/clientpositive/tez_join_hash.q
+++ b/ql/src/test/queries/clientpositive/tez_join_hash.q
@@ -5,7 +5,6 @@ set hive.explain.user=false;
create table orc_src (key string, value string) STORED AS ORC;
insert into table orc_src select * from src;
-set hive.execution.engine=tez;
set hive.vectorized.execution.enabled=true;
set hive.auto.convert.join.noconditionaltask.size=1;
set hive.exec.reducers.bytes.per.reducer=20000;
@@ -22,7 +21,7 @@ set hive.mapjoin.hybridgrace.minwbsize=350;
set hive.mapjoin.hybridgrace.minnumpartitions=8;
explain
-select count(*) from (select x.key as key, y.value as value from
+select key, count(*) from (select x.key as key, y.value as value from
srcpart x join srcpart y on (x.key = y.key)
union all
select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value;
@@ -31,11 +30,3 @@ select key, count(*) from (select x.key as key, y.value as value from
srcpart x join srcpart y on (x.key = y.key)
union all
select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value;
-
-set hive.execution.engine=mr;
-select key, count(*) from (select x.key as key, y.value as value from
-srcpart x join srcpart y on (x.key = y.key)
-union all
-select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value;
-
-
http://git-wip-us.apache.org/repos/asf/hive/blob/bfdc74ff/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out
index 26d12e5..f14d9b0 100644
--- a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out
@@ -130,13 +130,13 @@ POSTHOOK: Input: default@src
#### A masked pattern was here ####
1028
PREHOOK: query: explain
-select count(*) from (select x.key as key, y.value as value from
+select key, count(*) from (select x.key as key, y.value as value from
srcpart x join srcpart y on (x.key = y.key)
union all
select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
PREHOOK: type: QUERY
POSTHOOK: query: explain
-select count(*) from (select x.key as key, y.value as value from
+select key, count(*) from (select x.key as key, y.value as value from
srcpart x join srcpart y on (x.key = y.key)
union all
select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
@@ -288,8 +288,8 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2310 Data size: 24541 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: bigint)
- outputColumnNames: _col0
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2310 Data size: 24541 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -640,336 +640,3 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
96 20
97 144
98 144
-PREHOOK: query: select key, count(*) from (select x.key as key, y.value as value from
-srcpart x join srcpart y on (x.key = y.key)
-union all
-select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select key, count(*) from (select x.key as key, y.value as value from
-srcpart x join srcpart y on (x.key = y.key)
-union all
-select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-0 468
-10 20
-100 144
-103 144
-104 144
-105 20
-11 20
-111 20
-113 144
-114 20
-116 20
-118 144
-119 468
-12 144
-120 144
-125 144
-126 20
-128 468
-129 144
-131 20
-133 20
-134 144
-136 20
-137 144
-138 1088
-143 20
-145 20
-146 144
-149 144
-15 144
-150 20
-152 144
-153 20
-155 20
-156 20
-157 20
-158 20
-160 20
-162 20
-163 20
-164 144
-165 144
-166 20
-167 468
-168 20
-169 1088
-17 20
-170 20
-172 144
-174 144
-175 144
-176 144
-177 20
-178 20
-179 144
-18 144
-180 20
-181 20
-183 20
-186 20
-187 468
-189 20
-19 20
-190 20
-191 144
-192 20
-193 468
-194 20
-195 144
-196 20
-197 144
-199 468
-2 20
-20 20
-200 144
-201 20
-202 20
-203 144
-205 144
-207 144
-208 468
-209 144
-213 144
-214 20
-216 144
-217 144
-218 20
-219 144
-221 144
-222 20
-223 144
-224 144
-226 20
-228 20
-229 144
-230 2100
-233 144
-235 20
-237 144
-238 144
-239 144
-24 144
-241 20
-242 144
-244 20
-247 20
-248 20
-249 20
-252 20
-255 144
-256 144
-257 20
-258 20
-26 144
-260 20
-262 20
-263 20
-265 144
-266 20
-27 20
-272 144
-273 468
-274 20
-275 20
-277 1088
-278 144
-28 20
-280 144
-281 144
-282 144
-283 20
-284 20
-285 20
-286 20
-287 20
-288 144
-289 20
-291 20
-292 20
-296 20
-298 468
-30 20
-302 20
-305 20
-306 20
-307 144
-308 20
-309 144
-310 20
-311 468
-315 20
-316 468
-317 144
-318 468
-321 144
-322 144
-323 20
-325 144
-327 468
-33 20
-331 144
-332 20
-333 144
-335 20
-336 20
-338 20
-339 20
-34 20
-341 20
-342 144
-344 144
-345 20
-348 2100
-35 468
-351 20
-353 144
-356 20
-360 20
-362 20
-364 20
-365 20
-366 20
-367 144
-368 20
-369 468
-37 144
-373 20
-374 20
-375 20
-377 20
-378 20
-379 20
-382 144
-384 468
-386 20
-389 20
-392 20
-393 20
-394 20
-395 144
-396 468
-397 144
-399 144
-4 20
-400 20
-401 2100
-402 20
-403 468
-404 144
-406 1088
-407 20
-409 468
-41 20
-411 20
-413 144
-414 144
-417 468
-418 20
-419 20
-42 144
-421 20
-424 144
-427 20
-429 144
-43 20
-430 468
-431 468
-432 20
-435 20
-436 20
-437 20
-438 468
-439 144
-44 20
-443 20
-444 20
-446 20
-448 20
-449 20
-452 20
-453 20
-454 468
-455 20
-457 20
-458 144
-459 144
-460 20
-462 144
-463 144
-466 468
-467 20
-468 1088
-469 2100
-47 20
-470 20
-472 20
-475 20
-477 20
-478 144
-479 20
-480 468
-481 20
-482 20
-483 20
-484 20
-485 20
-487 20
-489 1088
-490 20
-491 20
-492 144
-493 20
-494 20
-495 20
-496 20
-497 20
-498 468
-5 468
-51 144
-53 20
-54 20
-57 20
-58 144
-64 20
-65 20
-66 20
-67 144
-69 20
-70 468
-72 144
-74 20
-76 144
-77 20
-78 20
-8 20
-80 20
-82 20
-83 144
-84 144
-85 20
-86 20
-87 20
-9 20
-90 468
-92 20
-95 144
-96 20
-97 144
-98 144
http://git-wip-us.apache.org/repos/asf/hive/blob/bfdc74ff/ql/src/test/results/clientpositive/tez/tez_join_hash.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/tez_join_hash.q.out b/ql/src/test/results/clientpositive/tez/tez_join_hash.q.out
index 02678fd..347c48c 100644
--- a/ql/src/test/results/clientpositive/tez/tez_join_hash.q.out
+++ b/ql/src/test/results/clientpositive/tez/tez_join_hash.q.out
@@ -126,13 +126,13 @@ POSTHOOK: Input: default@src
#### A masked pattern was here ####
1028
PREHOOK: query: explain
-select count(*) from (select x.key as key, y.value as value from
+select key, count(*) from (select x.key as key, y.value as value from
srcpart x join srcpart y on (x.key = y.key)
union all
select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
PREHOOK: type: QUERY
POSTHOOK: query: explain
-select count(*) from (select x.key as key, y.value as value from
+select key, count(*) from (select x.key as key, y.value as value from
srcpart x join srcpart y on (x.key = y.key)
union all
select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
@@ -155,55 +155,55 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
+ alias: x
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Map 6
Map Operator Tree:
TableScan
- alias: x
- Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE
+ alias: y
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Map 7
Map Operator Tree:
TableScan
alias: z
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: value is not null (type: boolean)
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 21512 Data size: 3829136 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4200 Data size: 78220 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string)
Map 8
Map Operator Tree:
@@ -230,17 +230,17 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 19512 Data size: 3473136 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 2200 Data size: 40972 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string)
+ expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 19512 Data size: 3473136 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2200 Data size: 40972 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 21512 Data size: 3829136 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4200 Data size: 78220 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string)
Reducer 4
Reduce Operator Tree:
@@ -251,18 +251,18 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 50261 Data size: 8946458 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4620 Data size: 86042 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 25130 Data size: 4674180 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4620 Data size: 86042 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 25130 Data size: 4674180 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 4620 Data size: 86042 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Reducer 5
Execution mode: vectorized
@@ -272,14 +272,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 25130 Data size: 4674180 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2310 Data size: 43021 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 25130 Data size: 201040 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2310 Data size: 43021 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 25130 Data size: 201040 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2310 Data size: 43021 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -626,336 +626,3 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
96 20
97 144
98 144
-PREHOOK: query: select key, count(*) from (select x.key as key, y.value as value from
-srcpart x join srcpart y on (x.key = y.key)
-union all
-select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select key, count(*) from (select x.key as key, y.value as value from
-srcpart x join srcpart y on (x.key = y.key)
-union all
-select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-0 468
-10 20
-100 144
-103 144
-104 144
-105 20
-11 20
-111 20
-113 144
-114 20
-116 20
-118 144
-119 468
-12 144
-120 144
-125 144
-126 20
-128 468
-129 144
-131 20
-133 20
-134 144
-136 20
-137 144
-138 1088
-143 20
-145 20
-146 144
-149 144
-15 144
-150 20
-152 144
-153 20
-155 20
-156 20
-157 20
-158 20
-160 20
-162 20
-163 20
-164 144
-165 144
-166 20
-167 468
-168 20
-169 1088
-17 20
-170 20
-172 144
-174 144
-175 144
-176 144
-177 20
-178 20
-179 144
-18 144
-180 20
-181 20
-183 20
-186 20
-187 468
-189 20
-19 20
-190 20
-191 144
-192 20
-193 468
-194 20
-195 144
-196 20
-197 144
-199 468
-2 20
-20 20
-200 144
-201 20
-202 20
-203 144
-205 144
-207 144
-208 468
-209 144
-213 144
-214 20
-216 144
-217 144
-218 20
-219 144
-221 144
-222 20
-223 144
-224 144
-226 20
-228 20
-229 144
-230 2100
-233 144
-235 20
-237 144
-238 144
-239 144
-24 144
-241 20
-242 144
-244 20
-247 20
-248 20
-249 20
-252 20
-255 144
-256 144
-257 20
-258 20
-26 144
-260 20
-262 20
-263 20
-265 144
-266 20
-27 20
-272 144
-273 468
-274 20
-275 20
-277 1088
-278 144
-28 20
-280 144
-281 144
-282 144
-283 20
-284 20
-285 20
-286 20
-287 20
-288 144
-289 20
-291 20
-292 20
-296 20
-298 468
-30 20
-302 20
-305 20
-306 20
-307 144
-308 20
-309 144
-310 20
-311 468
-315 20
-316 468
-317 144
-318 468
-321 144
-322 144
-323 20
-325 144
-327 468
-33 20
-331 144
-332 20
-333 144
-335 20
-336 20
-338 20
-339 20
-34 20
-341 20
-342 144
-344 144
-345 20
-348 2100
-35 468
-351 20
-353 144
-356 20
-360 20
-362 20
-364 20
-365 20
-366 20
-367 144
-368 20
-369 468
-37 144
-373 20
-374 20
-375 20
-377 20
-378 20
-379 20
-382 144
-384 468
-386 20
-389 20
-392 20
-393 20
-394 20
-395 144
-396 468
-397 144
-399 144
-4 20
-400 20
-401 2100
-402 20
-403 468
-404 144
-406 1088
-407 20
-409 468
-41 20
-411 20
-413 144
-414 144
-417 468
-418 20
-419 20
-42 144
-421 20
-424 144
-427 20
-429 144
-43 20
-430 468
-431 468
-432 20
-435 20
-436 20
-437 20
-438 468
-439 144
-44 20
-443 20
-444 20
-446 20
-448 20
-449 20
-452 20
-453 20
-454 468
-455 20
-457 20
-458 144
-459 144
-460 20
-462 144
-463 144
-466 468
-467 20
-468 1088
-469 2100
-47 20
-470 20
-472 20
-475 20
-477 20
-478 144
-479 20
-480 468
-481 20
-482 20
-483 20
-484 20
-485 20
-487 20
-489 1088
-490 20
-491 20
-492 144
-493 20
-494 20
-495 20
-496 20
-497 20
-498 468
-5 468
-51 144
-53 20
-54 20
-57 20
-58 144
-64 20
-65 20
-66 20
-67 144
-69 20
-70 468
-72 144
-74 20
-76 144
-77 20
-78 20
-8 20
-80 20
-82 20
-83 144
-84 144
-85 20
-86 20
-87 20
-9 20
-90 468
-92 20
-95 144
-96 20
-97 144
-98 144
http://git-wip-us.apache.org/repos/asf/hive/blob/bfdc74ff/ql/src/test/results/clientpositive/tez_join_hash.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez_join_hash.q.out b/ql/src/test/results/clientpositive/tez_join_hash.q.out
new file mode 100644
index 0000000..6b366af
--- /dev/null
+++ b/ql/src/test/results/clientpositive/tez_join_hash.q.out
@@ -0,0 +1,920 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+create table orc_src (key string, value string) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@orc_src
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+create table orc_src (key string, value string) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@orc_src
+PREHOOK: query: insert into table orc_src select * from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@orc_src
+POSTHOOK: query: insert into table orc_src select * from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@orc_src
+POSTHOOK: Lineage: orc_src.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orc_src.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: explain
+SELECT count(*) FROM src, orc_src where src.key=orc_src.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT count(*) FROM src, orc_src where src.key=orc_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 PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ alias: orc_src
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT count(*) FROM src, orc_src where src.key=orc_src.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_src
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT count(*) FROM src, orc_src where src.key=orc_src.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_src
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+1028
+PREHOOK: query: explain
+select key, count(*) from (select x.key as key, y.value as value from
+srcpart x join srcpart y on (x.key = y.key)
+union all
+select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key, count(*) from (select x.key as key, y.value as value from
+srcpart x join srcpart y on (x.key = y.key)
+union all
+select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-12 is a root stage , consists of Stage-15, Stage-16, Stage-1
+ Stage-15 has a backup stage: Stage-1
+ Stage-10 depends on stages: Stage-15
+ Stage-9 depends on stages: Stage-1, Stage-10, Stage-11 , consists of Stage-13, Stage-14, Stage-2
+ Stage-13 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-13
+ Stage-3 depends on stages: Stage-2, Stage-7, Stage-8
+ Stage-14 has a backup stage: Stage-2
+ Stage-8 depends on stages: Stage-14
+ Stage-2
+ Stage-16 has a backup stage: Stage-1
+ Stage-11 depends on stages: Stage-16
+ Stage-1
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-12
+ Conditional Operator
+
+ Stage: Stage-15
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_1:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_1:x
+ TableScan
+ alias: x
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-10
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-9
+ Conditional Operator
+
+ Stage: Stage-13
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_1:b
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-7
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Union
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TableScan
+ alias: z
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Union
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2310 Data size: 24541 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2310 Data size: 24541 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2310 Data size: 24541 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-14
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_0-subquery2:$hdt$_0-subquery2:z
+ Fetch Operator
+ limit: -1
+#### A masked pattern was here ####
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_0-subquery2:$hdt$_0-subquery2:z
+ TableScan
+ alias: z
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Union
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Union
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ TableScan
+ alias: z
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Union
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 4200 Data size: 44620 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 4620 Data size: 49082 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-16
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:y
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:y
+ TableScan
+ alias: y
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-11
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ alias: x
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key, count(*) from (select x.key as key, y.value as value from
+srcpart x join srcpart y on (x.key = y.key)
+union all
+select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select key, count(*) from (select x.key as key, y.value as value from
+srcpart x join srcpart y on (x.key = y.key)
+union all
+select key, value from srcpart z) a join src b on (a.value = b.value) group by a.key, a.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+#### A masked pattern was here ####
+0 468
+10 20
+100 144
+103 144
+104 144
+105 20
+11 20
+111 20
+113 144
+114 20
+116 20
+118 144
+119 468
+12 144
+120 144
+125 144
+126 20
+128 468
+129 144
+131 20
+133 20
+134 144
+136 20
+137 144
+138 1088
+143 20
+145 20
+146 144
+149 144
+15 144
+150 20
+152 144
+153 20
+155 20
+156 20
+157 20
+158 20
+160 20
+162 20
+163 20
+164 144
+165 144
+166 20
+167 468
+168 20
+169 1088
+17 20
+170 20
+172 144
+174 144
+175 144
+176 144
+177 20
+178 20
+179 144
+18 144
+180 20
+181 20
+183 20
+186 20
+187 468
+189 20
+19 20
+190 20
+191 144
+192 20
+193 468
+194 20
+195 144
+196 20
+197 144
+199 468
+2 20
+20 20
+200 144
+201 20
+202 20
+203 144
+205 144
+207 144
+208 468
+209 144
+213 144
+214 20
+216 144
+217 144
+218 20
+219 144
+221 144
+222 20
+223 144
+224 144
+226 20
+228 20
+229 144
+230 2100
+233 144
+235 20
+237 144
+238 144
+239 144
+24 144
+241 20
+242 144
+244 20
+247 20
+248 20
+249 20
+252 20
+255 144
+256 144
+257 20
+258 20
+26 144
+260 20
+262 20
+263 20
+265 144
+266 20
+27 20
+272 144
+273 468
+274 20
+275 20
+277 1088
+278 144
+28 20
+280 144
+281 144
+282 144
+283 20
+284 20
+285 20
+286 20
+287 20
+288 144
+289 20
+291 20
+292 20
+296 20
+298 468
+30 20
+302 20
+305 20
+306 20
+307 144
+308 20
+309 144
+310 20
+311 468
+315 20
+316 468
+317 144
+318 468
+321 144
+322 144
+323 20
+325 144
+327 468
+33 20
+331 144
+332 20
+333 144
+335 20
+336 20
+338 20
+339 20
+34 20
+341 20
+342 144
+344 144
+345 20
+348 2100
+35 468
+351 20
+353 144
+356 20
+360 20
+362 20
+364 20
+365 20
+366 20
+367 144
+368 20
+369 468
+37 144
+373 20
+374 20
+375 20
+377 20
+378 20
+379 20
+382 144
+384 468
+386 20
+389 20
+392 20
+393 20
+394 20
+395 144
+396 468
+397 144
+399 144
+4 20
+400 20
+401 2100
+402 20
+403 468
+404 144
+406 1088
+407 20
+409 468
+41 20
+411 20
+413 144
+414 144
+417 468
+418 20
+419 20
+42 144
+421 20
+424 144
+427 20
+429 144
+43 20
+430 468
+431 468
+432 20
+435 20
+436 20
+437 20
+438 468
+439 144
+44 20
+443 20
+444 20
+446 20
+448 20
+449 20
+452 20
+453 20
+454 468
+455 20
+457 20
+458 144
+459 144
+460 20
+462 144
+463 144
+466 468
+467 20
+468 1088
+469 2100
+47 20
+470 20
+472 20
+475 20
+477 20
+478 144
+479 20
+480 468
+481 20
+482 20
+483 20
+484 20
+485 20
+487 20
+489 1088
+490 20
+491 20
+492 144
+493 20
+494 20
+495 20
+496 20
+497 20
+498 468
+5 468
+51 144
+53 20
+54 20
+57 20
+58 144
+64 20
+65 20
+66 20
+67 144
+69 20
+70 468
+72 144
+74 20
+76 144
+77 20
+78 20
+8 20
+80 20
+82 20
+83 144
+84 144
+85 20
+86 20
+87 20
+9 20
+90 468
+92 20
+95 144
+96 20
+97 144
+98 144