924060929 commented on code in PR #67177:
URL: https://github.com/apache/doris/pull/67177#discussion_r3870549845
##########
regression-test/suites/nereids_p0/local_shuffle/test_local_shuffle_rqg_bugs.groovy:
##########
@@ -1663,5 +1663,86 @@ suite("test_local_shuffle_rqg_bugs") {
assertTrue(false, "Bug 26: ${t.message}")
}
+ // RQG builds 208624/208625/208649: a non-serial BUCKET_SHUFFLE Exchange
+ // addressed all pooled instances, but the scalar DISTINCT root reduced the
+ // receiver pipeline to one task per BE. Rows routed to the other logical
+ // instances had no receiver and were silently lost. Keep the original
+ // 10-bucket data and predicates so 4 BEs * 3 tasks form this mismatch.
+ try {
+ logger.info("Bug 27: scalar DISTINCT over serial BUCKET_SHUFFLE outer
joins")
+ ["bug27_t5", "bug27_t52", "bug27_t53"].each { table ->
+ sql "DROP TABLE IF EXISTS ${table}"
+ }
+ sql """CREATE TABLE bug27_t5 (
+ col_bigint BIGINT, col_v10 VARCHAR(10), col_v64
VARCHAR(64), pk INT
+ ) ENGINE=OLAP DISTRIBUTED BY HASH(pk) BUCKETS 10
+ PROPERTIES ("replication_num"="1")"""
+ sql """CREATE TABLE bug27_t52 (
+ pk INT, col_bigint BIGINT, col_v10 VARCHAR(10), col_v64
VARCHAR(64)
+ ) ENGINE=OLAP DUPLICATE KEY(pk, col_bigint, col_v10)
+ DISTRIBUTED BY HASH(pk) BUCKETS 10 PROPERTIES
("replication_num"="1")"""
+ sql """CREATE TABLE bug27_t53 (
+ pk INT, col_v10 VARCHAR(10), col_bigint BIGINT, col_v64
VARCHAR(64)
+ ) ENGINE=OLAP DUPLICATE KEY(pk, col_v10)
+ DISTRIBUTED BY HASH(pk) BUCKETS 10 PROPERTIES
("replication_num"="1")"""
+ sql """INSERT INTO bug27_t5 VALUES
+
(-94,'had','y',0),(672609,'k','h',1),(-3766684,'a','p',2),(5070261,'on','x',3),
+
(NULL,'u','at',4),(-86,'v','c',5),(21910,'how','m',6),(-63,'that''s','go',7),
+ (-8276281,'s','a',8),(-101,'w','y',9)"""
+ sql """INSERT INTO bug27_t52 VALUES
+
(0,NULL,'g','i'),(1,-6138328,'z','do'),(2,-23217,'g','about'),(3,104,'you''re','z'),
+
(4,NULL,'oh','i'),(5,-54,'want','to'),(6,NULL,'x','c'),(7,NULL,'you''re','come'),
+ (8,3447,'really','from'),(9,-5459,'i','will')"""
+ sql """INSERT INTO bug27_t53 VALUES
+
(0,'right',NULL,'g'),(1,'on',-486256,'on'),(2,'I''ll',-1,'at'),(3,'h',29263,'don''t'),
+
(4,'a',5453,'s'),(5,'j',-119,'can''t'),(6,'one',89,'n'),(7,'s',-7227,'u'),
+ (8,'time',94,'b'),(9,'yes',1816630,'yes')"""
+
+ def vars =
"enable_local_shuffle_planner=true,enable_local_shuffle=true," +
+
"enable_bucket_shuffle_join=true,ignore_storage_data_distribution=true," +
+
"bucket_shuffle_downgrade_ratio=0.8,use_serial_exchange=false," +
+ "parallel_pipeline_task_num=3,enable_sql_cache=false"
+ def result1 = sql """SELECT /*+SET_VAR(${vars})*/ COUNT(DISTINCT t1.pk)
Review Comment:
Addressed in the final test layout. The earlier assertion-based block was
removed. The current diff adds the generic
`test_serial_aggregation_over_parallel_join` suite with `order_qt_*` queries
and a generated `.out` golden file, following the regression-test convention.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
