This is an automated email from the ASF dual-hosted git repository.

yiguolei pushed a commit to branch branch-2.1
in repository https://gitbox.apache.org/repos/asf/doris.git


The following commit(s) were added to refs/heads/branch-2.1 by this push:
     new b6e5281a1ca [Fix](bug) fix the divide zero in local shuffle: (#37948)
b6e5281a1ca is described below

commit b6e5281a1ca44e61adbcaf99632a19fcfb185e7f
Author: HappenLee <[email protected]>
AuthorDate: Wed Jul 17 01:03:53 2024 +0800

    [Fix](bug) fix the divide zero in local shuffle: (#37948)
    
    ## Proposed changes
    
    cherry pick #37906
    
    <!--Describe your changes.-->
---
 .../pipeline_x/pipeline_x_fragment_context.cpp     |  6 ++-
 .../data/query_p0/limit/sql/withGroupByUnion.out   | 52 ++++++++++++++++++++++
 .../suites/query_p0/limit/sql/withGroupByUnion.sql |  1 +
 3 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/be/src/pipeline/pipeline_x/pipeline_x_fragment_context.cpp 
b/be/src/pipeline/pipeline_x/pipeline_x_fragment_context.cpp
index bcb3c53b532..854bd1e7def 100644
--- a/be/src/pipeline/pipeline_x/pipeline_x_fragment_context.cpp
+++ b/be/src/pipeline/pipeline_x/pipeline_x_fragment_context.cpp
@@ -298,8 +298,12 @@ Status PipelineXFragmentContext::_plan_local_exchange(
             }
         }
 
+        // if 'num_buckets == 0' means the fragment is colocated by exchange 
node not the
+        // scan node. so here use `_num_instance` to replace the `num_buckets` 
to prevent dividing 0
+        // still keep colocate plan after local shuffle
         RETURN_IF_ERROR(_plan_local_exchange(
-                
_pipelines[pip_idx]->operator_xs().front()->ignore_data_hash_distribution()
+                
_pipelines[pip_idx]->operator_xs().front()->ignore_data_hash_distribution() ||
+                                num_buckets == 0
                         ? _num_instances
                         : num_buckets,
                 pip_idx, _pipelines[pip_idx], bucket_seq_to_instance_idx,
diff --git a/regression-test/data/query_p0/limit/sql/withGroupByUnion.out 
b/regression-test/data/query_p0/limit/sql/withGroupByUnion.out
new file mode 100644
index 00000000000..2d0e2af41c5
--- /dev/null
+++ b/regression-test/data/query_p0/limit/sql/withGroupByUnion.out
@@ -0,0 +1,52 @@
+-- This file is automatically generated. You should know what you did if you 
want to edit this
+-- !withGroupByUnion --
+0      ALGERIA
+1      ALGERIA
+1      ARGENTINA
+1      BRAZIL
+1      CANADA
+1      CHINA
+1      EGYPT
+1      ETHIOPIA
+1      FRANCE
+1      GERMANY
+1      INDIA
+1      INDONESIA
+1      IRAN
+1      IRAQ
+1      JAPAN
+1      JORDAN
+1      KENYA
+1      MOROCCO
+1      MOZAMBIQUE
+1      PERU
+1      ROMANIA
+1      RUSSIA
+1      SAUDI ARABIA
+1      UNITED KINGDOM
+1      UNITED STATES
+1      VIETNAM
+2      BRAZIL
+3      CANADA
+4      EGYPT
+5      ETHIOPIA
+6      FRANCE
+7      GERMANY
+8      INDIA
+9      INDONESIA
+10     IRAN
+11     IRAQ
+12     JAPAN
+13     JORDAN
+14     KENYA
+15     MOROCCO
+16     MOZAMBIQUE
+17     PERU
+18     CHINA
+19     ROMANIA
+20     SAUDI ARABIA
+21     VIETNAM
+22     RUSSIA
+23     UNITED KINGDOM
+24     UNITED STATES
+
diff --git a/regression-test/suites/query_p0/limit/sql/withGroupByUnion.sql 
b/regression-test/suites/query_p0/limit/sql/withGroupByUnion.sql
new file mode 100644
index 00000000000..b47b0d17ff2
--- /dev/null
+++ b/regression-test/suites/query_p0/limit/sql/withGroupByUnion.sql
@@ -0,0 +1 @@
+select * from (select count(a.nationkey), a.name from tpch_tiny_nation a  
join[shuffle] tpch_tiny_nation b on a.name = b.name group by a.name union 
select sum(c.nationkey), c.name from tpch_tiny_nation c  join[shuffle] 
tpch_tiny_nation d on c.name = d.name group by c.name) t order by 1,2 limit 50;


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to