thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-21 23:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #28105 from azat/enable-optimize_distributed_group_by_sharding_key

Browse Source 
Enable optimize_distributed_group_by_sharding_key by default
This commit is contained in:
Maksim Kita 2021-08-25 14:07:33 +03:00 committed by GitHub
commit df1fe27791
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 16 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/Core/Settings.h
View File

@ -125,7 +125,7 @@ class IColumn;
M(UInt64, parallel_distributed_insert_select, 0, "Process distributed INSERT SELECT query in the same cluster on local tables on every shard, if 1 SELECT is executed on each shard, if 2 SELECT and INSERT is executed on each shard", 0) \
M(UInt64, distributed_group_by_no_merge, 0, "If 1, Do not merge aggregation states from different servers for distributed queries (shards will process query up to the Complete stage, initiator just proxies the data from the shards). If 2 the initiator will apply ORDER BY and LIMIT stages (it is not in case when shard process query up to the Complete stage)", 0) \
M(UInt64, distributed_push_down_limit, 1, "If 1, LIMIT will be applied on each shard separatelly. Usually you don't need to use it, since this will be done automatically if it is possible, i.e. for simple query SELECT FROM LIMIT.", 0) \
M(Bool, optimize_distributed_group_by_sharding_key, false, "Optimize GROUP BY sharding_key queries (by avoiding costly aggregation on the initiator server).", 0) \
M(Bool, optimize_distributed_group_by_sharding_key, true, "Optimize GROUP BY sharding_key queries (by avoiding costly aggregation on the initiator server).", 0) \
M(UInt64, optimize_skip_unused_shards_limit, 1000, "Limit for number of sharding key values, turns off optimize_skip_unused_shards if the limit is reached", 0) \
M(Bool, optimize_skip_unused_shards, false, "Assumes that data is distributed by sharding_key. Optimization to skip unused shards if SELECT query filters by sharding_key.", 0) \
M(Bool, optimize_skip_unused_shards_rewrite_in, true, "Rewrite IN in query for remote shards to exclude values that does not belong to the shard (requires optimize_skip_unused_shards)", 0) \

7
tests/queries/0_stateless/01213_optimize_skip_unused_shards_DISTINCT.reference
View File

@ -3,6 +3,11 @@ distributed_group_by_no_merge
1
optimize_skip_unused_shards
1
optimize_skip_unused_shards lack of WHERE
optimize_skip_unused_shards lack of WHERE (optimize_distributed_group_by_sharding_key=0)
0
1
optimize_skip_unused_shards lack of WHERE (optimize_distributed_group_by_sharding_key=1)
0
1
0
1

11
tests/queries/0_stateless/01213_optimize_skip_unused_shards_DISTINCT.sql
View File

@ -12,8 +12,15 @@ SELECT DISTINCT id FROM dist_01213 WHERE id = 1 SETTINGS distributed_group_by_no
SELECT 'optimize_skip_unused_shards';
SELECT DISTINCT id FROM dist_01213 WHERE id = 1 SETTINGS optimize_skip_unused_shards=1;
-- check that querying all shards is ok
SELECT 'optimize_skip_unused_shards lack of WHERE';
SELECT DISTINCT id FROM dist_01213 SETTINGS optimize_skip_unused_shards=1;
SELECT 'optimize_skip_unused_shards lack of WHERE (optimize_distributed_group_by_sharding_key=0)';
SELECT DISTINCT id FROM dist_01213 SETTINGS optimize_skip_unused_shards=1, optimize_distributed_group_by_sharding_key=0;
-- with optimize_distributed_group_by_sharding_key=1 there will be 4 rows,
-- since DISTINCT will be done on each shard separatelly, and initiator will
-- not do anything (since we use optimize_skip_unused_shards=1 that must
-- guarantee that the data had been INSERTed according to sharding key,
-- which is not our case, since we use one local table).
SELECT 'optimize_skip_unused_shards lack of WHERE (optimize_distributed_group_by_sharding_key=1)';
SELECT DISTINCT id FROM dist_01213 SETTINGS optimize_skip_unused_shards=1, optimize_distributed_group_by_sharding_key=1;
DROP TABLE local_01213;
DROP TABLE dist_01213;