[Fix](query cache) support partition-based instance parallelism#60974
Open
924060929 wants to merge 2 commits intoapache:masterfrom
Open
[Fix](query cache) support partition-based instance parallelism#60974924060929 wants to merge 2 commits intoapache:masterfrom
924060929 wants to merge 2 commits intoapache:masterfrom
Conversation
When total tablets are much larger than pipeline capacity, one-tablet-per-instance planning creates excessive BE concurrency pressure in query-cache workloads. Trigger partition-based planning when: total_tablets > parallel_pipeline_task_num * participating_be_num Before: instance_num ~= total_tablets After: instance_num ~= partitions_on_each_be Per-BE planning example: BE1 tablets: p1[t1,t2], p2[t3] -> instances: [p1:t1,t2], [p2:t3] BE2 tablets: p1[t4], p2[t5,t6] -> instances: [p1:t4], [p2:t5,t6] This keeps tablets from the same partition in one instance and separates different partitions into different instances. If partition mapping is incomplete or partition planning fails, fallback to default planning for correctness. Tests: - partition-based planning path - fallback-to-default path (incomplete mapping) - non-query-cache default planning path
Contributor
|
Thank you for your contribution to Apache Doris. Please clearly describe your PR:
|
Contributor
Author
|
run buildall |
TPC-H: Total hot run time: 28643 ms |
TPC-DS: Total hot run time: 183195 ms |
Contributor
FE UT Coverage ReportIncrement line coverage |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What problem does this PR solve?
When total tablets are much larger than pipeline capacity, one-tablet-per-instance planning creates excessive BE concurrency pressure in query-cache workloads.
Trigger partition-based planning when:
total_tablets > parallel_pipeline_task_num * participating_be_num
Before:
instance_num ~= total_tablets
After:
instance_num ~= partitions_on_each_be
Per-BE planning example:
BE1 tablets: p1[t1,t2], p2[t3] -> instances: [p1:t1,t2], [p2:t3]
BE2 tablets: p1[t4], p2[t5,t6] -> instances: [p1:t4], [p2:t5,t6]
This keeps tablets from the same partition in one instance and separates
different partitions into different instances. If partition mapping is incomplete
or partition planning fails, fallback to default planning for correctness.
Tests:
Check List (For Author)
Test
Behavior changed:
Does this need documentation?
Check List (For Reviewer who merge this PR)