[FLINK-30631][runtime] Limit the max number of subpartitons consumed by each downstream task #21646
Conversation
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
Collaborator
wanglijie95
force-pushed
the
FLINK-30631
branch
from
50715d0 to
4129ede
Compare
zhuzhurk
reviewed
Jan 13, 2023
Contributor
zhuzhurk
left a comment
zhuzhurk
left a comment
There was a problem hiding this comment.
Thanks for opening this PR. @wanglijie95
I only have one comment regarding the first commit.
...ache/flink/runtime/scheduler/adaptivebatch/DefaultVertexParallelismAndInputInfosDecider.java
Outdated
Show resolved
Hide resolved
Contributor
Author
|
@zhuzhurk Thanks for review, I 've addressed the comment, please take a look. |
…ism and input infos
…by each downstream task
wanglijie95
force-pushed
the
FLINK-30631
branch
from
8f0f55a to
81f6e2b
Compare
Contributor
Author
|
@flinkbot run azure |
chucheng92
pushed a commit
to chucheng92/flink
that referenced
this pull request
Feb 3, 2023
…by each downstream task This closes apache#21646
akkinenivijay
pushed a commit
to krisnaru/flink
that referenced
this pull request
Feb 11, 2023
…by each downstream task This closes apache#21646
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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 is the purpose of the change
In the current implementation(FLINK-25035), when the upstream vertex parallelism is much greater than the downstream vertex parallelism, it may lead to a large number of channels in the downstream tasks(for example, A -> B, all to all edge, max parallelism is 1000. If parallelism of A is 1000, parallelism of B is decided to be 1, then the only subtask of B will consume 1000 * 1000 subpartitions), resulting in a large overhead for processing channels.
In this ticket, we temporarily address this issue by limiting the max number of subpartitons consumed by each downstream task. The ultimate solution should be to support single channel consume multiple subpartitons.
Verifying this change
Unit tests:
DefaultVertexParallelismAndInputInfosDeciderTest#testEvenlyDistributeDataWithMaxSubpartitionLimitationDefaultVertexParallelismAndInputInfosDeciderTest#testDecideParallelismWithMaxSubpartitionLimitationDoes this pull request potentially affect one of the following parts:
@Public(Evolving): (no)Documentation