This repository has been archived by the owner on Sep 18, 2023. It is now read-only.
[NSE-588] config the pre-allocated memory for shuffle's splitter #594
Conversation
This file contains 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
added 2 commits
November 30, 2021 16:25
…the preallocated buffer size for each column each reducer. max of pre-allocated memory in split is 1/4 of offheap memory per task
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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 changes were proposed in this pull request?
Previously we preallocate memory during split operation for each column and each reducer. the size is controlled by record batch size. It doesn't scale if we use larger record batch, larger shuffle.partitions or more columns to shuffle.
we added a config to set the preallocated size and differ it from record batch size. In the code, we control the maximal memory allocated as 1/4 of total task offheap memory.
How was this patch tested?
tested on single node.