[kv] Introduce a shared memory cache for PrewriteBuffer between different replica #1951
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
swuferhong
force-pushed
the
pre-writebuffer-cache
branch
from
0f6f035 to
7e693a9
Compare
| import static org.apache.fluss.utils.concurrent.LockUtils.inLock; | ||
|
|
||
| /** a shared off-heap memory pool for {@link KvPreWriteBuffer} of different tableBucket. */ | ||
| public class KvPreWriteBufferMemoryPool { |
Contributor
There was a problem hiding this comment.
I'm curious about why not to reuse the LazyMemorySegmentPool?
Contributor
Author
There was a problem hiding this comment.
LazyMemorySegmentPool uses a large memory chunks (page size), for example, the default value of 128 KB. Personally, I don't think it's necessary to set it this large, because a single value of kv record here isn't as big as a recordBatch.
swuferhong
force-pushed
the
pre-writebuffer-cache
branch
from
7e693a9 to
e4e96b1
Compare
swuferhong
force-pushed
the
pre-writebuffer-cache
branch
2 times, most recently
from
4d5d7c6 to
7560223
Compare
swuferhong
force-pushed
the
pre-writebuffer-cache
branch
from
7560223 to
4475391
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Purpose
Linked issue: close #1950
When testing the stability of
PrimaryKeytables, a frequent issue arises where exceptionally high write traffic peaks cause delayed log synchronization. This leads to continuous accumulation in the KV'sPrewriteBuffer. Since the currentPrewriteBufferlacks a back-pressure mechanism, has no memory cap, and utilizes JVM heap memory, it can easily trigger OOM errors, resulting in TabletServer crashes.In this pr, we will introduce an off-heap shared memory cache to share memory between different
Replica.Brief change log
Tests
API and Format
Documentation