[SPARK-51947] Spark connect model cache offloading #50752
+228
−57
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
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
WeichenXu123
changed the title
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
Signed-off-by: Weichen Xu <[email protected]>
xi-db
reviewed
May 2, 2025
| .build[String, CacheItem]() | ||
| .asMap() | ||
| } else { | ||
| new ConcurrentHashMap[String, CacheItem]() |
There was a problem hiding this comment.
Do you think it is risky that mlcache has no memory limit when offloading is disabled? Probably it makes sense to keep the old behaviour in this case: mlcache also has memory limit and retention time when offloading is disabled, but once a model is evicted, future access to it will throw an error CACHE_INVALID. WDYT?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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?
Support offloading model cache to spark driver local disk
Why are the changes needed?
Motivation: this feature helps to reduce spark driver memory pressure.
Does this PR introduce any user-facing change?
No.
How was this patch tested?
Manually.
Was this patch authored or co-authored using generative AI tooling?
No.