Uh oh!
There was an error while loading. Please reload this page.
SBLK_MASK_LOCK_THREADID allow tid up to 65535 (#88772) - #89335
Merged
jeffschwMSFT merged 1 commit intoAug 10, 2023
Merged
Conversation
* SBLK_MASK_LOCK_THREADID allow tid up to 65535 * copy comment from NativeAOT ObjectHeader.cs --------- Co-authored-by: dickens <dickens.tam@pulsartradingcap.com>
carlossanlop
commented
Aug 2, 2023
Contributor
Friendly reminder: if you want this servicing fix to be included in the September 2023 Release, you'll have to merge this PR before August 14th. |
Maoni0
approved these changes
Aug 3, 2023
jeffschwMSFT
approved these changes
Aug 9, 2023
jeffschwMSFT
left a comment
Member
There was a problem hiding this comment.
approved. we will take for consideration in 7.0.x
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 freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
6 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Customer Impact - from @dickens-code
Our apps require low latency performance and we are trying hard to reduce memory allocation in order to minimise GC occurrences.
We noticed that one of our apps experiences a very long GC pause of 2 seconds, and with the help of @cshung, we discovered that our app is having very large sync block memory space (20 million sync blocks), which introduced a very long time of sync block scanning during GC events.
We found out that new sync blocks are introduced when thread ID > 1024 is taking object locks and we tried to release the limit of thread ID to 65535 and the sync block memory space size was obviously improved
With the custom-built
coreclr.dllwe observed that our app's GC pauses were brought down to around 100ms which makes more sense according to our business requirementsTesting
Test failures are known - on my machine, I don't have sufficient memory to pass the 20GB large pages test case, all other large page test cases are passing.
Risk
Low - the bits were not used for anything before this fix, and the change is merged to main for 2 weeks with no regression found.