8371702: ZGC: NUMA-Affinity for Worker Threads in the Relocation Phase

[jsikstro]

Hello,

The main goal of this PR is to solve a performance regression in relatively small environments on a NUMA machine. See the associated issue for a more detailed explanation on regression itself.

I propose we add functionality to set the affinity of worker threads in the Relocation Phase of ZGC so that the worker threads are always accessing NUMA-local memory when relocating objects. As soon as a worker threads is about to start relocating a new forwarding entry (or just page), it makes sure that it has the appropriate affinity set. At the most, each worker thread will set its own affinity the same number of times as there are NUMA nodes on the system. When the threads are about to exit the Relocation Phase (i.e. by completing ZRelocateTask), they "strip" their affinity so that they are allowed to run on any CPU that they were originally allowed to run on.

I've done significant performance testing, which solves the observed regression and gives an additional performance boost in the same environments. I have not been able to observe similar boosts in performance on much larger environments (>=70 CPUs and >32GB memory) and also no regressions.

---

Progress

• Change must be properly reviewed (1 review required, with at least 1 Reviewer)
• Change must not contain extraneous whitespace
• Commit message must refer to an issue

Issue

• JDK-8371702: ZGC: NUMA-Affinity for Worker Threads in the Relocation Phase (Bug - P4)

Reviewers

• Axel Boldt-Christmas (@xmas92 - Reviewer)
• Erik Österlund (@fisk - Reviewer)

Contributors

• Axel Boldt-Christmas <aboldtch@openjdk.org>

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.org/jdk.git pull/28262/head:pull/28262
$ git checkout pull/28262

Update a local copy of the PR:
$ git checkout pull/28262
$ git pull https://git.openjdk.org/jdk.git pull/28262/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 28262

View PR using the GUI difftool:
$ git pr show -t 28262

Using diff file

Download this PR as a diff file:
https://git.openjdk.org/jdk/pull/28262.diff

Using Webrev

Link to Webrev Comment

[bridgekeeper]

👋 Welcome back jsikstro! A progress list of the required criteria for merging this PR into pr/28261 will be added to the body of your pull request. There are additional pull request commands available for use with this pull request.

[openjdk]

@jsikstro This change now passes all automated pre-integration checks.

ℹ️ This project also has non-automated pre-integration requirements. Please see the file CONTRIBUTING.md for details.

After integration, the commit message for the final commit will be:

8371702: ZGC: NUMA-Affinity for Worker Threads in the Relocation Phase

Co-authored-by: Axel Boldt-Christmas <aboldtch@openjdk.org>
Reviewed-by: aboldtch, eosterlund

You can use pull request commands such as /summary, /contributor and /issue to adjust it as needed.

At the time when this comment was updated there had been 54 new commits pushed to the master branch:

• 848c0c7: 8372285: G1: Micro-optimize x86 barrier code
• 55362e1: 8372385: tools/jpackage/junit/share/jdk.jpackage/jdk/jpackage/internal/cli/MainTest.java fails
• b054a56: 8351095: [macos] Add more jpackage tests for --mac-app-store option
• ... and 51 more: https://git.openjdk.org/jdk/compare/aec54726df7efdea6f85ccd26763acb7ee839e2f...master

As there are no conflicts, your changes will automatically be rebased on top of these commits when integrating. If you prefer to avoid this automatic rebasing, please check the documentation for the /integrate command for further details.

➡️ To integrate this PR with the above commit message to the master branch, type /integrate in a new comment.

[openjdk]

@jsikstro The following label will be automatically applied to this pull request:

• hotspot-gc

When this pull request is ready to be reviewed, an "RFR" email will be sent to the corresponding mailing list. If you would like to change these labels, use the /label pull request command.

[mlbridge]

Webrevs

• 07: Full - Incremental (86e9bfc3)
• 06: Full - Incremental (e8b13127)
• 05: Full - Incremental (7ef2ced6)
• 04: Full (ccb16084)
• 03: Full - Incremental (f8cd6aac)
• 02: Full - Incremental (8c0083c9)
• 01: Full - Incremental (fea63eca)
• 00: Full (2aabc2fb)

[jsikstro]

/contributor add @xmas92

[openjdk]

@jsikstro
Contributor Axel Boldt-Christmas <aboldtch@openjdk.org> successfully added.

[openjdk-notifier]

The parent pull request that this pull request depends on has now been integrated and the target branch of this pull request has been updated. This means that changes from the dependent pull request can start to show up as belonging to this pull request, which may be confusing for reviewers. To remedy this situation, simply merge the latest changes from the new target branch into this pull request by running commands similar to these in the local repository for your personal fork:

git checkout JDK-8371702_zgc_narc_regression_fix
git fetch https://git.openjdk.org/jdk.git master
git merge FETCH_HEAD
# if there are conflicts, follow the instructions given by git merge
git commit -m "Merge master"
git push

[openjdk]

@jsikstro this pull request can not be integrated into master due to one or more merge conflicts. To resolve these merge conflicts and update this pull request you can run the following commands in the local repository for your personal fork:

git checkout JDK-8371702_zgc_narc_regression_fix
git fetch https://git.openjdk.org/jdk.git master
git merge FETCH_HEAD
# resolve conflicts and follow the instructions given by git merge
git commit -m "Merge master"
git push

[openjdk]

⚠️ @jsikstro This pull request contains merges that bring in commits not present in the target repository. Since this is not a "merge style" pull request, these changes will be squashed when this pull request in integrated. If this is your intention, then please ignore this message. If you want to preserve the commit structure, you must change the title of this pull request to Merge <project>:<branch> where <project> is the name of another project in the OpenJDK organization (for example Merge jdk:master).

[jsikstro]

After some more performance testing, I have decided to revert back to my original patch since we don't get as reliably good result with the changes that Axel proposed. I think Axel's changes are good, but there's something that is not obvious that is affecting performance negatively inside the loop that takes care of forwardings.

To get this in JDK26 without more struggle I think we should take this as is and follow-up in a future enhancement to make the code in this are nicer.

[xmas92]

Looks good. Just a style comment.

[fisk]

Looks good.

[jsikstro]

Thank you for the reviews! @xmas92 @fisk
/integrate

[openjdk]

Going to push as commit de546d0.
Since your change was applied there have been 55 commits pushed to the master branch:

• 7cd3d7f: 8372376: ZGC: Inaccurate verification of raw nulls in flip promoting pages
• 848c0c7: 8372285: G1: Micro-optimize x86 barrier code
• 55362e1: 8372385: tools/jpackage/junit/share/jdk.jpackage/jdk/jpackage/internal/cli/MainTest.java fails
• ... and 52 more: https://git.openjdk.org/jdk/compare/aec54726df7efdea6f85ccd26763acb7ee839e2f...master

Your commit was automatically rebased without conflicts.

[openjdk]

@jsikstro Pushed as commit de546d0.

💡 You may see a message that your pull request was closed with unmerged commits. This can be safely ignored.