Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

release-23.1: pkg/kv/kvclient: update per-vCPU concurrency limits #131535

Closed

Conversation

blathers-crl[bot]
Copy link

@blathers-crl blathers-crl bot commented Sep 27, 2024

Backport 1/1 commits from #131226 on behalf of @sean-.

/cc @cockroachdb/release


Increase the current values (arbitrarily selected) by 6x (also an
arbitrary increase). Annecdotal evidence from customers suggests
this may unlock some workloads where vCPU utilization appears to
"plateau" around 70%, and now allows for ~100% vCPU utilization.
Until #131125 and #131126 are implemented, it is not possible to
directly monitor these incremental improvements to the defaults.

Epic: CRDB-42388
Epic: CRDB-42389

Release note (performance improvement): Increase the per-vCPU
concurrency limits for KV operations. Specifically, increase
kv.dist_sender.concurrency_limit to 384/vCPU (up from 64/vCPU)
and kv.streamer.concurrency_limit to 96/vCPU (up from 8/vCPU).


Release justification:

Increase the current values (arbitrarily selected) by 6x (also an
arbitrary increase).  Annecdotal evidence from customers suggests
this may unlock some workloads where vCPU utilization appears to
"plateau" around 70%, and now allows for ~100% vCPU utilization.
Until #131125 and #131126 are implemented, it is not possible to
directly monitor these incremental improvements to the defaults.

Epic: CRDB-42388
Epic: CRDB-42389

Release note (performance improvement): Increase the per-vCPU
concurrency limits for KV operations.  Specifically, increase
`kv.dist_sender.concurrency_limit` to 384/vCPU (up from 64/vCPU)
and `kv.streamer.concurrency_limit` to 96/vCPU (up from 8/vCPU).
@blathers-crl blathers-crl bot requested review from a team as code owners September 27, 2024 19:44
@blathers-crl blathers-crl bot force-pushed the blathers/backport-release-23.1-131226 branch from 0c5b325 to 01c016b Compare September 27, 2024 19:44
@blathers-crl blathers-crl bot removed the request for review from a team September 27, 2024 19:44
@blathers-crl blathers-crl bot added the blathers-backport This is a backport that Blathers created automatically. label Sep 27, 2024
@blathers-crl blathers-crl bot requested a review from mw5h September 27, 2024 19:44
@blathers-crl blathers-crl bot added the O-robot Originated from a bot. label Sep 27, 2024
Copy link
Author

blathers-crl bot commented Sep 27, 2024

Thanks for opening a backport.

Please check the backport criteria before merging:

  • Backports should only be created for serious
    issues
    or test-only changes.
  • Backports should not break backwards-compatibility.
  • Backports should change as little code as possible.
  • Backports should not change on-disk formats or node communication protocols.
  • Backports should not add new functionality (except as defined
    here).
  • Backports must not add, edit, or otherwise modify cluster versions; or add version gates.
  • All backports must be reviewed by the owning areas TL. For more information as to how that review should be conducted, please consult the backport
    policy
    .
If your backport adds new functionality, please ensure that the following additional criteria are satisfied:
  • There is a high priority need for the functionality that cannot wait until the next release and is difficult to address in another way.
  • The new functionality is additive-only and only runs for clusters which have specifically “opted in” to it (e.g. by a cluster setting).
  • New code is protected by a conditional check that is trivial to verify and ensures that it only runs for opt-in clusters. State changes must be further protected such that nodes running old binaries will not be negatively impacted by the new state (with a mixed version test added).
  • The PM and TL on the team that owns the changed code have signed off that the change obeys the above rules.
  • Your backport must be accompanied by a post to the appropriate Slack
    channel (#db-backports-point-releases or #db-backports-XX-X-release) for awareness and discussion.

Also, please add a brief release justification to the body of your PR to justify this
backport.

@blathers-crl blathers-crl bot added the backport Label PR's that are backports to older release branches label Sep 27, 2024
Copy link
Author

blathers-crl bot commented Sep 27, 2024

It looks like your PR touches production code but doesn't add or edit any test code. Did you consider adding tests to your PR?

🦉 Hoot! I am a Blathers, a bot for CockroachDB. My owner is dev-inf.

@cockroach-teamcity
Copy link
Member

This change is Reviewable

@nvanbenschoten
Copy link
Member

@sean- we're not going to be able to backport this change, as it does not meet the backport policy: https://cockroachlabs.atlassian.net/wiki/spaces/ENG/pages/1043235321/Database+Backport+Patch+Policy. We typically only land tuning changes like this in major releases, so that users don't see unexpected step changes during patch release upgrades. cc. @michae2

Copy link
Collaborator

@sean- sean- left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Serious issues are defined as high-priority or high-severity bugs in existing functionality, or as critical gaps in an operators' ability to detect and troubleshoot serious issues in their clusters. Serious issues either have high business priority or have severe impact if they were encountered by customers. This includes correctness, stability, or security issues, data corruption/loss, significant performance regressions, breaking working and widely used functionality, and an inability to detect and debug production issues.

I read that and thought this would've met the threshold under "high business priority," "have sever impact," or "significant performance regression."

Reviewable status: :shipit: complete! 0 of 0 LGTMs obtained (waiting on @michae2, @mw5h, and @nvanbenschoten)

@michae2
Copy link
Collaborator

michae2 commented Sep 27, 2024

I agree that we shouldn't backport this. It's a good change, but there's some risk to it, too (which is that it could possibly reduce performance for some other kind of workload, or could possibly cause an OOM if someone is running with an incorrect GOMEMLIMIT).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backport Label PR's that are backports to older release branches blathers-backport This is a backport that Blathers created automatically. O-robot Originated from a bot.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants