Skip to content

Optimize Statefulset Controller Performance: Reduce Work Duration Time & Minimize Cache Locking. #130806

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 1 commit into from
May 6, 2025
Merged

Optimize Statefulset Controller Performance: Reduce Work Duration Time & Minimize Cache Locking. #130806

merged 1 commit into from
May 6, 2025

Conversation

hakuna-matatah
Copy link
Contributor

@hakuna-matatah hakuna-matatah commented Mar 14, 2025 •
edited
Loading

What type of PR is this?

/kind cleanup

What this PR does / why we need it:

This PR introduces a StatefulSet indexer for the PodInformer to efficiently query Pods belonging to StatefulSets or Orphans from the InformerCache, avoiding a full namespace scan.

This improves performance and correctness at scale by minimizing the time a read lock is held on the cache, reducing blockage of CacheController delta processing. It also helps lower workqueue processing time per object/key.

  • The graph below illustrates that the 5-minute P99 average of work_queue_work_duration_seconds varies between approximately 1 second and 8 seconds, indicating the time required to process each item in the StatefulSet queue.
Screenshot 2025-03-08 at 4 26 38 PM
  • PProf analysis indicates that a significant portion of the sync loop cycles is spent in the getPodsForStatefulset phase, particularly in the ListAllByNamespace call. Another major contributor is the ClaimPods phase, which involves processing all those pods. Reducing the number of pods processed per cycle would not only alleviate lock contention on the cache (allowing the CacheController to write more efficiently) but also decrease work_queue_processing_time within the sync loop. This optimization would enhance the performance and throughput of the DaemonSet (DS) controller.
Screenshot 2025-03-09 at 10 46 20 PM (1)
  • The following graph illustrates the average p99 of work_queue_queue_duration in seconds. The 5-minute P99 average wait time for an item in the queue before processing is approximately 1 second.
Screenshot 2025-03-08 at 4 21 36 PM

Optimizing this list call will provide the following benefits:

  1. Reduce Read Lock Duration on the InformerCache, allowing writes to proceed faster and reducing chances of cache staleness at scale.
  2. Lower Work Queue Processing Time, enabling faster convergence to the desired state.
  3. Reduce Queue Wait Time, ensuring items are dispatched and processed more efficiently.

Which issue(s) this PR fixes:

Fixes #

#130767

Special notes for your reviewer:

Does this PR introduce a user-facing change?

Additional documentation e.g., KEPs (Kubernetes Enhancement Proposals), usage docs, etc.:

@k8s-ci-robot k8s-ci-robot added size/M Denotes a PR that changes 30-99 lines, ignoring generated files. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. do-not-merge/release-note-label-needed Indicates that a PR should not merge because it's missing one of the release note labels. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/needs-sig Indicates an issue or PR lacks a `sig/foo` label and requires one. needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one. needs-priority Indicates a PR lacks a `priority/foo` label and requires one. labels Mar 14, 2025
@k8s-ci-robot k8s-ci-robot added sig/apps Categorizes an issue or PR as relevant to SIG Apps. and removed do-not-merge/needs-sig Indicates an issue or PR lacks a `sig/foo` label and requires one. labels Mar 14, 2025
@github-project-automation github-project-automation bot moved this to Needs Triage in SIG Apps Mar 14, 2025
@hakuna-matatah hakuna-matatah changed the title Reduce locking duration on cache to fetch data from Cache in SatefulSet Controller Reduce locking duration on cache to fetch data in SatefulSet Controller Mar 14, 2025
dims
dims reviewed Mar 14, 2025
View reviewed changes
dims
dims reviewed Mar 14, 2025
View reviewed changes
dims
dims reviewed Mar 14, 2025
View reviewed changes
mengqiy
mengqiy reviewed Mar 14, 2025
View reviewed changes
@mengqiy
Copy link
Member

mengqiy commented Mar 14, 2025

/retest

@mengqiy mengqiy mentioned this pull request Mar 14, 2025
Open
@dims
Copy link
Member

dims commented Mar 14, 2025

@hakuna-matatah please add some context for the graphs in the PR body as well

@hakuna-matatah
Copy link
Contributor Author

hakuna-matatah commented Mar 14, 2025 •
edited
Loading

@hakuna-matatah please add some context for the graphs in the PR body as well

Done @dims.

The graph above shows that the 5-minute P99 average of work_queue_work_duration_seconds ranges from ~1s to 8s, representing the time taken to process each item in the StatefulSet queue. Additionally, the 5-minute P99 average wait time for an item in the queue before processing is ~1s. From the pprof analysis, most cycles are spent on listing pods.

Optimizing this list call will provide the following benefits:

  1. Reduce Read Lock Duration on the InformerCache, allowing writes to proceed faster and reducing chances of cache staleness at scale.
  2. Lower Work Queue Processing Time, enabling faster convergence to the desired state.
  3. Reduce Queue Wait Time, ensuring items are dispatched and processed more efficiently.

@mengqiy
Copy link
Member

mengqiy commented Mar 14, 2025 •
edited
Loading

please add some context for the graphs in the PR body as well

+1
Normally I'd suggest adding a short description above or below each graph.

@dims
Copy link
Member

dims commented Mar 14, 2025

/assign @soltysh @atiratree

@dims
Copy link
Member

dims commented Mar 14, 2025

/release-note-none
/priority important-soon

@k8s-ci-robot k8s-ci-robot added the release-note-none Denotes a PR that doesn't merit a release note. label Mar 14, 2025
@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

16 similar comments
@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-triage-robot
Copy link

The Kubernetes project has merge-blocking tests that are currently too flaky to consistently pass.

This bot retests PRs for certain kubernetes repos according to the following rules:

  • The PR does have any do-not-merge/* labels
  • The PR does not have the needs-ok-to-test label
  • The PR is mergeable (does not have a needs-rebase label)
  • The PR is approved (has cncf-cla: yes, lgtm, approved labels)
  • The PR is failing tests required for merge

You can:

/retest

@k8s-ci-robot
Copy link
Contributor

@hakuna-matatah: The following test failed, say /retest to rerun all failed tests or /retest-required to rerun all mandatory failed tests:

Test name Commit Details Required Rerun command
pull-kubernetes-linter-hints c005b85 link false /test pull-kubernetes-linter-hints

Full PR test history. Your PR dashboard. Please help us cut down on flakes by linking to an open issue when you hit one in your PR.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here.

@wojtek-t
Copy link
Member

/lgtm cancel

[Just to avoid constant resting of linter hints]

@k8s-ci-robot k8s-ci-robot removed the lgtm "Looks good to me", indicates that a PR is ready to be merged. label Mar 24, 2025
@atiratree atiratree mentioned this pull request May 2, 2025
Closed
@dims
Copy link
Member

dims commented May 4, 2025

@hakuna-matatah you have a approve/lgtm from @wojtek-t #130806 (comment)

However there is a linter CI job that is failing, can you please fix it? then i can re-apply lgtm?

@wojtek-t
Copy link
Member

wojtek-t commented May 6, 2025

/lgtm

@k8s-ci-robot k8s-ci-robot added the lgtm "Looks good to me", indicates that a PR is ready to be merged. label May 6, 2025
@k8s-ci-robot
Copy link
Contributor

LGTM label has been added.

Git tree hash: 963844811a9687d111f4bba3de5e133d598d99bd

@k8s-ci-robot k8s-ci-robot merged commit d2507bb into kubernetes:master May 6, 2025
5 of 14 checks passed
@k8s-ci-robot k8s-ci-robot added this to the v1.34 milestone May 6, 2025
@github-project-automation github-project-automation bot moved this from Needs Triage to Done in SIG Apps May 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dims dims dims left review comments

@mengqiy mengqiy mengqiy left review comments

@atiratree atiratree Awaiting requested review from atiratree

@mimowo mimowo Awaiting requested review from mimowo

@soltysh soltysh Awaiting requested review from soltysh

@wojtek-t wojtek-t Awaiting requested review from wojtek-t

Assignees

@soltysh soltysh

@atiratree atiratree

@wojtek-t wojtek-t

Labels
approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. lgtm "Looks good to me", indicates that a PR is ready to be merged. priority/important-soon Must be staffed and worked on either currently, or very soon, ideally in time for the next release. release-note-none Denotes a PR that doesn't merit a release note. sig/apps Categorizes an issue or PR as relevant to SIG Apps. size/M Denotes a PR that changes 30-99 lines, ignoring generated files. triage/accepted Indicates an issue or PR is ready to be actively worked on.
Projects
SIG Apps
Archived in project
Milestone
v1.34
Development

Successfully merging this pull request may close these issues.
8 participants
@hakuna-matatah @mengqiy @dims @soltysh @wojtek-t @k8s-ci-robot @k8s-triage-robot @atiratree