perf: Cache requirements for pods alongside requests #1950
+46
−38
Conversation
This file contains 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
k8s-ci-robot
added
the
cncf-cla: yes
k8s-ci-robot
added
approved
jonathan-innis
force-pushed
the
cache-pod-requirements
branch
from
e31f059 to
3645b79
Compare
Pull Request Test Coverage Report for Build 13143439974Details
💛 - Coveralls |
rschalo
reviewed
Feb 4, 2025
| @@ -265,10 +273,24 @@ func (s *Scheduler) Solve(ctx context.Context, pods []*corev1.Pod) Results { | |||
| } | |||
| } | |||
|
|
|||
| func (s *Scheduler) updateCachedPodData(p *corev1.Pod) { | |||
| podData := PodData{ | |||
There was a problem hiding this comment.
Want to make the requirements before the struct and then assign to both struct members when making podData?
There was a problem hiding this comment.
Do you think that makes it easier to parse? I'm not really seeing a ton of value though -- though, I'm not 100% what you mean
|
/lgtm |
k8s-ci-robot
added
lgtm
jonathan-innis
force-pushed
the
cache-pod-requirements
branch
from
3645b79 to
d39172c
Compare
k8s-ci-robot
removed
the
lgtm
jonathan-innis
force-pushed
the
cache-pod-requirements
branch
from
d39172c to
d3e51f5
Compare
jonathan-innis
force-pushed
the
cache-pod-requirements
branch
from
d3e51f5 to
3ad4e57
Compare
k8s-ci-robot
removed
the
needs-rebase
k8s-ci-robot
added
the
lgtm
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: jonathan-innis, rschalo The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
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.
Fixes #N/A
Description
Cache requirements for pods alongside requests so we don't have to spend memory continually re-creating the pod requirements when we are iterating through the pods in our scheduling loops. This also prevents the garbage collector from having to run as frequently since there will be more live memory that is being used in the scheduling loop
These changes were executed against the scheduling benchmark (which showed negligible performance changes) and a live test that deploys 20,000 pods to the cluster and generates 10,000 nodes (with two pods per node constrained by the size of the instance types on NodePools). Prior to the change, this test took 27m17s. After the change, the same test case takes 25m24s (a 1m53s improvement).
Before PR
Scheduling Benchmark
Heap Profiles
Alloc Space
Inuse Space
Live Test
Scheduling Time: 27m17s
After PR
Scheduling Benchmark
Heap Profiles
Alloc Space
Inuse Space
Live Test
Scheduling Time: 25m24s
How was this change tested?
make presubmitBy submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.