Scheduling benchmark #1594
Merged
Scheduling benchmark #1594
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
✅ Deploy Preview for karpenter-docs-prod canceled.
|
tzneal
force-pushed
the
scheduling-benchmark
branch
from
184115e to
3744b39
Compare
name old time/op new time/op delta Scheduling1-12 1.08ms ± 1% 0.85ms ± 2% -21.52% (p=0.008 n=5+5) Scheduling50-12 33.3ms ± 3% 21.5ms ± 4% -35.43% (p=0.008 n=5+5) Scheduling100-12 62.4ms ± 2% 39.9ms ± 3% -36.05% (p=0.008 n=5+5) Scheduling500-12 231ms ± 1% 151ms ± 2% -34.80% (p=0.008 n=5+5) Scheduling1000-12 504ms ± 1% 367ms ± 8% -27.16% (p=0.008 n=5+5) Scheduling2000-12 1.18s ± 4% 0.88s ± 2% -25.07% (p=0.008 n=5+5) Scheduling5000-12 4.50s ± 2% 3.94s ± 6% -12.48% (p=0.008 n=5+5) name old pods/sec new pods/sec delta Scheduling1-12 925 ± 1% 1178 ± 2% +27.43% (p=0.008 n=5+5) Scheduling50-12 1.50k ± 3% 2.33k ± 4% +54.94% (p=0.008 n=5+5) Scheduling100-12 1.60k ± 2% 2.51k ± 3% +56.42% (p=0.008 n=5+5) Scheduling500-12 2.16k ± 1% 3.32k ± 2% +53.41% (p=0.008 n=5+5) Scheduling1000-12 1.99k ± 1% 2.73k ± 7% +37.57% (p=0.008 n=5+5) Scheduling2000-12 1.70k ± 4% 2.26k ± 2% +33.43% (p=0.008 n=5+5) Scheduling5000-12 1.11k ± 2% 1.27k ± 6% +14.42% (p=0.008 n=5+5)
tzneal
force-pushed
the
scheduling-benchmark
branch
from
3744b39 to
ee5d730
Compare
ellistarn
reviewed
Mar 30, 2022
Makefile
Outdated
| @@ -6,6 +6,13 @@ LDFLAGS ?= -ldflags=-X=github.com/aws/karpenter/pkg/utils/project.Version=$(shel | |||
| GOFLAGS ?= -tags=$(CLOUD_PROVIDER) $(LDFLAGS) | |||
| WITH_GOFLAGS = GOFLAGS="$(GOFLAGS)" | |||
|
|
|||
| # detect nice binary | |||
There was a problem hiding this comment.
In the interest of keeping this Makefile manageable, I think it's fair to assume that you need nice installed if you want to run the benchmark.
There was a problem hiding this comment.
I'm fine removing it entirely, doubt CI has it and if you want it locally you can just run nice -19 make benchmark
ellistarn
approved these changes
Mar 30, 2022
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.
1. Issue, if available:
N/A
2. Description of changes:
Extends scheduling benchmark and adds a minimum pods/sec scheduling threshold to CI builds.
3. How was this change tested?
Unit tests & on EKS scaling up/down the inflate deployment.
4. Does this change impact docs?
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.