Final drop of the scale-from-zero implementation - #606
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR implements scale-from-zero functionality by integrating pod-based metrics collection from EndpointPicker services and preparing for direct actuation to scale workloads from zero replicas.
Changes:
- Replaced
client.Readerwithclient.Clientthroughout the codebase to enable write operations needed for scaling - Integrated
PodScrapingSourceinto the datastore to collect metrics from EndpointPicker pods - Added infrastructure for direct actuation with commented-out code blocks pending completion
Reviewed changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 9 comments.
Show a summary per file
| File | Description |
|---|---|
| internal/utils/pool/pool.go | Updated function signatures to accept client.Client instead of client.Reader |
| internal/utils/pool/gvr.go | Fixed package declaration from scalefromzero to pool |
| internal/engines/scalefromzero/engine_test.go | Updated test to use Client field instead of Reader |
| internal/engines/scalefromzero/engine.go | Added metrics collection logic using PodScrapingSource and prepared actuation code |
| internal/datastore/datastore_test.go | Updated test calls to include required ctx and client parameters |
| internal/datastore/datastore.go | Enhanced PoolSet to create and register pod scraping sources for metrics collection |
| internal/controller/inferencepool_reconciler_test.go | Updated tests to use Client field instead of Reader |
| internal/controller/inferencepool_reconciler.go | Changed reconciler to use client.Client and pass required parameters |
| cmd/main.go | Updated main to pass Client instead of Reader to reconciler |
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 20, 2026 18:31
eefa54a to
8fff566
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 20, 2026 22:08
974503a to
2555737
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 21, 2026 02:50
3d3652b to
a53f130
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 21, 2026 13:21
43b45df to
cd8e033
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 21, 2026 14:24
62decf8 to
484e6d0
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 23, 2026 18:54
475f02a to
dabdbcb
Compare
Collaborator
Author
Done! I am expecting for this PR to have a single commit only. Thanks! |
| while [ $SENT -lt %d ]; do | ||
| echo "Sending request $((SENT + 1)) / %d..." | ||
|
|
||
| RESPONSE=$(curl -s -w "\n%%{http_code}" --max-time 180 -X POST http://%s:80/v1/completions \ |
Collaborator
There was a problem hiding this comment.
should be http://%s-istio:80/v1/completions
dumb0002
force-pushed
the
scale-from-zero-part2
branch
2 times, most recently
from
January 23, 2026 20:50
538da74 to
61a093d
Compare
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 16 out of 16 changed files in this pull request and generated 1 comment.
Comments suppressed due to low confidence (1)
deploy/install.sh:1
- The word 'addres' is misspelled in the commented-out echo statement.
#!/bin/bash
| wg.Wait() | ||
| close(errorCh) | ||
|
|
||
| // Aggregate errors |
Collaborator
There was a problem hiding this comment.
Error aggregation below should run in a goroutine to consume errors as they are produced. Otherwise there is a risk of a deadlock when the errorCh buffer is full.
Collaborator
Author
There was a problem hiding this comment.
I fix it in a follow-up PR. Thanks!
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 23, 2026 21:07
07dc069 to
2ad304a
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 23, 2026 21:13
2ad304a to
f6952a7
Compare
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 23, 2026 21:17
f6952a7 to
f59205c
Compare
Signed-off-by: Braulio Dumba <Braulio.Dumba@ibm.com>
dumb0002
force-pushed
the
scale-from-zero-part2
branch
from
January 23, 2026 21:32
3b31877 to
ef00e47
Compare
Collaborator
|
/ok-to-test |
Collaborator
|
/retest |
Collaborator
|
/lgtm |
Collaborator
|
emulated tests pass. Merging. |
github-actions
Bot
added
the
lgtm
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
lionelvillard
approved these changes
Jan 23, 2026
lionelvillard
left a comment
lionelvillard
left a comment
Collaborator
There was a problem hiding this comment.
thanks @dumb0002 , great work!
This file contains hidden or 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
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.
This PR starts the implementation of the logic to support scale from zero outlined in the design doc here
This PR is responsible for the following:
Related Issue: #372