Repository navigation
Admission: a disabled external runtime counts for no memory - #104
Merged
Merged
Conversation
Admission counted a runtime as loaded from its last status alone. A disabled external runtime, which LLooM does not own, kept its last running status, so its memory stayed on the node's budget and the plan proposed stopping it. On 01 a retired 96 GB external entry for the old TP-4 server made TP-4 admission project 210 GB. A disabled external runtime now counts as not loaded. A disabled managed runtime that is still up keeps counting until LLooM stops it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Admission counted a runtime as loaded from its last status alone. A disabled external runtime, which LLooM doesn't own, kept its last
runningorexternalstatus. So its memory stayed on the node's budget, and the plan proposed stopping it.Found during tonight's TP-4 qualification. On 01, the retired external entry for the old TP-4 server (
sparkglm-tp4-standalone, 96 GB) made TP-4 admission project 210 GB on a node with 5.8 GB actually in use.Fix: a disabled external runtime counts as not loaded. A disabled managed runtime that's still up keeps counting until LLooM stops it.
Test:
test/runtime-policy.test.mjs. A retired external runtime with a stale status adds nothing and gets no stop action, while a disabled managed one that's still running is counted. It fails before the fix: 65 GB projected instead of 35.check,lint,format:checkandtest:unitpass.🤖 Generated with Claude Code