release-26.1: mmaprototype: fix panic when sls <= loadNoChange but nls > loadNoChange #160633
+121
−3
Conversation
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
Add a datadriven test that reproduces the panic in sortTargetCandidateSetAndPick when sls <= loadNoChange but nls > loadNoChange. The scenario involves a node with two stores where one store (s2) contributes heavily to node CPU overload while another (s1) does not. When s1 tries to shed based on node-level overload, the candidate set excludes s2 (due to refusing disposition), making s1's store-level load look normal, but sortTargetCandidateSetAndPick receives sls as the loadThreshold which violates its invariant. Also add panic recovery to TestClusterState so panics are captured as expected output rather than failing the test, enabling regression tests for panic bugs. Informs cockroachdb#160569
When deciding whether a store should shed load, computeCandidatesForReplicaTransfer was checking both sls (store-level) and nls (node-level) load summaries. If nls indicated overload but sls did not, shedding would proceed anyway. This caused a panic in sortTargetCandidateSetAndPick which requires loadThreshold > loadNoChange. The fix is to only check sls when deciding if a store should shed. If sls <= loadNoChange, the store itself isn't overloaded relative to candidates that can receive the load. High nls with low sls means other stores on the node are causing node-level overload, so shedding from this store wouldn't help. Fixes cockroachdb#160569
blathers-crl
bot
added
blathers-backport
|
Thanks for opening a backport. Before merging, please confirm that the change does not break backwards compatibility and otherwise complies with the backport policy. Include a brief release justification in the PR description explaining why the backport is appropriate. All backports must be reviewed by the TL for the owning area. While the stricter LTS policy does not yet apply, please exercise judgment and consider gating non-critical changes behind a disabled-by-default feature flag when appropriate. |
blathers-crl
bot
added
backport
Member
|
This change is |
wenyihu6
approved these changes
Jan 7, 2026
sumeerbhola
approved these changes
Jan 7, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Backport 2/2 commits from #160615 on behalf of @tbg.
When deciding whether a store should shed load, computeCandidatesForReplicaTransfer
was checking both sls (store-level) and nls (node-level) load summaries. If nls
indicated overload but sls did not, shedding would proceed anyway. This caused a
panic in sortTargetCandidateSetAndPick which requires loadThreshold > loadNoChange.
The fix is to only check sls when deciding if a store should shed. If sls <=
loadNoChange, the store itself isn't overloaded relative to candidates that can
receive the load. High nls with low sls means other stores on the node are
causing node-level overload, so shedding from this store wouldn't help.
Fixes #160569
Release justification: low risk fix for panics in mmaprototype