Prevent remote writes from hanging after source death - #25
Open
mkhazraee wants to merge 7 commits into
Open
Conversation
mkhazraee
force-pushed
the
moein/dead_src_hang
branch
from
September 10, 2026 01:14
b058119 to
f80211e
Compare
Signed-off-by: Moein <moein@nvidia.com>
Signed-off-by: Moein <moein@nvidia.com>
Retry failed probe sends within the existing grace period and re-probe unresolved writes when a same-name source returns. Add stall timing to logs and document the intentional best-effort failure policy. Signed-off-by: Moein <moein@nvidia.com>
Retain unresolved target writes and their memory registrations during shutdown. Notify targets after safe source cancellation, and probe unknown-generation tombstones instead of clearing them. Signed-off-by: Moein <moein@nvidia.com>
mkhazraee
force-pushed
the
moein/dead_src_hang
branch
from
September 10, 2026 19:48
b3630c2 to
69dd697
Compare
Signed-off-by: Moein <moein@nvidia.com>
Extract probe and cancellation handling; detect late writes. Track source incarnations through Guard-confirmed death. Document the best-effort contract and update lifecycle tests. Signed-off-by: Moein <moein@nvidia.com>
Keep native transfers tracked for cleanup. Report unresolved cancellations and late writes through an optional handler, logging by default. Signed-off-by: Moein <moein@nvidia.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add a control-channel probe when a remote write times out.
Testing