NAS-139155 / None / nvme-pci: optimize hung device timeouts and remove stale namespaces#236
Closed
ixhamza wants to merge 1 commit intotruenas/linux-6.18from
Closed
NAS-139155 / None / nvme-pci: optimize hung device timeouts and remove stale namespaces#236ixhamza wants to merge 1 commit intotruenas/linux-6.18from
ixhamza wants to merge 1 commit intotruenas/linux-6.18from
Conversation
bugclerk
changed the title
Reduce hung device detection time by eliminating redundant waits: - Skip explicit queue deletion during reset (saves admin_timeout) - Detect hung device after first CAP.TO by checking CSTS.RDY - Skip re-enable in reset_work for hung devices (saves CAP.TO) Total savings: admin_timeout + CAP.TO for hung devices. For example, with default admin_timeout (60s) and CAP.TO of 45s, this saves 105 seconds. For hung devices, namespaces are removed after transitioning to DEAD state. This cleans up stale block devices that previously remained visible to userspace despite the dead controller, and generates hotplug events enabling proper drive replacement workflows. Signed-off-by: Ameer Hamza <ahamza@ixsystems.com>
Member
Author
|
Superseded by #238. |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reduce hung device detection time by eliminating redundant waits:
admin_timeout)CAP.TOby checkingCSTS.RDYCAP.TO)Total savings:
admin_timeout+CAP.TOfor hung devices. For example, with default admin_timeout (60s) andCAP.TOof 45s (Customer's Scenario), this saves 105 seconds.For hung devices, namespaces are removed after transitioning to DEAD state. This cleans up stale block devices that previously remained visible to userspace despite the dead controller, and generates hotplug events enabling proper drive replacement workflows.
Testing