Os after controller fails
ClosedPublic
Actions

Authored by imp on Jul 28 2021, 10:33 PM.

Details

Reviewers

mav
chuck

Commits

rG24d2d1813e82: nvme/nda: Fail all nvme I/Os after controller fails
rG4b977e6dda92: nvme/nda: Fail all nvme I/Os after controller fails

Summary

Once the controller has failed, fail all I/O w/o sending it to the
device. The reset of the nvme driver won't schedule any I/O to the
failed device, and the controller is in an indeterminate state and can't
accept I/O. Fail both at the top end of the sim and the bottom
end. Don't bother queueing up the I/O for failure in a different task.

Diff Detail

Repository

rS FreeBSD src repository - subversion

Lint

Lint Passed

Unit

No Test Coverage

Build Status

Buildable 40815
Build 37704: arc lint + arc unit

Event Timeline

imp created this revision.Jul 28 2021, 10:33 PM

Herald added a subscriber: dab. · View Herald TranscriptJul 28 2021, 10:33 PM

imp requested review of this revision.Jul 28 2021, 10:33 PM

Harbormaster completed remote builds in B40735: Diff 92909.Jul 28 2021, 10:33 PM

imp added reviewers: mav, chuck.Jul 28 2021, 10:33 PM

chuck added inline comments.Jul 31 2021, 2:59 PM

sys/dev/nvme/nvme_qpair.c
1076–1077	Should this comment get updated as `nvme_qpair_manual_complete_request()` isn't posting to a task?
sys/dev/nvme/nvme_sim.c
262	I'm not seeing a definition for `CAM_REQ_DEV_NOT_THERE`. Should this be `CAM_DEV_NOT_THERE`?