jewel: mds: Failure in #11415

merged 1 commit into from Oct 17, 2016


None yet

3 participants

@ukernel @ldachary ukernel mds: remove fail-safe queueing replay request
MDSRank::queue_one_replay() does not create active request
immediately, it just queues corresponding C_MDS_RetryMessage
for execution. So the fail-safe code can queue an extra replay
request. This can cause replay requests be processed out-of-order

Signed-off-by: Yan, Zheng <>
(cherry picked from commit d755a4a)
@dachary dachary self-assigned this Oct 11, 2016
@dachary dachary added this to the jewel milestone Oct 11, 2016
dachary commented Oct 13, 2016

jenkins test this please (unittest_bluefs core)

dachary commented Oct 14, 2016

@jcsp does this backport look good to merge ? It passed the fs suite (except for one known bug that is, I believe, unrelated)

@jcsp jcsp was assigned by dachary Oct 14, 2016
dachary commented Oct 17, 2016

jenkins test this please (terminated it seems, no failure visible)

jcsp commented Oct 17, 2016


@dachary dachary merged commit ada7edd into ceph:jewel Oct 17, 2016

1 of 2 checks passed

default Build started sha1 is merged.
Signed-off-by all commits in this PR are signed
@theanalyst theanalyst changed the title from jewel: Failure in to "jewel: mds: Failure in" Nov 17, 2016
@theanalyst theanalyst changed the title from "jewel: mds: Failure in" to jewel: mds: Failure in Nov 17, 2016
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment