[LU-8348] Don't send an last_commited after journal abort to ability a replay uncommitted data Created: 29/Jun/16  Updated: 10/Sep/16  Resolved: 10/Sep/16

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: None
Fix Version/s: Lustre 2.9.0

Type: Bug Priority: Major
Reporter: Artem Blagodarenko (Inactive) Assignee: WC Triage
Resolution: Fixed Votes: 0
Labels: patch

Issue Links:
Duplicate
Severity: 3
Rank (Obsolete): 9223372036854775807

 Description   

If FS hit an error and journal aborted, commited callback will called with non zero errno. But lustre ignore a error flag and update a last_rcvd / last_commited values. If any reply executed in same time clients will have a new last_commited updates and flush a requests from un-commited queue.
But it data isn't on persistent storage and need to be replayed after fail to avoid data corruption.

 Comments   
Comment by Gerrit Updater [ 29/Jun/16 ]

Artem Blagodarenko (artem.blagodarenko@seagate.com) uploaded a new patch: http://review.whamcloud.com/21060
Subject: LU-8348 recovery: don't send last_committed after panic
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 090bb282a768eb6334f245fd764c14284dfc5470

Comment by Gerrit Updater [ 10/Sep/16 ]

Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/21060/
Subject: LU-8348 recovery: don't send last_committed after panic
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 89ebd1fd43a30b5446aeb0c4e26357bbdb073f08

Comment by Peter Jones [ 10/Sep/16 ]

Landed for 2.9

Generated at Sat Feb 10 02:16:45 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.