[LU-9507] o2iblnd assert on reconnect Created: 16/May/17  Updated: 25/Aug/17  Resolved: 29/May/17

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: None
Fix Version/s: Lustre 2.10.0

Type: Bug Priority: Critical
Reporter: Amir Shehata (Inactive) Assignee: Doug Oucharek (Inactive)
Resolution: Fixed Votes: 0
Labels: None

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

 Description   

An assert in kiblnd_reconnect_peer() is being hit. With the multi-qp patch, it is possible to have ibp_connecting to be > 0. Since one connection can fail, and an attempt to reconnect can occur, while the other connections are still being established.

Discussed with Doug and this assert should be changed to an if statement, to log when this situation occurs instead of asserting.



 Comments   
Comment by Gerrit Updater [ 16/May/17 ]

Doug Oucharek (doug.s.oucharek@intel.com) uploaded a new patch: https://review.whamcloud.com/27139
Subject: LU-9507 lnd: Don't Assert On Reconnect with MultiQP
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 86b1e6bd11953858cde708cb55dd20f687109320

Comment by Gerrit Updater [ 29/May/17 ]

Oleg Drokin (oleg.drokin@intel.com) merged in patch https://review.whamcloud.com/27139/
Subject: LU-9507 lnd: Don't Assert On Reconnect with MultiQP
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: abf2ecad35e81f9c247da5c8214fa2fd7baf5439

Comment by Peter Jones [ 29/May/17 ]

Landed for 2.10

Generated at Sat Feb 10 02:26:48 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.