[LU-16062] Different client and server timeouts during lock enqueue with BL AST set Created: 31/Jul/22  Updated: 11/Oct/22  Resolved: 12/Sep/22

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: None
Fix Version/s: Lustre 2.16.0

Type: Bug Priority: Minor
Reporter: Vitaly Fertman Assignee: Vitaly Fertman
Resolution: Fixed Votes: 0
Labels: None

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

 Description    
531.159590] LustreError: 10802:0:(ldlm_lockd.c:256:expired_lock_main()) ### lock callback timer expired after 99s: evicting client at 192.168.2.7@tcp  ns: mdt-lustre-MDT0002_UUID lock: ffff880967ce0480/0xd2e918f816df7d21 lrc: 3/0,0 mode: CR/CR res: [0x280000407:0x150:0x0].0x0 bits 0x9/0x0 rrc: 3 type: IBT flags: 0x60200400000020 nid: 192.168.2.7@tcp remote: 0x794bcb111018717d expref: 49 pid: 12233 timeout: 530 lvb_type: 0

while client timeout is
pb_timeout = 152,

So, if the reply was lost the client doesn't have time to resend.

 Comments   
Comment by Gerrit Updater [ 31/Jul/22 ]

"Vitaly Fertman <vitaly.fertman@hpe.com>" uploaded a new patch: https://review.whamcloud.com/48094
Subject: LU-16062 ldlm: improve bl_timeout for prolong
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: b0352aa23c01edf6ca2755875a8b914e10e0051a

Comment by Peter Jones [ 12/Sep/22 ]

Landed for 2.16

Generated at Sat Feb 10 03:23:40 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.