[LU-8319] ASSERTION( inode == parent_dir ) failed: Created: 23/Jun/16  Updated: 01/Jun/21  Resolved: 12/Jul/16

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.8.0
Fix Version/s: Lustre 2.9.0

Type: Bug Priority: Critical
Reporter: nasf (Inactive) Assignee: nasf (Inactive)
Resolution: Fixed Votes: 0
Labels: None

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

 Description   

MDS crashed after 11 failovers:
2016-05-20 01:05:27 LustreError: 7776:0:(osd_handler.c:4175:osd_add_dot_dotdot()) ASSERTION( inode == parent_dir ) failed:
2016-05-20 01:05:27 LustreError: 44966:0:(osd_oi.c:725:osd_oi_insert()) lustre-MDT0000: the FID [0x200002435:0x2:0x0] is used by two objects: 536346719/3853005504 421527648/3853005505
2016-05-20 01:05:27 LustreError: 7776:0:(osd_handler.c:4175:osd_add_dot_dotdot()) LBUG



 Comments   
Comment by nasf (Inactive) [ 23/Jun/16 ]

Some logs show that there are FID allocation race:

40000000:00000040:3.0:1466298378.858704:0:8605:0:(fid_handler.c:309:__seq_server_alloc_meta()) srv-lustre-MDT0000: Allocated meta-sequence [0x00000002000004fc-0x00000002000004fd):0:mdt
40000000:00000040:3.0:1466298378.858707:0:8605:0:(fid_request.c:226:seq_client_alloc_seq()) cli-lustre-MDT0000: New range - [0x00000002000004fc-0x00000002000004fd):0:mdt
40000000:00000040:3.0:1466298378.858708:0:8605:0:(fid_request.c:237:seq_client_alloc_seq()) cli-lustre-MDT0000: Allocated sequence [0x2000004fc]
40000000:00000040:3.0:1466298378.858710:0:8605:0:(fid_request.c:363:seq_client_alloc_fid()) cli-lustre-MDT0000: Switch to sequence [0x00000002000004fc]
40000000:00000040:9.0:1466298378.858711:0:8791:0:(fid_request.c:382:seq_client_alloc_fid()) cli-lustre-MDT0000: Allocated FID [0x2000004fc:0x2:0x0]
40000000:00000040:3.0:1466298378.858714:0:8605:0:(fid_request.c:382:seq_client_alloc_fid()) cli-lustre-MDT0000: Allocated FID [0x2000004fc:0x2:0x0]

So the both processes (8791 and 8605) got the same FID.

Comment by Gerrit Updater [ 23/Jun/16 ]

Fan Yong (fan.yong@intel.com) uploaded a new patch: http://review.whamcloud.com/20939
Subject: LU-8319 fid: fix race in fid allocation
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: f4e0293d7630341a8cd2527848a2c30f637fbd7c

Comment by Gerrit Updater [ 11/Jul/16 ]

Oleg Drokin (oleg.drokin@intel.com) merged in patch http://review.whamcloud.com/20939/
Subject: LU-8319 fid: fix race in fid allocation
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 4c066a61d5bc4b59e6fd23d5416500f0e61be3a1

Comment by nasf (Inactive) [ 12/Jul/16 ]

The patch has been landed to master.

Comment by Gerrit Updater [ 24/Aug/16 ]

Fan Yong (fan.yong@intel.com) uploaded a new patch: http://review.whamcloud.com/22122
Subject: LU-8319 fid: fix race in fid allocation
Project: fs/lustre-release
Branch: b2_7
Current Patch Set: 1
Commit: 1416e46fb3474638dcbf3359d9194c9cec9f2ea4

Generated at Sat Feb 10 02:16:30 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.