[LU-4562] parallel-scale test_connectathon: didn't read '.' dir entry, pass 0 Created: 29/Jan/14  Updated: 07/May/14  Resolved: 07/May/14

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

Type: Bug Priority: Blocker
Reporter: Maloo Assignee: Di Wang
Resolution: Duplicate Votes: 0
Labels: None
Environment:

server and client: lustre-master build # 1837 RHEL6 ldiskfs


Issue Links:
Duplicate
duplicates LU-4715 creating enough files in a directory ... Resolved
is duplicated by LU-856 Test failure on test suite parallel-s... Closed
Related
is related to LU-3531 DNE2: striped directory Resolved
Severity: 3
Rank (Obsolete): 12453

 Description   

This issue was created by maloo for sarah <sarah@whamcloud.com>

This issue relates to the following test suite run: http://maloo.whamcloud.com/test_sets/bf0a39ca-859f-11e3-a2cb-52540035b04c.

The sub-test test_connectathon failed with the following error:

connectathon failed: 1

test log shows

./test6: readdir
	./test6: (/mnt/lustre/d0.connectathon) didn't read '.' dir entry, pass 0
	./test6: (/mnt/lustre/d0.connectathon) Test failed with 1 errors
basic tests failed
 parallel-scale test_connectathon: @@@@@@ FAIL: connectathon failed: 1 


 Comments   
Comment by Jodi Levi (Inactive) [ 29/Jan/14 ]

Di,
Can you please take a look and comment on this ticket?
Thank you!

Comment by Di Wang [ 29/Jan/14 ]

This might already be fixed by this patch, which is landed after tag 2.5.54.

commit 7117ff487e59737a3d375b8d8bf1464201b4ea05
Author: wang di <di.wang@intel.com>
Date: Mon Jan 20 15:49:34 2014 -0800

LU-3531 mdc: release dir page cache after accessing

Release the dir page cache in llite/lmv, so the page
will be hold until entires was filled by filldir.

Signed-off-by: wang di <di.wang@intel.com>
Change-Id: I8b24bec74b14ff2b65130c02294821fc16ca1421
Reviewed-on: http://review.whamcloud.com/8935
Tested-by: Jenkins
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Tested-by: Oleg Drokin <oleg.drokin@intel.com>

Please check how it goes with the later build. Thanks.

Comment by Sarah Liu [ 07/Feb/14 ]

the latest tag-2.4.55 still has this problem:

https://maloo.whamcloud.com/test_sets/8e7d66a2-8e18-11e3-9383-52540035b04c

Comment by Jian Yu [ 18/Feb/14 ]

Lustre Build: http://build.whamcloud.com/job/lustre-master/1890/

The failure still occurred:
https://maloo.whamcloud.com/test_sets/34da534a-9687-11e3-bc3b-52540035b04c
https://maloo.whamcloud.com/test_sets/4ab871b0-9687-11e3-bc3b-52540035b04c
https://maloo.whamcloud.com/test_sets/68f2c766-9687-11e3-bc3b-52540035b04c
https://maloo.whamcloud.com/test_sets/374bbd46-9680-11e3-a009-52540035b04c
https://maloo.whamcloud.com/test_sets/56a578e4-9680-11e3-a009-52540035b04c
https://maloo.whamcloud.com/test_sets/68db57f4-9680-11e3-a009-52540035b04c

Comment by Di Wang [ 20/Feb/14 ]

probably try this build http://review.whamcloud.com/#/c/9191/ to see whether it fix the problem.

Comment by Andreas Dilger [ 14/Mar/14 ]

I suspect that this may be the same as LU-4715.

Comment by Di Wang [ 07/May/14 ]

According to the log, the fix in LU-4603 should fix this problem. Please re-open it if not.

Generated at Sat Feb 10 01:43:50 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.