[LU-7449] chmod hung at end of sanityn test_91

• Status: Resolved
• Project: Lustre
• Type: Bug
• Priority: Minor
• Reporter: Maloo
• Assignee: Niu Yawei (Inactive)
• Resolution: Cannot Reproduce
• Severity: 3

Description

This issue was created by maloo for John Hammond <[e-mail]>

This issue relates to the following test suite run: https://testing.hpdd.intel.com/test_sets/ba2de2ae-8998-11e5-a7bb-5254006e85c2.

The sub-test conf-sanity failed with the following error:

test failed to respond and timed out

conf-sanity failed because of a stuck chmod left over from sanityn test_91.

https://testing.hpdd.intel.com/test_logs/ba4c31a0-8998-11e5-a7bb-5254006e85c2/show_text

Please provide additional information about the failure here.

Info required for matching: sanityn test_91

Comments

[Niu Yawei (Inactive)]

Looks the stuck chmod isn't necessarily from test_91.

Stopping client onyx-37vm6.onyx.hpdd.intel.com /mnt/lustre opts:
Stopping client onyx-37vm5.onyx.hpdd.intel.com /mnt/lustre opts:
COMMAND  PID USER   FD   TYPE      DEVICE SIZE/OFF               NODE NAME
chmod   4569 root  cwd    DIR 1273,181606   282624 144115188193296385 /mnt/lustre
/mnt/lustre is still busy, wait one second

The pid of the stuck chmod is 4569. (The pid number is pretty small)

== sanityn test 91: chmod and unlink striped directory == 08:00:08 (1447344008)
start pid 31563 to chmod striped directory
start pid 31564 to unlink striped directory

The pid of chmod from test_91 is 31563.

But there isn't any further information (logs, stack trace, etc.)

[James Nunez (Inactive)]

Another conf-sanity failure on master:
2015-12-03 00:59:35 - https://testing.hpdd.intel.com/test_sets/0521ed0c-9982-11e5-9bd2-5254006e85c2
2015-12-08 07:09:11 - https://testing.hpdd.intel.com/test_sets/02c4fb4a-9da5-11e5-91b0-5254006e85c2
2016-01-03 12:09:15 - https://testing.hpdd.intel.com/test_sets/3166c44a-b229-11e5-bf32-5254006e85c2
2016-01-12 12:43:02 - https://testing.hpdd.intel.com/test_sets/6e90d156-b942-11e5-b318-5254006e85c2