[LU-6123] conf-sanity test_72: FAIL: mount client failed

• Status: Resolved
• Project: Lustre
• Affects Version/s: Lustre 2.7.0
• Fix Version/s: Lustre 2.9.0
• Type: Bug
• Priority: Blocker
• Reporter: Jian Yu
• Assignee: Lai Siyao
• Resolution: Fixed

Environment

Lustre build: https://build.hpdd.intel.com/job/lustre-master/2820

• Severity: 3

Description

conf-sanity test 72 failed as follows:

mount lustre on /mnt/lustre.....
Starting client: shadow-52vm2.shadow.whamcloud.com:  -o user_xattr,flock shadow-52vm7@tcp:/lustre /mnt/lustre
CMD: shadow-52vm2.shadow.whamcloud.com mkdir -p /mnt/lustre
mkdir: cannot create directory `/mnt/lustre': File exists
CMD: shadow-52vm2.shadow.whamcloud.com mount -t lustre -o user_xattr,flock shadow-52vm7@tcp:/lustre /mnt/lustre
warning: /mnt/lustre: cannot resolve: Cannot send after transport endpoint shutdown
 conf-sanity test_72: @@@@@@ FAIL: mount client failed

Console log on client:

01:36:43:Lustre: Evicted from MGS (at 10.1.6.88@tcp) after server handle changed from 0x4724486cf472d1a2 to 0x4724486cf48d6a17
01:36:43:Lustre: MGC10.1.6.88@tcp: Connection restored to MGS (at 10.1.6.88@tcp)
01:36:43:Lustre: DEBUG MARKER: mkdir -p /mnt/lustre
01:36:43:LustreError: 167-0: lustre-MDT0000-mdc-ffff88007ae1e400: This client was evicted by lustre-MDT0000; in progress operations using this service will fail.
01:36:43:LustreError: 1193:0:(file.c:3170:ll_inode_revalidate_fini()) lustre: revalidate FID [0x200000007:0x1:0x0] error: rc = -5
01:36:43:Lustre: DEBUG MARKER: mount -t lustre -o user_xattr,flock shadow-52vm7@tcp:/lustre /mnt/lustre
01:36:43:Lustre: DEBUG MARKER: /usr/sbin/lctl mark  conf-sanity test_72: @@@@@@ FAIL: mount client failed

Maloo reports:
https://testing.hpdd.intel.com/test_sets/e379ea16-9b9d-11e4-9d4a-5254006e85c2
https://testing.hpdd.intel.com/test_sets/79089440-9bbe-11e4-b679-5254006e85c2
https://testing.hpdd.intel.com/test_sets/3e12c382-9bec-11e4-afb8-5254006e85c2
https://testing.hpdd.intel.com/test_sets/06263934-9bf3-11e4-b679-5254006e85c2

Issue Links

• is related to: LU-4340 conf-sanity test_69: error: File too ...
• is related to: LU-6063 conf-sanity test_76a fails on RHEL7, ...

Comments

[Jian Yu]

conf-sanity test 76a hit the same failure.

[Jodi Levi (Inactive)]

Lai,
Could you please have a look at this one?
Thank you!

[Lai Siyao]

maloo logs don't provide any useful information, and I can't reproduce it in local system.

[Oleg Drokin]

I suspect this might be another manifestation of LU-5420.

[Jian Yu]

After except conf-sanity test 69, the tests passed:
https://testing.hpdd.intel.com/test_sets/d6a1d7ea-330a-11e5-a247-5254006e85c2

[Andreas Dilger]

LU-4340 is fixing test_69, so likely this can be closed when that is landed.

[Lai Siyao]

This doesn't show up again after LU-4340 gets fixed, let's close it.