[LU-3352] conf-sanity test_73: failover nids haven't changed

• Type: Bug
• Resolution: Fixed
• Priority: Blocker
• Fix Version/s: Lustre 2.4.1, Lustre 2.5.0
• Affects Version/s: Lustre 2.4.0
• Severity: 3
• Assignee: Emoly Liu
• Reporter: Maloo

Description

This issue was created by maloo for Andreas Dilger <[e-mail]>

This issue relates to the following test suite run: http://maloo.whamcloud.com/test_sets/e5d0ffde-bd82-11e2-a548-52540035b04c.

The sub-test test_73 failed with the following error in the test output:

failover nids haven't changed

Info required for matching: conf-sanity 73

Issue Links

• is related to: LU-3006 failover nids added after format don't propogate to clients
• is related to: LU-3244 Test failure on test suite conf-sanity, subtest test_73: failure to start ost

Comments

[Emoly Liu]

This problem is probably caused by the script

do_facet ost1 "$TUNEFS --failnode=1.2.3.4@tcp $(ostdevname 1)"

removing "@tcp" should work on IB network.

[Emoly Liu]

The maloo search result showed that conf-sanity test_73 had never passed with networktype=o2ib since it was created.

[Emoly Liu]

I think this may be infiniband only (similar to LU-2200).

Seems so. I will check it. Thanks.

[Nathaniel Clark]

I think this may be infiniband only (similar to LU-2200).

another instance:
https://maloo.whamcloud.com/test_sets/e5d0ffde-bd82-11e2-a548-52540035b04c
https://maloo.whamcloud.com/test_sets/792ed836-c225-11e2-a892-52540035b04c

[Keith Mannthey (Inactive)]

Another one here. I marked the test run as well. https://maloo.whamcloud.com/test_sets/2b2181d0-bd2e-11e2-a548-52540035b04c

[Peter Jones]

Emoly

Could you please look into this one?

Thanks

Peter

[Andreas Dilger]

This might be related to the recent changes in http://review.whamcloud.com/5982 and http://review.whamcloud.com/6216 that change the way that the target and MGS are notified about configuration changes.