[LU-6182] racer test_1: test failed to respond and timed out

• Status: Closed
• Project: Lustre
• Affects Version/s: Lustre 2.7.0
• Type: Bug
• Priority: Minor
• Reporter: Maloo
• Assignee: WC Triage
• Resolution: Cannot Reproduce

Environment

client and server: lustre-master build #2835

• Severity: 3

Description

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

This issue relates to the following test suite run: https://testing.hpdd.intel.com/test_sets/8ec48e96-a7a9-11e4-93dd-5254006e85c2.

The sub-test test_1 failed with the following error:

test failed to respond and timed out

racer didn't finish in time while cannot find related error messages.

Info required for matching: racer 1

Comments

[Andreas Dilger]

First minor thing to fix is removing the spurious error messages from the console:

mdd_object.c:70:mdd_la_get()) lustre-MDD0000: object [0x200000403:0x101:0x0] not found: rc = -2
vvp_io.c:1214:vvp_io_init()) lustre: refresh file layout [0x200000401:0x21d:0x0] error -13
file.c:184:ll_close_inode_openhandle()) lustre-clilmv-ffff88006251b000: inode [0x200000401:0x189:0x0] mdc close failed: rc = -13

We shouldn't be printing console messages just because of -EACCESS (permission denied) or -ENOENT (file not found).

That won't close the bug, but will remove useless error messages that confuse the sysadmins and don't actually affect operation, and don't really help anyone.

[Saurabh Tandan (Inactive)]

master, build# 3264, 2.7.64 tag
Regression:EL6.7 Server/EL6.7 Client - DNE
https://testing.hpdd.intel.com/test_sets/a57f7cc6-9f7a-11e5-8c89-5254006e85c2

[Saurabh Tandan (Inactive)]

Server: 2.5.5, b2_5_fe/62
Client: Master, Build# 3266, Tag 2.7.64
https://testing.hpdd.intel.com/test_sets/a020d7ae-a04a-11e5-a33d-5254006e85c2

[Saurabh Tandan (Inactive)]

Another instance for EL7.1 Server/EL7.1 Client - DNE
Master , Build# 3270
https://testing.hpdd.intel.com/test_sets/6084f6b4-a26d-11e5-bdef-5254006e85c2

[James Nunez (Inactive)]

We haven't seen this issue in a long time. we've opened a few tickets recently, LU-11359 and LU-11358 for example, that record recent racer hangs. Thus, I'm closing this ticket.