[LU-2848] Failure on test suite sanity test_151: NOT IN CACHE before: , after:

• Type: Bug
• Resolution: Duplicate
• Priority: Minor
• Affects Version/s: Lustre 2.4.0
• Severity: 3
• Assignee: Li Wei (Inactive)
• Reporter: Maloo

Description

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

This issue relates to the following test suite run: https://maloo.whamcloud.com/test_sets/b63e5d08-7bf0-11e2-897d-52540035b04c.

The sub-test test_151 failed with the following error:

NOT IN CACHE: before: , after:

Got following error when testing lnet network hash with router. Servers(MDS and OSS) are IB and clients are using tcp. module parameter rnet_htable_size=1070

== sanity test 151: test cache on oss and controls ================================= 20:42:07 (1361421727)
3+0 records in
3+0 records out
12288 bytes (12 kB) copied, 0.00840027 s, 1.5 MB/s
 sanity test_151: @@@@@@ FAIL: NOT IN CACHE: before: , after:  
  Trace dump:
  = /usr/lib64/lustre/tests/test-framework.sh:3971:error_noexit()
  = /usr/lib64/lustre/tests/test-framework.sh:3994:error()
  = /usr/lib64/lustre/tests/sanity.sh:8373:test_151()
  = /usr/lib64/lustre/tests/test-framework.sh:4234:run_one()
  = /usr/lib64/lustre/tests/test-framework.sh:4267:run_one_logged()
  = /usr/lib64/lustre/tests/test-framework.sh:4137:run_test()
  = /usr/lib64/lustre/tests/sanity.sh:8393:main()
Dumping lctl log to /tmp/test_logs/2013-02-20/190622/sanity.test_151.*.1361421729.log
client-15: Host key verification failed.
client-15: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
client-15: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]
fat-amd-1-ib: Host key verification failed.
fat-amd-1-ib: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
fat-amd-1-ib: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]
fat-amd-3-ib: Host key verification failed.
fat-amd-3-ib: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
fat-amd-3-ib: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]
client-5: Host key verification failed.
client-5: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
client-5: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]

Issue Links

• is duplicated by: LU-2902 sanity test_156: NOT IN CACHE: before: , after:
• is related to: LU-2902 sanity test_156: NOT IN CACHE: before: , after:
• is related to: LU-2735 sanity.sh test_151: NOT IN CACHE: before: 337, after: 337

Comments

[Peter Jones]

duplicate of LU-2902

[Li Wei (Inactive)]

Thanks for letting me know; I'll leave it to you then.

[Keith Mannthey (Inactive)]

I am working on LU-2902 this is the same basic issue test_156 of sanity.

`roc_hit` and data we get back from it are having issues.

I have local debug ongoing to see if I can trigger it and a debug patch at http://review.whamcloud.com/5648.

I just thought I would cross point as it looks to be the same basic issue.

[Li Wei (Inactive)]

http://review.whamcloud.com/5680 (Diagnostic patch)

[Andreas Dilger]

This might also be a test environment issue, or is this because the remote node was down?

client-15: Host key verification failed.
client-15: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
client-15: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]
fat-amd-1-ib: Host key verification failed.
fat-amd-1-ib: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
fat-amd-1-ib: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]
fat-amd-3-ib: Host key verification failed.
fat-amd-3-ib: rsync: connection unexpectedly closed (0 bytes received so far) [sender]
fat-amd-3-ib: rsync error: unexplained error (code 255) at io.c(600) [sender=3.0.6]

[Andreas Dilger]

Looks like this is a problem in the /proc parameters, possibly related to get_osd_param() not finding the stats. The "$BEFORE" and "$AFTER" variables are empty, so roc_hit() is not finding the "cache_hit" statistic in "

{obdfilter,osd-*}

.$FSNAME-OST*.stats".

Some other minor cleanups needed in this test:

• use $(roc_hit) instead of `roc_hit`
• use 'skip "not cache-capable obdfilter"' and 'skip "oss cache is disabled"' instead of 'echo'
• wrap at 80 columns
• tabs for indentation