[LU-10470] performance-sanity on ubuntu: missing liblustreapi.so Created: 08/Jan/18  Updated: 21/Aug/18  Resolved: 21/Aug/18

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.10.3, Lustre 2.10.4, Lustre 2.10.5
Fix Version/s: None

Type: Bug Priority: Minor
Reporter: Minh Diep Assignee: WC Triage
Resolution: Cannot Reproduce Votes: 0
Labels: ubuntu

Issue Links:
Related
is related to LU-11176 Ubuntu package Issue Resolved
is related to LU-10365 sanity test 400a fails with 'client a... Resolved
Severity: 3
Rank (Obsolete): 9223372036854775807

 Description   

This issue was created by maloo for Minh Diep <minh.diep@intel.com>

This issue relates to the following test suite run:

https://testing.hpdd.intel.com/test_sets/1dca98e4-f471-11e7-8c43-52540065bddc

+ su mpiuser sh -c "/usr/bin/mpirun --mca btl tcp,self --mca btl_tcp_if_include eth0 -mca boot ssh -machinefile /tmp/mdsrate-create-small.machines -np 1 /usr/lib64/lustre/tests/mdsrate --create --time 600 --nfiles 129464 --dir /mnt/lustre/mdsrate/single --filefmt 'f%%d' "
/usr/lib64/lustre/tests/mdsrate: error while loading shared libraries: liblustreapi.so: cannot open shared object file: No such file or directory
-------------------------------------------------------
Primary job terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
-------------------------------------------------------
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

Process name: [[34766,1],0]
Exit code: 127



 Comments   
Comment by James A Simmons [ 06/Aug/18 ]

Same as LU-111176. 

Comment by James A Simmons [ 06/Aug/18 ]

Give the patch https://review.whamcloud.com/#/c/32943 a try.

Comment by James Nunez (Inactive) [ 16/Aug/18 ]

We landed the suggested patch, https://review.whamcloud.com/#/c/32943, but are still seeing the same error.

The following test results are for Ubuntu 16.04 clients with CentOS 7 servers for b2_10 build #135 which includes patch 32943; https://testing.whamcloud.com/test_sets/c38af0c2-a0fa-11e8-8ee3-52540065bddc .

Comment by James A Simmons [ 17/Aug/18 ]

Numez I pinged you on Skype. I will need to work with you to see what is exactly going with these nodes.

Comment by James A Simmons [ 20/Aug/18 ]

Looking at the built packages I noticed that liblusterapi.so is located in the lustre-devel-*.deb package. I have to ask is that package being installed into the test image. This could explain why some of the Ubuntu test are failing. Can you verify?

Comment by Minh Diep [ 21/Aug/18 ]

Hi simmonsja,

looking at https://build.whamcloud.com/job/lustre-b2_10/arch=x86_64,build_type=client,distro=ubuntu1604,ib_stack=inkernel/ I don't see a lustre-devel-*.deb package

Comment by James Nunez (Inactive) [ 21/Aug/18 ]

I think James means lustre-dev package. For the latest b2_10 it would be lustre-dev_2.10.5-RC2-1_amd64.deb .

Comment by James A Simmons [ 21/Aug/18 ]

Thanks Nunez. That is what I meant. typo...

Minh when you installed this into the b2_10 and master repo images please let me know. I do have a patch for LU-10365 to push which will require this change.

Comment by Minh Diep [ 21/Aug/18 ]

simmonsja, you can push it now. I have added lustre-dev to the installation

Comment by James A Simmons [ 21/Aug/18 ]

I rebased https://review.whamcloud.com/#/c/31737. Lets see if it passes now.

Comment by James A Simmons [ 21/Aug/18 ]

Minh is it safe to close this ticket now?

Comment by Minh Diep [ 21/Aug/18 ]

yes

Generated at Sat Feb 10 02:35:23 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.