[LU-16658] performance sanity test_6 mdsrate-lookup-10dirs - UCX ERROR

• Type: Bug
• Resolution: Fixed
• Priority: Critical
• Labels: failing_tests
• Severity: 3
• Assignee: WC Triage
• Reporter: Andreas Dilger

Description

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

This issue relates to the following test suite run: https://testing.whamcloud.com/test_sets/d2a273de-f0d8-426b-adb8-ccd3fed94347

Client appears to hand/drop connection while doing initial file/dir creation

===== mdsrate-lookup-10dirs.sh Test preparation: creating 10 dirs with 12650 files.
+ /usr/lib64/openmpi/bin/mdsrate --mknod --ndirs 10 --dirfmt '/mnt/lustre/mdsrate/lookup-%d' --nfiles 12650 --filefmt 'f%%d'
+ chmod 0777 /mnt/lustre
drwxrwxrwx 4 root root 4096 Jul 19 19:11 /mnt/lustre
+ su mpiuser sh -c "/usr/lib64/openmpi/bin/mpirun --mca btl tcp,self --mca btl_tcp_if_include eth0 -mca boot ssh --oversubscribe --oversubscribe -machinefile /tmp/auster.machines -np 10 /usr/lib64/openmpi/bin/mdsrate --mknod --ndirs 10 --dirfmt '/mnt/lustre/mdsrate/lookup-%d' --nfiles 12650 --filefmt 'f%%d' "
0: onyx-91vm11.onyx.whamcloud.com starting at Tue Jul 19 19:11:39 2022
[1658257899.971284] [onyx-91vm12:60266:0]          select.c:514  UCX  ERROR   no active messages transport to <no debug data>: posix/memory - Destination is unreachable, sysv/memory - Destination is unreachable, self/memory0 - Destination is unreachable, tcp/eth0 - Destination is unreachable, tcp/lo - Destination is unreachable

VVVVVVV DO NOT REMOVE LINES BELOW, Added by Maloo for auto-association VVVVVVV
performance-sanity test_6 - Timeout occurred after 610 minutes, last suite running was performance-sanity

Issue Links

• is related to: LU-3786 performance-sanity test_6: mkdir hung (sys_mkdir)
• is related to: LU-16729 replace mdsrate with mdtest in Lustre test suite
• is related to: LU-16270 performance-sanity test_6: mkdir: cannot create directory '/mnt/lustre/mdsrate': File exists