== replay-dual test 26: dbench and tar with mds failover ========================================================== 02:30:08 (1738481408) Starting client oleg451-client.virtnet: -o user_xattr,flock 192.168.204.151@tcp:/lustre /mnt/lustre Started clients oleg451-client.virtnet: 192.168.204.151@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,noencrypt,statfs_project) Started tar loop with pid 14957 Started dbench loop with 14958 looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Sun Feb 2 02:30:10 EST 2025 waiting for dbench pid 14989 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs failed to create barrier semaphore 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients 1 189 7.58 MB/sec warmup 1 sec latency 31.589 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 3456 2205184 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 3072 3708928 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3704832 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 6144 7413760 1% /mnt/lustre 1 405 7.17 MB/sec warmup 2 sec latency 30.050 ms 1 678 7.06 MB/sec warmup 3 sec latency 42.813 ms 1 923 5.44 MB/sec warmup 4 sec latency 32.594 ms test_26 fail mds1 1 times Failing mds1 on oleg451-server Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 1215 4.61 MB/sec warmup 5 sec latency 24.728 ms 02:30:16 (1738481416) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 1223 3.85 MB/sec warmup 6 sec latency 955.534 ms 1 1223 3.30 MB/sec warmup 7 sec latency 1955.777 ms 1 1223 2.88 MB/sec warmup 8 sec latency 2956.002 ms 1 1223 2.56 MB/sec warmup 9 sec latency 3956.247 ms 1 1223 2.31 MB/sec warmup 10 sec latency 4956.514 ms 1 1223 2.10 MB/sec warmup 11 sec latency 5956.774 ms 1 1223 1.92 MB/sec warmup 12 sec latency 6956.983 ms 1 1223 1.77 MB/sec warmup 13 sec latency 7957.203 ms 1 1223 1.65 MB/sec warmup 14 sec latency 8957.516 ms 1 1223 1.54 MB/sec warmup 15 sec latency 9957.753 ms Failover mds1 to oleg451-server mount facets: mds1 1 1223 1.44 MB/sec warmup 16 sec latency 10957.911 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1223 1.36 MB/sec warmup 17 sec latency 11958.139 ms 1 1223 1.28 MB/sec warmup 18 sec latency 12958.400 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 1 1223 1.21 MB/sec warmup 19 sec latency 13958.733 ms Started lustre-MDT0000 02:30:29 (1738481429) targets are mounted 02:30:29 (1738481429) facet_failover done 1 1223 0.00 MB/sec execute 1 sec latency 15959.147 ms 1 1223 0.00 MB/sec execute 2 sec latency 16959.480 ms 1 1223 0.00 MB/sec execute 3 sec latency 17959.697 ms 1 1223 0.00 MB/sec execute 4 sec latency 18959.849 ms 1 1223 0.00 MB/sec execute 5 sec latency 19960.024 ms 1 1262 0.01 MB/sec execute 6 sec latency 20749.345 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1556 0.43 MB/sec execute 7 sec latency 43.403 ms 1 1698 0.39 MB/sec execute 8 sec latency 47.337 ms 1 1954 0.37 MB/sec execute 9 sec latency 57.708 ms 1 2154 0.36 MB/sec execute 10 sec latency 22.187 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210304 4736 2203520 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 13312 3629056 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 40960 3568640 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 54272 7197696 1% /mnt/lustre 1 2400 0.45 MB/sec execute 11 sec latency 76.390 ms 1 2602 0.49 MB/sec execute 12 sec latency 49.338 ms 1 2979 0.80 MB/sec execute 13 sec latency 55.168 ms test_26 fail mds1 2 times 1 3515 1.09 MB/sec execute 14 sec latency 27.324 ms Failing mds1 on oleg451-server Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 3707 1.05 MB/sec execute 15 sec latency 323.363 ms 02:30:45 (1738481445) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 3707 0.98 MB/sec execute 16 sec latency 1323.582 ms 1 3707 0.92 MB/sec execute 17 sec latency 2323.852 ms 1 3707 0.87 MB/sec execute 18 sec latency 3324.103 ms 1 3707 0.83 MB/sec execute 19 sec latency 4324.298 ms 1 3707 0.79 MB/sec execute 20 sec latency 5324.524 ms 1 3707 0.75 MB/sec execute 21 sec latency 6324.793 ms 1 3707 0.71 MB/sec execute 22 sec latency 7324.995 ms 1 3707 0.68 MB/sec execute 23 sec latency 8325.250 ms 1 3707 0.65 MB/sec execute 24 sec latency 9325.513 ms 1 3707 0.63 MB/sec execute 25 sec latency 10325.754 ms Failover mds1 to oleg451-server mount facets: mds1 1 3707 0.60 MB/sec execute 26 sec latency 11325.961 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 3707 0.58 MB/sec execute 27 sec latency 12326.170 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all 1 3707 0.56 MB/sec execute 28 sec latency 13326.425 ms pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 Started lustre-MDT0000 02:30:59 (1738481459) targets are mounted 02:30:59 (1738481459) facet_failover done 1 3707 0.54 MB/sec execute 29 sec latency 14326.686 ms 1 3707 0.52 MB/sec execute 30 sec latency 15326.887 ms 1 3707 0.51 MB/sec execute 31 sec latency 16327.087 ms 1 3707 0.49 MB/sec execute 32 sec latency 17327.304 ms 1 3707 0.48 MB/sec execute 33 sec latency 18327.556 ms 1 3707 0.46 MB/sec execute 34 sec latency 19327.698 ms 1 3729 0.45 MB/sec execute 35 sec latency 20235.481 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3927 0.47 MB/sec execute 36 sec latency 21.559 ms 1 4076 0.46 MB/sec execute 37 sec latency 21.597 ms 1 4241 0.45 MB/sec execute 38 sec latency 101.384 ms 1 4391 0.45 MB/sec execute 39 sec latency 60.683 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 6016 2202496 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 16384 3534848 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 46080 3534848 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 62464 7069696 1% /mnt/lustre 1 4702 0.48 MB/sec execute 40 sec latency 28.324 ms 1 4996 0.54 MB/sec execute 41 sec latency 20.687 ms 1 5151 0.53 MB/sec execute 42 sec latency 59.586 ms test_26 fail mds1 3 times 1 5294 0.52 MB/sec execute 43 sec latency 53.072 ms Failing mds1 on oleg451-server Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 5449 0.51 MB/sec execute 44 sec latency 172.271 ms 02:31:15 (1738481475) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 5449 0.50 MB/sec execute 45 sec latency 1172.547 ms 1 5449 0.49 MB/sec execute 46 sec latency 2172.720 ms 1 5449 0.48 MB/sec execute 47 sec latency 3172.945 ms 1 5449 0.47 MB/sec execute 48 sec latency 4173.201 ms 1 5449 0.46 MB/sec execute 49 sec latency 5173.496 ms 1 5449 0.45 MB/sec execute 50 sec latency 6173.737 ms 1 5449 0.44 MB/sec execute 51 sec latency 7173.960 ms 1 5449 0.43 MB/sec execute 52 sec latency 8174.209 ms 1 5449 0.42 MB/sec execute 53 sec latency 9174.503 ms 1 5449 0.42 MB/sec execute 54 sec latency 10174.740 ms Failover mds1 to oleg451-server mount facets: mds1 1 5449 0.41 MB/sec execute 55 sec latency 11174.888 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 5449 0.40 MB/sec execute 56 sec latency 12175.053 ms 1 5449 0.39 MB/sec execute 57 sec latency 13175.294 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 Started lustre-MDT0000 02:31:28 (1738481488) targets are mounted 02:31:28 (1738481488) facet_failover done 1 5449 0.39 MB/sec execute 58 sec latency 14175.554 ms 1 5449 0.38 MB/sec execute 59 sec latency 15175.778 ms 1 5449 0.37 MB/sec execute 60 sec latency 16175.942 ms 1 5449 0.37 MB/sec execute 61 sec latency 17176.218 ms 1 5449 0.36 MB/sec execute 62 sec latency 18176.455 ms 1 5449 0.36 MB/sec execute 63 sec latency 19176.696 ms 1 5449 0.35 MB/sec execute 64 sec latency 20176.871 ms 1 5449 0.34 MB/sec execute 65 sec latency 21177.062 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 5583 0.34 MB/sec execute 66 sec latency 21548.208 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5902 0.36 MB/sec execute 67 sec latency 21.874 ms 1 6027 0.36 MB/sec execute 68 sec latency 75.788 ms 1 6436 0.41 MB/sec execute 69 sec latency 55.538 ms 1 6765 0.43 MB/sec execute 70 sec latency 49.541 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 7168 2201344 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 18432 3530752 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 49152 3517440 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 67584 7048192 1% /mnt/lustre 1 7114 0.49 MB/sec execute 71 sec latency 23.229 ms 1 7323 0.50 MB/sec execute 72 sec latency 30.517 ms 1 7488 0.49 MB/sec execute 73 sec latency 25.198 ms test_26 fail mds1 4 times Failing mds1 on oleg451-server 1 7657 0.49 MB/sec execute 74 sec latency 24.751 ms Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 7750 0.48 MB/sec execute 75 sec latency 575.936 ms 02:31:45 (1738481505) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 7750 0.48 MB/sec execute 76 sec latency 1576.175 ms 1 7750 0.47 MB/sec execute 77 sec latency 2576.464 ms 1 7750 0.46 MB/sec execute 78 sec latency 3576.651 ms 1 7750 0.46 MB/sec execute 79 sec latency 4576.841 ms 1 7750 0.45 MB/sec execute 80 sec latency 5577.056 ms 1 7750 0.45 MB/sec execute 81 sec latency 6577.384 ms 1 7750 0.44 MB/sec execute 82 sec latency 7577.675 ms 1 7750 0.44 MB/sec execute 83 sec latency 8577.925 ms 1 7750 0.43 MB/sec execute 84 sec latency 9578.127 ms 1 7750 0.43 MB/sec execute 85 sec latency 10578.337 ms Failover mds1 to oleg451-server mount facets: mds1 1 7750 0.42 MB/sec execute 86 sec latency 11578.600 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 7750 0.42 MB/sec execute 87 sec latency 12578.754 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 1 7750 0.41 MB/sec execute 88 sec latency 13578.869 ms Started lustre-MDT0000 02:31:58 (1738481518) targets are mounted 02:31:58 (1738481518) facet_failover done 1 7750 0.41 MB/sec execute 89 sec latency 14578.986 ms 1 7750 0.40 MB/sec execute 90 sec latency 15579.204 ms 1 7750 0.40 MB/sec execute 91 sec latency 16579.422 ms 1 7750 0.39 MB/sec execute 92 sec latency 17579.593 ms 1 7750 0.39 MB/sec execute 93 sec latency 18579.809 ms 1 7750 0.39 MB/sec execute 94 sec latency 19580.060 ms 1 7750 0.38 MB/sec execute 95 sec latency 20580.202 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 7919 0.38 MB/sec execute 96 sec latency 20748.414 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8133 0.39 MB/sec execute 97 sec latency 39.509 ms 1 8329 0.39 MB/sec execute 98 sec latency 29.187 ms 1 8590 0.42 MB/sec execute 99 sec latency 23.755 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 8576 2199936 1% /mnt/lustre[MDT:0] 1 cleanup 100 sec lustre-OST0000_UUID 3771392 18432 3381248 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 49152 3405824 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 67584 6787072 1% /mnt/lustre 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1313 11.968 43.393 Close 957 2.236 7.030 Rename 54 393.052 20235.457 Unlink 255 6.160 27.764 Qpathinfo 1199 3.743 34.474 Qfileinfo 210 0.586 2.652 Qfsinfo 209 0.692 3.412 Sfileinfo 107 398.511 20749.335 Find 454 1.740 16.833 WriteX 640 2.527 10.653 ReadX 2053 0.220 36.916 LockX 4 2.282 3.059 UnlockX 4 2.402 3.206 Flush 89 269.507 21548.190 Throughput 0.416145 MB/sec 1 clients 1 procs max_latency=21548.208 ms stopping dbench on /mnt/lustre at Sun Feb 2 02:32:11 EST 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Sun Feb 2 02:32:12 EST 2025 waiting for dbench pid 19218 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 0 of 1 processes prepared for launch 0 sec 1 of 1 processes prepared for launch 0 sec releasing clients test_26 fail mds1 5 times 1 208 8.10 MB/sec warmup 1 sec latency 32.930 ms Failing mds1 on oleg451-server Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 338 6.13 MB/sec warmup 2 sec latency 264.504 ms 02:32:15 (1738481535) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 338 4.09 MB/sec warmup 3 sec latency 1264.637 ms 1 338 3.07 MB/sec warmup 4 sec latency 2264.869 ms 1 338 2.45 MB/sec warmup 5 sec latency 3265.193 ms 1 338 2.04 MB/sec warmup 6 sec latency 4265.421 ms 1 338 1.75 MB/sec warmup 7 sec latency 5265.672 ms 1 338 1.53 MB/sec warmup 8 sec latency 6265.976 ms 1 338 1.36 MB/sec warmup 9 sec latency 7266.238 ms 1 338 1.23 MB/sec warmup 10 sec latency 8266.507 ms 1 338 1.11 MB/sec warmup 11 sec latency 9266.828 ms 1 338 1.02 MB/sec warmup 12 sec latency 10267.077 ms Failover mds1 to oleg451-server mount facets: mds1 1 338 0.94 MB/sec warmup 13 sec latency 11267.288 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 338 0.88 MB/sec warmup 14 sec latency 12267.494 ms 1 338 0.82 MB/sec warmup 15 sec latency 13267.712 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 1 338 0.77 MB/sec warmup 16 sec latency 14267.892 ms Started lustre-MDT0000 02:32:28 (1738481548) targets are mounted 02:32:28 (1738481548) facet_failover done 1 338 0.72 MB/sec warmup 17 sec latency 15268.138 ms 1 338 0.68 MB/sec warmup 18 sec latency 16268.356 ms 1 338 0.65 MB/sec warmup 19 sec latency 17268.668 ms 1 338 0.00 MB/sec execute 1 sec latency 19269.025 ms 1 338 0.00 MB/sec execute 2 sec latency 20269.225 ms 1 429 0.95 MB/sec execute 3 sec latency 20773.281 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 708 2.23 MB/sec execute 4 sec latency 57.043 ms 1 816 1.84 MB/sec execute 5 sec latency 63.231 ms 1 990 1.61 MB/sec execute 6 sec latency 44.281 ms 1 1190 1.54 MB/sec execute 7 sec latency 28.402 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 9600 2198912 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 38912 3415040 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 22528 3444736 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 61440 6859776 1% /mnt/lustre 1 1451 1.72 MB/sec execute 8 sec latency 27.194 ms 1 1646 1.55 MB/sec execute 9 sec latency 66.109 ms 1 1865 1.41 MB/sec execute 10 sec latency 29.844 ms test_26 fail mds1 6 times Failing mds1 on oleg451-server 1 2135 1.31 MB/sec execute 11 sec latency 54.447 ms Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 2225 1.21 MB/sec execute 12 sec latency 408.342 ms 02:32:45 (1738481565) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 2225 1.12 MB/sec execute 13 sec latency 1408.590 ms 1 2225 1.04 MB/sec execute 14 sec latency 2408.855 ms 1 2225 0.97 MB/sec execute 15 sec latency 3409.149 ms 1 2225 0.91 MB/sec execute 16 sec latency 4409.417 ms 1 2225 0.85 MB/sec execute 17 sec latency 5409.747 ms 1 2225 0.81 MB/sec execute 18 sec latency 6410.031 ms 1 2225 0.76 MB/sec execute 19 sec latency 7410.295 ms 1 2225 0.73 MB/sec execute 20 sec latency 8410.551 ms 1 2225 0.69 MB/sec execute 21 sec latency 9410.843 ms 1 2225 0.66 MB/sec execute 22 sec latency 10411.102 ms Failover mds1 to oleg451-server mount facets: mds1 1 2225 0.63 MB/sec execute 23 sec latency 11411.359 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2225 0.60 MB/sec execute 24 sec latency 12411.593 ms 1 2225 0.58 MB/sec execute 25 sec latency 13411.833 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 Started lustre-MDT0000 02:32:58 (1738481578) targets are mounted 02:32:58 (1738481578) facet_failover done 1 2225 0.56 MB/sec execute 26 sec latency 14412.131 ms 1 2225 0.54 MB/sec execute 27 sec latency 15412.322 ms 1 2225 0.52 MB/sec execute 28 sec latency 16412.539 ms 1 2225 0.50 MB/sec execute 29 sec latency 17412.810 ms 1 2225 0.48 MB/sec execute 30 sec latency 18413.063 ms 1 2225 0.47 MB/sec execute 31 sec latency 19413.271 ms 1 2298 0.48 MB/sec execute 32 sec latency 20192.184 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2496 0.50 MB/sec execute 33 sec latency 49.219 ms 1 2903 0.60 MB/sec execute 34 sec latency 46.607 ms 1 3197 0.63 MB/sec execute 35 sec latency 52.745 ms 1 3523 0.72 MB/sec execute 36 sec latency 60.503 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 10624 2197888 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 47104 3557376 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 37888 3566592 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 84992 7123968 2% /mnt/lustre 1 3697 0.72 MB/sec execute 37 sec latency 22.158 ms 1 3917 0.73 MB/sec execute 38 sec latency 18.403 ms 1 4061 0.71 MB/sec execute 39 sec latency 24.023 ms test_26 fail mds1 7 times 1 4281 0.70 MB/sec execute 40 sec latency 44.309 ms Failing mds1 on oleg451-server Stopping /mnt/lustre-mds1 (opts:) on oleg451-server 1 4421 0.69 MB/sec execute 41 sec latency 363.295 ms 02:33:14 (1738481594) shut down facet: mds1 facet_host: oleg451-server facet_failover_host: oleg451-server 1 4421 0.68 MB/sec execute 42 sec latency 1363.503 ms 1 4421 0.66 MB/sec execute 43 sec latency 2363.733 ms 1 4421 0.65 MB/sec execute 44 sec latency 3364.027 ms 1 4421 0.63 MB/sec execute 45 sec latency 4364.227 ms 1 4421 0.62 MB/sec execute 46 sec latency 5364.374 ms 1 4421 0.60 MB/sec execute 47 sec latency 6364.544 ms 1 4421 0.59 MB/sec execute 48 sec latency 7364.764 ms 1 4421 0.58 MB/sec execute 49 sec latency 8365.014 ms 1 4421 0.57 MB/sec execute 50 sec latency 9365.282 ms 1 4421 0.56 MB/sec execute 51 sec latency 10365.485 ms Failover mds1 to oleg451-server mount facets: mds1 1 4421 0.55 MB/sec execute 52 sec latency 11365.682 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 4421 0.54 MB/sec execute 53 sec latency 12365.945 ms 1 4421 0.53 MB/sec execute 54 sec latency 13366.183 ms oleg451-server: oleg451-server.virtnet: executing set_default_debug -1 all pdsh@oleg451-client: oleg451-server: ssh exited with exit code 1 Started lustre-MDT0000 02:33:27 (1738481607) targets are mounted 02:33:27 (1738481607) facet_failover done 1 4421 0.52 MB/sec execute 55 sec latency 14366.339 ms 1 4421 0.51 MB/sec execute 56 sec latency 15366.442 ms 1 4421 0.50 MB/sec execute 57 sec latency 16366.699 ms 1 4421 0.49 MB/sec execute 58 sec latency 17366.936 ms 1 4421 0.48 MB/sec execute 59 sec latency 18367.144 ms 1 4421 0.47 MB/sec execute 60 sec latency 19367.334 ms 1 4421 0.47 MB/sec execute 61 sec latency 20367.459 ms 1 4421 0.46 MB/sec execute 62 sec latency 21367.599 ms oleg451-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4695 0.47 MB/sec execute 63 sec latency 21402.580 ms 1 5025 0.51 MB/sec execute 64 sec latency 22.279 ms kill: sending signal to 14976 failed: No such process dbench killed by signal 15 stopping dbench on /mnt/lustre at Sun Feb 2 02:33:37 EST 2025 with return code 0 1 5227 0.51 MB/sec execute 65 sec latency 80.565 ms 19218 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 19218 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished