== replay-dual test 26: dbench and tar with mds failover ========================================================== 13:24:25 (1761240265) Starting client oleg427-client.virtnet: -o user_xattr,flock 192.168.204.127@tcp:/lustre /mnt/lustre Started clients oleg427-client.virtnet: 192.168.204.127@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,encrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 44632 Started dbench loop with 44634 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 Thu Oct 23 13:24:28 EDT 2025 waiting for dbench pid 44670 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 1 of 1 processes prepared for launch 0 sec releasing clients UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3328 2205184 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 27648 3729408 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3750912 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 30720 7480320 1% /mnt/lustre 1 55 2.14 MB/sec warmup 1 sec latency 100.495 ms 1 115 2.60 MB/sec warmup 2 sec latency 126.165 ms 1 149 2.08 MB/sec warmup 3 sec latency 141.379 ms 1 186 1.85 MB/sec warmup 4 sec latency 131.656 ms 1 231 1.77 MB/sec warmup 5 sec latency 105.070 ms test_26 fail mds1 1 times 1 278 1.73 MB/sec warmup 6 sec latency 125.919 ms Failing mds1 on oleg427-server 1 315 1.64 MB/sec warmup 7 sec latency 135.576 ms Stopping /mnt/lustre-mds1 (opts:) on oleg427-server 1 357 1.59 MB/sec warmup 8 sec latency 123.174 ms 1 389 1.53 MB/sec warmup 9 sec latency 470.772 ms 1 389 1.38 MB/sec warmup 10 sec latency 1473.326 ms 13:24:39 (1761240279) shut down facet: mds1 facet_host: oleg427-server facet_failover_host: oleg427-server 1 389 1.25 MB/sec warmup 11 sec latency 2473.670 ms 1 389 1.15 MB/sec warmup 12 sec latency 3474.508 ms 1 389 1.06 MB/sec warmup 13 sec latency 4475.907 ms 1 389 0.99 MB/sec warmup 14 sec latency 5476.168 ms 1 389 0.92 MB/sec warmup 15 sec latency 6477.859 ms 1 389 0.86 MB/sec warmup 16 sec latency 7478.893 ms 1 389 0.81 MB/sec warmup 17 sec latency 8479.084 ms 1 389 0.77 MB/sec warmup 18 sec latency 9479.922 ms 1 389 0.73 MB/sec warmup 19 sec latency 10480.853 ms Failover mds1 to oleg427-server mount facets: mds1 1 389 0.00 MB/sec execute 1 sec latency 12481.811 ms 1 389 0.00 MB/sec execute 2 sec latency 13482.708 ms 1 389 0.00 MB/sec execute 3 sec latency 14483.563 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 389 0.00 MB/sec execute 4 sec latency 15484.280 ms 1 389 0.00 MB/sec execute 5 sec latency 16485.087 ms 1 389 0.00 MB/sec execute 6 sec latency 17486.992 ms 1 389 0.00 MB/sec execute 7 sec latency 18487.265 ms 1 389 0.00 MB/sec execute 8 sec latency 19487.974 ms oleg427-server: oleg427-server.virtnet: executing set_default_debug -1 all pdsh@oleg427-client: oleg427-server: ssh exited with exit code 1 1 389 0.00 MB/sec execute 9 sec latency 20488.187 ms Started lustre-MDT0000 13:24:58 (1761240298) targets are mounted 13:24:58 (1761240298) facet_failover done 1 389 0.00 MB/sec execute 10 sec latency 21488.556 ms 1 389 0.00 MB/sec execute 11 sec latency 22488.723 ms 1 426 0.10 MB/sec execute 12 sec latency 22893.068 ms oleg427-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 485 0.24 MB/sec execute 13 sec latency 82.797 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 575 0.40 MB/sec execute 14 sec latency 101.651 ms 1 663 0.49 MB/sec execute 15 sec latency 72.935 ms 1 695 0.46 MB/sec execute 16 sec latency 295.243 ms 1 738 0.44 MB/sec execute 17 sec latency 131.080 ms 1 798 0.42 MB/sec execute 18 sec latency 108.762 ms 1 869 0.41 MB/sec execute 19 sec latency 63.653 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3584 2204928 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 37888 3668992 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 12288 3720192 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 50176 7389184 1% /mnt/lustre 1 902 0.39 MB/sec execute 20 sec latency 168.079 ms 1 933 0.38 MB/sec execute 21 sec latency 225.733 ms 1 980 0.37 MB/sec execute 22 sec latency 90.466 ms 1 1062 0.39 MB/sec execute 23 sec latency 125.949 ms 1 1145 0.38 MB/sec execute 24 sec latency 57.905 ms test_26 fail mds1 2 times 1 1196 0.37 MB/sec execute 25 sec latency 71.623 ms Failing mds1 on oleg427-server 1 1242 0.36 MB/sec execute 26 sec latency 77.869 ms Stopping /mnt/lustre-mds1 (opts:) on oleg427-server 1 1383 0.45 MB/sec execute 27 sec latency 66.666 ms 1 1393 0.43 MB/sec execute 28 sec latency 803.564 ms 1 1393 0.42 MB/sec execute 29 sec latency 1804.023 ms 13:25:18 (1761240318) shut down facet: mds1 facet_host: oleg427-server facet_failover_host: oleg427-server 1 1393 0.41 MB/sec execute 30 sec latency 2804.354 ms 1 1393 0.39 MB/sec execute 31 sec latency 3804.657 ms 1 1393 0.38 MB/sec execute 32 sec latency 4804.866 ms 1 1393 0.37 MB/sec execute 33 sec latency 5805.308 ms 1 1393 0.36 MB/sec execute 34 sec latency 6805.470 ms 1 1393 0.35 MB/sec execute 35 sec latency 7805.669 ms 1 1393 0.34 MB/sec execute 36 sec latency 8806.887 ms 1 1393 0.33 MB/sec execute 37 sec latency 9807.093 ms 1 1393 0.32 MB/sec execute 38 sec latency 10807.466 ms 1 1393 0.31 MB/sec execute 39 sec latency 11807.664 ms Failover mds1 to oleg427-server mount facets: mds1 1 1393 0.30 MB/sec execute 40 sec latency 12807.913 ms 1 1393 0.30 MB/sec execute 41 sec latency 13808.138 ms 1 1393 0.29 MB/sec execute 42 sec latency 14808.370 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1393 0.28 MB/sec execute 43 sec latency 15808.624 ms 1 1393 0.28 MB/sec execute 44 sec latency 16808.771 ms 1 1393 0.27 MB/sec execute 45 sec latency 17813.370 ms 1 1393 0.26 MB/sec execute 46 sec latency 18817.735 ms oleg427-server: oleg427-server.virtnet: executing set_default_debug -1 all 1 1393 0.26 MB/sec execute 47 sec latency 19820.129 ms pdsh@oleg427-client: oleg427-server: ssh exited with exit code 1 1 1393 0.25 MB/sec execute 48 sec latency 20820.284 ms Started lustre-MDT0000 13:25:37 (1761240337) targets are mounted 13:25:37 (1761240337) facet_failover done 1 1426 0.25 MB/sec execute 49 sec latency 21311.992 ms 1 1489 0.24 MB/sec execute 50 sec latency 162.255 ms 1 1548 0.24 MB/sec execute 51 sec latency 79.342 ms oleg427-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1605 0.24 MB/sec execute 52 sec latency 77.385 ms 1 1643 0.23 MB/sec execute 53 sec latency 278.976 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1684 0.23 MB/sec execute 54 sec latency 112.096 ms 1 1738 0.23 MB/sec execute 55 sec latency 87.180 ms 1 1814 0.22 MB/sec execute 56 sec latency 78.267 ms 1 1871 0.22 MB/sec execute 57 sec latency 76.271 ms 1 1938 0.22 MB/sec execute 58 sec latency 234.403 ms 1 2002 0.21 MB/sec execute 59 sec latency 102.123 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4224 2204288 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 59392 3664896 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 15360 3703808 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 74752 7368704 2% /mnt/lustre 1 2051 0.21 MB/sec execute 60 sec latency 79.585 ms 1 2119 0.21 MB/sec execute 61 sec latency 112.084 ms 1 2166 0.21 MB/sec execute 62 sec latency 103.934 ms 1 2239 0.21 MB/sec execute 63 sec latency 78.715 ms 1 2345 0.22 MB/sec execute 64 sec latency 181.933 ms test_26 fail mds1 3 times 1 2389 0.22 MB/sec execute 65 sec latency 207.324 ms Failing mds1 on oleg427-server 1 2440 0.22 MB/sec execute 66 sec latency 129.214 ms Stopping /mnt/lustre-mds1 (opts:) on oleg427-server 1 2499 0.22 MB/sec execute 67 sec latency 127.317 ms 1 2499 0.22 MB/sec execute 68 sec latency 1128.166 ms 13:25:57 (1761240357) shut down facet: mds1 facet_host: oleg427-server facet_failover_host: oleg427-server 1 2499 0.22 MB/sec execute 69 sec latency 2129.056 ms 1 2499 0.21 MB/sec execute 70 sec latency 3129.283 ms 1 2499 0.21 MB/sec execute 71 sec latency 4129.507 ms 1 2499 0.21 MB/sec execute 72 sec latency 5129.783 ms 1 2499 0.20 MB/sec execute 73 sec latency 6131.654 ms 1 2499 0.20 MB/sec execute 74 sec latency 7131.857 ms 1 2499 0.20 MB/sec execute 75 sec latency 8132.174 ms 1 2499 0.20 MB/sec execute 76 sec latency 9132.883 ms 1 2499 0.19 MB/sec execute 77 sec latency 10135.320 ms 1 2499 0.19 MB/sec execute 78 sec latency 11135.569 ms Failover mds1 to oleg427-server mount facets: mds1 1 2499 0.19 MB/sec execute 79 sec latency 12135.739 ms 1 2499 0.19 MB/sec execute 80 sec latency 13135.948 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2499 0.18 MB/sec execute 81 sec latency 14136.129 ms 1 2499 0.18 MB/sec execute 82 sec latency 15140.497 ms 1 2499 0.18 MB/sec execute 83 sec latency 16141.564 ms 1 2499 0.18 MB/sec execute 84 sec latency 17150.407 ms 1 2499 0.18 MB/sec execute 85 sec latency 18151.610 ms oleg427-server: oleg427-server.virtnet: executing set_default_debug -1 all pdsh@oleg427-client: oleg427-server: ssh exited with exit code 1 1 2499 0.17 MB/sec execute 86 sec latency 19151.842 ms Started lustre-MDT0000 13:26:15 (1761240375) targets are mounted 13:26:15 (1761240375) facet_failover done 1 2499 0.17 MB/sec execute 87 sec latency 20152.103 ms 1 2499 0.17 MB/sec execute 88 sec latency 21152.446 ms 1 2506 0.17 MB/sec execute 89 sec latency 22026.928 ms 1 2566 0.17 MB/sec execute 90 sec latency 763.277 ms oleg427-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 2618 0.17 MB/sec execute 91 sec latency 825.568 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2773 0.20 MB/sec execute 92 sec latency 222.926 ms 1 2906 0.20 MB/sec execute 93 sec latency 74.090 ms 1 2982 0.21 MB/sec execute 94 sec latency 206.151 ms 1 3019 0.21 MB/sec execute 95 sec latency 188.196 ms 1 3209 0.21 MB/sec execute 96 sec latency 155.828 ms 1 3278 0.22 MB/sec execute 97 sec latency 133.189 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4864 2203648 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 62464 3633152 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 17408 3681280 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 79872 7314432 2% /mnt/lustre 1 3361 0.22 MB/sec execute 98 sec latency 132.881 ms 1 3499 0.25 MB/sec execute 99 sec latency 81.048 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec test_26 fail mds1 4 times 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 460 91.855 22893.053 Close 387 9.618 29.933 Rename 22 65.297 132.791 Unlink 57 20.839 74.068 Qpathinfo 437 112.480 22026.907 Qfileinfo 123 1.250 10.346 Qfsinfo 83 1.903 14.959 Sfileinfo 50 43.555 77.838 Find 186 5.380 34.637 WriteX 410 8.340 49.386 ReadX 906 1.106 53.453 LockX 2 8.661 8.929 UnlockX 2 10.062 12.752 Flush 43 116.992 295.226 Throughput 0.247389 MB/sec 1 clients 1 procs max_latency=22893.068 ms stopping dbench on /mnt/lustre at Thu Oct 23 13:26:31 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished Failing mds1 on oleg427-server Stopping /mnt/lustre-mds1 (opts:) on oleg427-server looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt 13:26:36 (1761240396) shut down facet: mds1 facet_host: oleg427-server facet_failover_host: oleg427-server Failover mds1 to oleg427-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg427-server: oleg427-server.virtnet: executing set_default_debug -1 all pdsh@oleg427-client: oleg427-server: ssh exited with exit code 1 Started lustre-MDT0000 13:26:55 (1761240415) targets are mounted 13:26:55 (1761240415) facet_failover done '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Thu Oct 23 13:26:58 EDT 2025 waiting for dbench pid 48171 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 oleg427-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 43 1.63 MB/sec warmup 1 sec latency 136.097 ms 1 82 1.82 MB/sec warmup 2 sec latency 235.005 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 125 1.84 MB/sec warmup 3 sec latency 130.378 ms 1 157 1.63 MB/sec warmup 4 sec latency 145.174 ms 1 200 1.56 MB/sec warmup 5 sec latency 116.822 ms 1 244 1.54 MB/sec warmup 6 sec latency 114.575 ms 1 287 1.52 MB/sec warmup 7 sec latency 131.433 ms 1 315 1.43 MB/sec warmup 8 sec latency 142.537 ms 1 341 1.36 MB/sec warmup 9 sec latency 169.684 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 5376 2203136 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 53248 3668992 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 13312 3732480 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 66560 7401472 1% /mnt/lustre 1 365 1.30 MB/sec warmup 10 sec latency 298.322 ms 1 405 1.30 MB/sec warmup 11 sec latency 97.512 ms 1 445 1.30 MB/sec warmup 12 sec latency 146.558 ms 1 478 1.28 MB/sec warmup 13 sec latency 140.664 ms 1 511 1.26 MB/sec warmup 14 sec latency 155.867 ms 1 582 1.32 MB/sec warmup 15 sec latency 209.486 ms 1 654 1.31 MB/sec warmup 16 sec latency 127.237 ms test_26 fail mds1 5 times 1 676 1.24 MB/sec warmup 17 sec latency 260.749 ms Failing mds1 on oleg427-server 1 711 1.17 MB/sec warmup 18 sec latency 168.427 ms 1 731 1.12 MB/sec warmup 19 sec latency 233.323 ms Stopping /mnt/lustre-mds1 (opts:) on oleg427-server 1 778 0.00 MB/sec execute 1 sec latency 832.441 ms 1 778 0.00 MB/sec execute 2 sec latency 1832.752 ms 1 778 0.00 MB/sec execute 3 sec latency 2833.036 ms 13:27:22 (1761240442) shut down facet: mds1 facet_host: oleg427-server facet_failover_host: oleg427-server 1 778 0.00 MB/sec execute 4 sec latency 3833.360 ms 1 778 0.00 MB/sec execute 5 sec latency 4833.627 ms 1 778 0.00 MB/sec execute 6 sec latency 5833.926 ms 1 778 0.00 MB/sec execute 7 sec latency 6834.157 ms 1 778 0.00 MB/sec execute 8 sec latency 7834.440 ms 1 778 0.00 MB/sec execute 9 sec latency 8834.728 ms 1 778 0.00 MB/sec execute 10 sec latency 9838.740 ms 1 778 0.00 MB/sec execute 11 sec latency 10839.620 ms 1 778 0.00 MB/sec execute 12 sec latency 11839.910 ms 1 778 0.00 MB/sec execute 13 sec latency 12840.185 ms Failover mds1 to oleg427-server mount facets: mds1 1 778 0.00 MB/sec execute 14 sec latency 13842.253 ms 1 778 0.00 MB/sec execute 15 sec latency 14843.455 ms 1 778 0.00 MB/sec execute 16 sec latency 15845.675 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 778 0.00 MB/sec execute 17 sec latency 16845.905 ms 1 778 0.00 MB/sec execute 18 sec latency 17846.828 ms 1 778 0.00 MB/sec execute 19 sec latency 18848.319 ms 1 778 0.00 MB/sec execute 20 sec latency 19850.527 ms oleg427-server: oleg427-server.virtnet: executing set_default_debug -1 all 1 778 0.00 MB/sec execute 21 sec latency 20850.822 ms pdsh@oleg427-client: oleg427-server: ssh exited with exit code 1 1 778 0.00 MB/sec execute 22 sec latency 21851.043 ms Started lustre-MDT0000 13:27:41 (1761240461) targets are mounted 13:27:41 (1761240461) facet_failover done 1 789 0.00 MB/sec execute 23 sec latency 22507.778 ms 1 825 0.01 MB/sec execute 24 sec latency 128.120 ms 1 878 0.01 MB/sec execute 25 sec latency 251.509 ms 1 914 0.02 MB/sec execute 26 sec latency 243.532 ms oleg427-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 957 0.02 MB/sec execute 27 sec latency 83.319 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 980 0.02 MB/sec execute 28 sec latency 223.622 ms 1 1002 0.02 MB/sec execute 29 sec latency 309.072 ms 1 1061 0.05 MB/sec execute 30 sec latency 174.956 ms 1 1127 0.05 MB/sec execute 31 sec latency 65.223 ms 1 1173 0.05 MB/sec execute 32 sec latency 91.677 ms 1 1230 0.05 MB/sec execute 33 sec latency 64.646 ms 1 1274 0.05 MB/sec execute 34 sec latency 114.078 ms 1 1410 0.13 MB/sec execute 35 sec latency 78.258 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1468 0.13 MB/sec execute 36 sec latency 86.911 ms 1 1515 0.13 MB/sec execute 37 sec latency 185.215 ms 1 1580 0.13 MB/sec execute 38 sec latency 79.388 ms 1 1632 0.12 MB/sec execute 39 sec latency 103.243 ms 1 1662 0.12 MB/sec execute 40 sec latency 269.566 ms 1 1713 0.12 MB/sec execute 41 sec latency 94.622 ms 1 1785 0.12 MB/sec execute 42 sec latency 92.185 ms 1 1848 0.12 MB/sec execute 43 sec latency 107.486 ms 1 1888 0.11 MB/sec execute 44 sec latency 319.759 ms 1 1974 0.11 MB/sec execute 45 sec latency 93.416 ms 1 2014 0.11 MB/sec execute 46 sec latency 86.595 ms 1 2083 0.11 MB/sec execute 47 sec latency 87.033 ms 1 2152 0.11 MB/sec execute 48 sec latency 93.132 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Oct 23 13:28:07 EDT 2025 with return code 0 48171 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48171 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished