== replay-dual test 26: dbench and tar with mds failover ========================================================== 05:55:27 (1787824527) Starting client oleg439-client.virtnet: -o user_xattr,flock 192.168.204.139@tcp:/lustre /mnt/lustre Started clients oleg439-client.virtnet: 192.168.204.139@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65671 Started dbench loop with 65673 striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d26.replay-dual/run_tar looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1956 1269348 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1788 1269516 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 5640 3597204 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 7204 7202660 1% /mnt/lustre '/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 Aug 27 05:55:35 EDT 2026 waiting for dbench pid 65762 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 0 8 0.00 MB/sec warmup 1 sec latency 89.071 ms 1 50 1.05 MB/sec warmup 2 sec latency 173.075 ms 1 90 1.40 MB/sec warmup 3 sec latency 157.174 ms 1 117 1.33 MB/sec warmup 4 sec latency 198.325 ms 1 155 1.31 MB/sec warmup 5 sec latency 120.082 ms 1 181 1.22 MB/sec warmup 6 sec latency 177.930 ms 1 193 1.09 MB/sec warmup 7 sec latency 701.421 ms 1 223 1.08 MB/sec warmup 8 sec latency 133.729 ms test_26 fail mds1 1 times 1 248 1.04 MB/sec warmup 9 sec latency 148.144 ms 1 279 1.04 MB/sec warmup 10 sec latency 188.038 ms 1 306 1.02 MB/sec warmup 11 sec latency 217.546 ms Failing mds1 on oleg439-server 1 331 1.00 MB/sec warmup 12 sec latency 213.623 ms Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 1 365 1.00 MB/sec warmup 13 sec latency 128.747 ms 1 380 0.97 MB/sec warmup 14 sec latency 641.044 ms 1 380 0.90 MB/sec warmup 15 sec latency 1642.510 ms 05:55:51 (1787824551) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server 1 380 0.85 MB/sec warmup 16 sec latency 2646.830 ms 1 380 0.80 MB/sec warmup 17 sec latency 3647.045 ms 1 380 0.75 MB/sec warmup 18 sec latency 4647.368 ms 1 380 0.71 MB/sec warmup 19 sec latency 5647.685 ms 1 380 0.00 MB/sec execute 1 sec latency 7648.697 ms 1 380 0.00 MB/sec execute 2 sec latency 8649.682 ms 1 380 0.00 MB/sec execute 3 sec latency 9650.150 ms 1 380 0.00 MB/sec execute 4 sec latency 10650.387 ms 1 380 0.00 MB/sec execute 5 sec latency 11650.865 ms 1 380 0.00 MB/sec execute 6 sec latency 12651.070 ms Failover mds1 to oleg439-server mount facets: mds1 1 380 0.00 MB/sec execute 7 sec latency 13651.282 ms 1 380 0.00 MB/sec execute 8 sec latency 14651.558 ms 1 380 0.00 MB/sec execute 9 sec latency 15651.870 ms 1 380 0.00 MB/sec execute 10 sec latency 16654.923 ms 1 380 0.00 MB/sec execute 11 sec latency 17655.174 ms 1 380 0.00 MB/sec execute 12 sec latency 18655.389 ms 1 380 0.00 MB/sec execute 13 sec latency 19656.032 ms 1 380 0.00 MB/sec execute 14 sec latency 20656.271 ms 1 380 0.00 MB/sec execute 15 sec latency 21660.310 ms 1 380 0.00 MB/sec execute 16 sec latency 22660.502 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 380 0.00 MB/sec execute 17 sec latency 23660.741 ms 1 380 0.00 MB/sec execute 18 sec latency 24661.067 ms 1 380 0.00 MB/sec execute 19 sec latency 25661.307 ms 1 380 0.00 MB/sec execute 20 sec latency 26662.438 ms 1 380 0.00 MB/sec execute 21 sec latency 27662.869 ms 1 380 0.00 MB/sec execute 22 sec latency 28663.287 ms 1 380 0.00 MB/sec execute 23 sec latency 29663.987 ms 1 380 0.00 MB/sec execute 24 sec latency 30664.552 ms 1 380 0.00 MB/sec execute 25 sec latency 31664.767 ms 1 380 0.00 MB/sec execute 26 sec latency 32666.046 ms 1 380 0.00 MB/sec execute 27 sec latency 33667.972 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all 1 380 0.00 MB/sec execute 28 sec latency 34668.174 ms pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 1 380 0.00 MB/sec execute 29 sec latency 35668.369 ms Started lustre-MDT0000 05:56:25 (1787824585) targets are mounted 05:56:25 (1787824585) facet_failover done 1 402 0.02 MB/sec execute 30 sec latency 35998.877 ms 1 445 0.07 MB/sec execute 31 sec latency 99.111 ms 1 473 0.09 MB/sec execute 32 sec latency 160.918 ms 1 506 0.12 MB/sec execute 33 sec latency 142.598 ms 1 552 0.16 MB/sec execute 34 sec latency 111.373 ms 1 577 0.17 MB/sec execute 35 sec latency 856.380 ms 1 638 0.21 MB/sec execute 36 sec latency 137.187 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 674 0.21 MB/sec execute 37 sec latency 109.228 ms 1 711 0.20 MB/sec execute 38 sec latency 136.322 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 735 0.20 MB/sec execute 39 sec latency 143.951 ms 1 765 0.19 MB/sec execute 40 sec latency 145.168 ms 1 789 0.19 MB/sec execute 41 sec latency 170.014 ms 1 817 0.19 MB/sec execute 42 sec latency 119.096 ms 1 867 0.19 MB/sec execute 43 sec latency 122.606 ms 1 892 0.18 MB/sec execute 44 sec latency 134.578 ms 1 921 0.18 MB/sec execute 45 sec latency 134.051 ms 1 957 0.18 MB/sec execute 46 sec latency 92.185 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2156 1269148 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1940 1269364 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 18364 3583840 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 33024 3569824 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 51388 7153664 1% /mnt/lustre 1 983 0.18 MB/sec execute 47 sec latency 138.317 ms 1 1041 0.19 MB/sec execute 48 sec latency 107.999 ms 1 1084 0.19 MB/sec execute 49 sec latency 85.550 ms 1 1131 0.19 MB/sec execute 50 sec latency 86.139 ms 1 1163 0.18 MB/sec execute 51 sec latency 129.037 ms 1 1172 0.18 MB/sec execute 52 sec latency 831.132 ms 1 1185 0.18 MB/sec execute 53 sec latency 1198.873 ms 1 1224 0.18 MB/sec execute 54 sec latency 135.732 ms 1 1264 0.17 MB/sec execute 55 sec latency 109.143 ms 1 1396 0.22 MB/sec execute 56 sec latency 87.539 ms test_26 fail mds2 2 times 1 1426 0.22 MB/sec execute 57 sec latency 124.335 ms 1 1473 0.21 MB/sec execute 58 sec latency 99.278 ms Failing mds2 on oleg439-server 1 1499 0.21 MB/sec execute 59 sec latency 148.135 ms 1 1540 0.21 MB/sec execute 60 sec latency 159.713 ms Stopping /mnt/lustre-mds2 (opts:) on oleg439-server 1 1593 0.21 MB/sec execute 61 sec latency 71.618 ms 1 1632 0.20 MB/sec execute 62 sec latency 152.839 ms 1 1677 0.20 MB/sec execute 63 sec latency 153.918 ms 05:56:59 (1787824619) shut down facet: mds2 facet_host: oleg439-server facet_failover_host: oleg439-server 1 1721 0.20 MB/sec execute 64 sec latency 121.188 ms 1 1805 0.20 MB/sec execute 65 sec latency 91.065 ms 1 1866 0.19 MB/sec execute 66 sec latency 80.009 ms 1 1961 0.19 MB/sec execute 67 sec latency 58.460 ms 1 2010 0.19 MB/sec execute 68 sec latency 94.018 ms 1 2083 0.19 MB/sec execute 69 sec latency 101.364 ms 1 2158 0.19 MB/sec execute 70 sec latency 68.436 ms 1 2235 0.19 MB/sec execute 71 sec latency 73.002 ms 1 2259 0.18 MB/sec execute 72 sec latency 761.156 ms 1 2259 0.18 MB/sec execute 73 sec latency 1765.721 ms Failover mds2 to oleg439-server 1 2259 0.18 MB/sec execute 74 sec latency 2765.954 ms mount facets: mds2 1 2259 0.18 MB/sec execute 75 sec latency 3766.180 ms 1 2259 0.17 MB/sec execute 76 sec latency 4769.850 ms 1 2259 0.17 MB/sec execute 77 sec latency 5770.372 ms 1 2259 0.17 MB/sec execute 78 sec latency 6772.458 ms 1 2259 0.17 MB/sec execute 79 sec latency 7772.688 ms 1 2259 0.16 MB/sec execute 80 sec latency 8773.012 ms 1 2259 0.16 MB/sec execute 81 sec latency 9773.571 ms 1 2259 0.16 MB/sec execute 82 sec latency 10773.804 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.16 MB/sec execute 83 sec latency 11774.097 ms 1 2259 0.16 MB/sec execute 84 sec latency 12774.378 ms 1 2259 0.16 MB/sec execute 85 sec latency 13775.242 ms 1 2259 0.15 MB/sec execute 86 sec latency 14775.469 ms 1 2259 0.15 MB/sec execute 87 sec latency 15776.170 ms 1 2259 0.15 MB/sec execute 88 sec latency 16776.998 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all 1 2259 0.15 MB/sec execute 89 sec latency 17780.363 ms pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 1 2259 0.15 MB/sec execute 90 sec latency 18789.682 ms Started lustre-MDT0001 05:57:26 (1787824646) targets are mounted 05:57:26 (1787824646) facet_failover done 1 2259 0.15 MB/sec execute 91 sec latency 19791.348 ms 1 2298 0.15 MB/sec execute 92 sec latency 20299.867 ms 1 2353 0.15 MB/sec execute 93 sec latency 94.605 ms 1 2388 0.15 MB/sec execute 94 sec latency 106.195 ms 1 2418 0.15 MB/sec execute 95 sec latency 151.443 ms 1 2454 0.15 MB/sec execute 96 sec latency 145.150 ms 1 2489 0.16 MB/sec execute 97 sec latency 114.060 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2571 0.16 MB/sec execute 98 sec latency 109.155 ms 1 2607 0.16 MB/sec execute 99 sec latency 105.059 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 384 108.019 20299.846 Close 331 121.675 35998.803 Rename 17 103.521 151.409 Unlink 41 30.145 61.869 Qpathinfo 356 16.471 90.609 Qfileinfo 101 2.316 18.652 Qfsinfo 52 4.040 20.686 Sfileinfo 50 67.660 143.937 Find 126 13.602 76.031 WriteX 350 15.451 79.768 ReadX 540 1.844 107.967 Flush 34 63.788 153.899 Throughput 0.155707 MB/sec 1 clients 1 procs max_latency=35998.877 ms stopping dbench on /mnt/lustre at Thu Aug 27 05:57:40 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2376 1268928 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2128 1269176 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 27216 3579004 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 31092 3575428 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58308 7154432 1% /mnt/lustre striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench 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 Aug 27 05:57:50 EDT 2026 waiting for dbench pid 67965 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 1 20 0.39 MB/sec warmup 1 sec latency 23.837 ms 1 99 2.26 MB/sec warmup 2 sec latency 80.285 ms test_26 fail mds1 3 times 1 137 2.01 MB/sec warmup 3 sec latency 168.554 ms 1 164 1.70 MB/sec warmup 4 sec latency 170.745 ms 1 184 1.48 MB/sec warmup 5 sec latency 337.315 ms Failing mds1 on oleg439-server 1 199 1.31 MB/sec warmup 6 sec latency 654.181 ms Stopping /mnt/lustre-mds1 (opts:) on oleg439-server 1 240 1.31 MB/sec warmup 7 sec latency 145.325 ms 1 271 1.27 MB/sec warmup 8 sec latency 221.958 ms 1 305 1.25 MB/sec warmup 9 sec latency 150.547 ms 1 339 1.23 MB/sec warmup 10 sec latency 210.350 ms 05:58:01 (1787824681) shut down facet: mds1 facet_host: oleg439-server facet_failover_host: oleg439-server 1 339 1.11 MB/sec warmup 11 sec latency 1211.755 ms 1 339 1.02 MB/sec warmup 12 sec latency 2213.794 ms 1 339 0.94 MB/sec warmup 13 sec latency 3214.229 ms 1 339 0.88 MB/sec warmup 14 sec latency 4215.692 ms 1 339 0.82 MB/sec warmup 15 sec latency 5215.895 ms 1 339 0.77 MB/sec warmup 16 sec latency 6218.524 ms 1 339 0.72 MB/sec warmup 17 sec latency 7218.805 ms 1 339 0.68 MB/sec warmup 18 sec latency 8219.080 ms 1 339 0.64 MB/sec warmup 19 sec latency 9220.687 ms 1 339 0.00 MB/sec execute 1 sec latency 11222.708 ms Failover mds1 to oleg439-server mount facets: mds1 1 339 0.00 MB/sec execute 2 sec latency 12224.579 ms 1 339 0.00 MB/sec execute 3 sec latency 13227.212 ms 1 339 0.00 MB/sec execute 4 sec latency 14227.815 ms 1 339 0.00 MB/sec execute 5 sec latency 15228.085 ms 1 339 0.00 MB/sec execute 6 sec latency 16232.896 ms 1 339 0.00 MB/sec execute 7 sec latency 17234.362 ms 1 339 0.00 MB/sec execute 8 sec latency 18235.175 ms 1 339 0.00 MB/sec execute 9 sec latency 19235.387 ms 1 339 0.00 MB/sec execute 10 sec latency 20235.662 ms 1 339 0.00 MB/sec execute 11 sec latency 21245.053 ms 1 339 0.00 MB/sec execute 12 sec latency 22250.212 ms 1 339 0.00 MB/sec execute 13 sec latency 23250.692 ms 1 339 0.00 MB/sec execute 14 sec latency 24251.892 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 339 0.00 MB/sec execute 15 sec latency 25252.363 ms 1 339 0.00 MB/sec execute 16 sec latency 26253.310 ms 1 339 0.00 MB/sec execute 17 sec latency 27255.495 ms 1 339 0.00 MB/sec execute 18 sec latency 28260.894 ms 1 339 0.00 MB/sec execute 19 sec latency 29261.303 ms 1 339 0.00 MB/sec execute 20 sec latency 30261.560 ms 1 339 0.00 MB/sec execute 21 sec latency 31261.802 ms 1 339 0.00 MB/sec execute 22 sec latency 32262.016 ms 1 339 0.00 MB/sec execute 23 sec latency 33262.335 ms oleg439-server: oleg439-server.virtnet: executing set_default_debug -1 all 1 339 0.00 MB/sec execute 24 sec latency 34272.806 ms 1 339 0.00 MB/sec execute 25 sec latency 35275.508 ms pdsh@oleg439-client: oleg439-server: ssh exited with exit code 1 1 357 0.02 MB/sec execute 26 sec latency 35609.081 ms Started lustre-MDT0000 05:58:37 (1787824717) targets are mounted 05:58:37 (1787824717) facet_failover done 1 385 0.05 MB/sec execute 27 sec latency 187.356 ms 1 421 0.09 MB/sec execute 28 sec latency 132.200 ms 1 461 0.13 MB/sec execute 29 sec latency 141.480 ms 1 493 0.16 MB/sec execute 30 sec latency 138.952 ms 1 525 0.19 MB/sec execute 31 sec latency 137.543 ms 1 596 0.26 MB/sec execute 32 sec latency 134.305 ms 1 642 0.27 MB/sec execute 33 sec latency 128.647 ms 1 673 0.26 MB/sec execute 34 sec latency 156.401 ms oleg439-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 709 0.25 MB/sec execute 35 sec latency 119.986 ms 1 735 0.25 MB/sec execute 36 sec latency 165.968 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 773 0.25 MB/sec execute 37 sec latency 117.609 ms 1 803 0.24 MB/sec execute 38 sec latency 111.648 ms 1 849 0.24 MB/sec execute 39 sec latency 124.563 ms 1 876 0.23 MB/sec execute 40 sec latency 144.016 ms 1 884 0.23 MB/sec execute 41 sec latency 670.666 ms 1 888 0.22 MB/sec execute 42 sec latency 1442.413 ms 1 923 0.22 MB/sec execute 43 sec latency 130.057 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 967 0.22 MB/sec execute 44 sec latency 95.605 ms 1 1009 0.22 MB/sec execute 45 sec latency 103.994 ms 1 1074 0.23 MB/sec execute 46 sec latency 72.100 ms 1 1124 0.23 MB/sec execute 47 sec latency 122.499 ms 1 1170 0.22 MB/sec execute 48 sec latency 89.474 ms 1 1202 0.22 MB/sec execute 49 sec latency 90.089 ms 1 1243 0.22 MB/sec execute 50 sec latency 97.062 ms 1 1378 0.27 MB/sec execute 51 sec latency 112.097 ms 1 1426 0.26 MB/sec execute 52 sec latency 149.088 ms 1 1470 0.26 MB/sec execute 53 sec latency 313.161 ms 1 1503 0.25 MB/sec execute 54 sec latency 118.817 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Aug 27 05:59:05 EDT 2026 with return code 0 67965 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67965 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished