== replay-dual test 26: dbench and tar with mds failover ========================================================== 17:46:04 (1788644764) Starting client oleg216-client.virtnet: -o user_xattr,flock 192.168.202.116@tcp:/lustre /mnt/lustre Started clients oleg216-client.virtnet: 192.168.202.116@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 65670 Started dbench loop with 65671 striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench 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 1944 1269360 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1768 1269536 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3588912 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7194368 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 Sat Sep 5 17:46:10 EDT 2026 waiting for dbench pid 65748 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 10 0.00 MB/sec warmup 1 sec latency 91.573 ms 1 66 1.44 MB/sec warmup 2 sec latency 101.045 ms 1 120 1.83 MB/sec warmup 3 sec latency 126.629 ms 1 148 1.57 MB/sec warmup 4 sec latency 190.672 ms 1 181 1.46 MB/sec warmup 5 sec latency 192.043 ms 1 196 1.30 MB/sec warmup 6 sec latency 523.286 ms 1 239 1.30 MB/sec warmup 7 sec latency 115.240 ms 1 285 1.33 MB/sec warmup 8 sec latency 113.698 ms test_26 fail mds1 1 times 1 313 1.27 MB/sec warmup 9 sec latency 137.971 ms 1 339 1.22 MB/sec warmup 10 sec latency 156.307 ms Failing mds1 on oleg216-server 1 365 1.18 MB/sec warmup 11 sec latency 153.130 ms Stopping /mnt/lustre-mds1 (opts:) on oleg216-server 1 389 1.15 MB/sec warmup 12 sec latency 214.406 ms 1 420 1.14 MB/sec warmup 13 sec latency 165.854 ms 1 420 1.06 MB/sec warmup 14 sec latency 1086.559 ms 1 420 0.99 MB/sec warmup 15 sec latency 2086.733 ms 17:46:26 (1788644786) shut down facet: mds1 facet_host: oleg216-server facet_failover_host: oleg216-server 1 420 0.93 MB/sec warmup 16 sec latency 3088.636 ms 1 420 0.87 MB/sec warmup 17 sec latency 4090.509 ms 1 420 0.82 MB/sec warmup 18 sec latency 5090.817 ms 1 420 0.78 MB/sec warmup 19 sec latency 6092.642 ms 1 420 0.00 MB/sec execute 1 sec latency 8093.284 ms 1 420 0.00 MB/sec execute 2 sec latency 9094.607 ms 1 420 0.00 MB/sec execute 3 sec latency 10094.950 ms 1 420 0.00 MB/sec execute 4 sec latency 11095.154 ms 1 420 0.00 MB/sec execute 5 sec latency 12095.684 ms Failover mds1 to oleg216-server mount facets: mds1 1 420 0.00 MB/sec execute 6 sec latency 13099.197 ms 1 420 0.00 MB/sec execute 7 sec latency 14101.344 ms 1 420 0.00 MB/sec execute 8 sec latency 15101.601 ms 1 420 0.00 MB/sec execute 9 sec latency 16101.982 ms 1 420 0.00 MB/sec execute 10 sec latency 17104.184 ms 1 420 0.00 MB/sec execute 11 sec latency 18104.494 ms 1 420 0.00 MB/sec execute 12 sec latency 19104.688 ms 1 420 0.00 MB/sec execute 13 sec latency 20105.317 ms 1 420 0.00 MB/sec execute 14 sec latency 21106.631 ms 1 420 0.00 MB/sec execute 15 sec latency 22107.242 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 420 0.00 MB/sec execute 16 sec latency 23108.514 ms 1 420 0.00 MB/sec execute 17 sec latency 24111.071 ms 1 420 0.00 MB/sec execute 18 sec latency 25111.376 ms 1 420 0.00 MB/sec execute 19 sec latency 26112.275 ms 1 420 0.00 MB/sec execute 20 sec latency 27113.584 ms 1 420 0.00 MB/sec execute 21 sec latency 28113.822 ms 1 420 0.00 MB/sec execute 22 sec latency 29114.151 ms 1 420 0.00 MB/sec execute 23 sec latency 30115.425 ms 1 420 0.00 MB/sec execute 24 sec latency 31116.167 ms 1 420 0.00 MB/sec execute 25 sec latency 32116.459 ms 1 420 0.00 MB/sec execute 26 sec latency 33116.620 ms oleg216-server: oleg216-server.virtnet: executing set_default_debug -1 all 1 420 0.00 MB/sec execute 27 sec latency 34116.915 ms 1 420 0.00 MB/sec execute 28 sec latency 35118.830 ms pdsh@oleg216-client: oleg216-server: ssh exited with exit code 1 1 422 0.00 MB/sec execute 29 sec latency 35860.728 ms Started lustre-MDT0000 17:47:00 (1788644820) targets are mounted 17:47:00 (1788644820) facet_failover done 1 469 0.05 MB/sec execute 30 sec latency 149.646 ms 1 513 0.09 MB/sec execute 31 sec latency 102.315 ms 1 552 0.13 MB/sec execute 32 sec latency 297.299 ms 1 609 0.18 MB/sec execute 33 sec latency 573.344 ms 1 660 0.18 MB/sec execute 34 sec latency 132.593 ms 1 695 0.18 MB/sec execute 35 sec latency 128.787 ms 1 720 0.18 MB/sec execute 36 sec latency 161.904 ms oleg216-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 741 0.17 MB/sec execute 37 sec latency 136.753 ms 1 778 0.17 MB/sec execute 38 sec latency 120.288 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 803 0.17 MB/sec execute 39 sec latency 166.507 ms 1 827 0.17 MB/sec execute 40 sec latency 179.034 ms 1 876 0.17 MB/sec execute 41 sec latency 117.927 ms 1 907 0.16 MB/sec execute 42 sec latency 130.786 ms 1 940 0.16 MB/sec execute 43 sec latency 113.771 ms 1 981 0.16 MB/sec execute 44 sec latency 169.010 ms 1 1057 0.18 MB/sec execute 45 sec latency 96.759 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2132 1269172 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1952 1269352 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 9344 3593324 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 41384 3561012 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 50728 7154336 1% /mnt/lustre 1 1102 0.18 MB/sec execute 46 sec latency 100.397 ms 1 1147 0.17 MB/sec execute 47 sec latency 136.928 ms 1 1172 0.17 MB/sec execute 48 sec latency 525.559 ms 1 1192 0.17 MB/sec execute 49 sec latency 717.522 ms 1 1229 0.16 MB/sec execute 50 sec latency 112.285 ms 1 1273 0.16 MB/sec execute 51 sec latency 92.058 ms 1 1376 0.21 MB/sec execute 52 sec latency 643.562 ms 1 1410 0.21 MB/sec execute 53 sec latency 138.943 ms 1 1468 0.21 MB/sec execute 54 sec latency 102.077 ms 1 1509 0.20 MB/sec execute 55 sec latency 128.497 ms test_26 fail mds2 2 times 1 1553 0.20 MB/sec execute 56 sec latency 126.817 ms Failing mds2 on oleg216-server 1 1591 0.20 MB/sec execute 57 sec latency 83.802 ms Stopping /mnt/lustre-mds2 (opts:) on oleg216-server 1 1627 0.19 MB/sec execute 58 sec latency 132.191 ms 1 1665 0.19 MB/sec execute 59 sec latency 127.164 ms 1 1719 0.19 MB/sec execute 60 sec latency 84.724 ms 1 1793 0.19 MB/sec execute 61 sec latency 91.528 ms 17:47:32 (1788644852) shut down facet: mds2 facet_host: oleg216-server facet_failover_host: oleg216-server 1 1861 0.19 MB/sec execute 62 sec latency 80.456 ms 1 1974 0.18 MB/sec execute 63 sec latency 82.889 ms 1 2060 0.18 MB/sec execute 64 sec latency 78.926 ms 1 2145 0.18 MB/sec execute 65 sec latency 88.428 ms 1 2209 0.18 MB/sec execute 66 sec latency 124.358 ms 1 2259 0.18 MB/sec execute 67 sec latency 479.076 ms 1 2259 0.18 MB/sec execute 68 sec latency 1479.473 ms 1 2259 0.17 MB/sec execute 69 sec latency 2479.895 ms 1 2259 0.17 MB/sec execute 70 sec latency 3480.117 ms 1 2259 0.17 MB/sec execute 71 sec latency 4480.342 ms Failover mds2 to oleg216-server mount facets: mds2 1 2259 0.17 MB/sec execute 72 sec latency 5480.510 ms 1 2259 0.16 MB/sec execute 73 sec latency 6485.240 ms 1 2259 0.16 MB/sec execute 74 sec latency 7485.423 ms 1 2259 0.16 MB/sec execute 75 sec latency 8486.811 ms 1 2259 0.16 MB/sec execute 76 sec latency 9487.215 ms 1 2259 0.15 MB/sec execute 77 sec latency 10487.762 ms 1 2259 0.15 MB/sec execute 78 sec latency 11488.271 ms 1 2259 0.15 MB/sec execute 79 sec latency 12488.746 ms 1 2259 0.15 MB/sec execute 80 sec latency 13488.978 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.15 MB/sec execute 81 sec latency 14489.179 ms 1 2259 0.15 MB/sec execute 82 sec latency 15489.510 ms 1 2259 0.14 MB/sec execute 83 sec latency 16489.741 ms 1 2259 0.14 MB/sec execute 84 sec latency 17489.925 ms 1 2259 0.14 MB/sec execute 85 sec latency 18490.352 ms 1 2259 0.14 MB/sec execute 86 sec latency 19490.574 ms oleg216-server: oleg216-server.virtnet: executing set_default_debug -1 all 1 2259 0.14 MB/sec execute 87 sec latency 20492.201 ms pdsh@oleg216-client: oleg216-server: ssh exited with exit code 1 1 2259 0.14 MB/sec execute 88 sec latency 21497.633 ms Started lustre-MDT0001 17:47:59 (1788644879) targets are mounted 17:47:59 (1788644879) facet_failover done 1 2259 0.13 MB/sec execute 89 sec latency 22500.099 ms 1 2327 0.14 MB/sec execute 90 sec latency 22903.159 ms 1 2373 0.14 MB/sec execute 91 sec latency 87.457 ms 1 2408 0.14 MB/sec execute 92 sec latency 92.605 ms 1 2440 0.14 MB/sec execute 93 sec latency 136.027 ms 1 2478 0.15 MB/sec execute 94 sec latency 171.128 ms 1 2562 0.15 MB/sec execute 95 sec latency 159.102 ms oleg216-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2586 0.15 MB/sec execute 96 sec latency 177.005 ms 1 2633 0.15 MB/sec execute 97 sec latency 121.012 ms 1 2768 0.17 MB/sec execute 98 sec latency 111.914 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2902 0.18 MB/sec execute 99 sec latency 171.823 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 0 cleanup 103 sec 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 405 108.921 22903.141 Close 340 117.062 35860.700 Rename 19 96.597 187.093 Unlink 45 24.185 60.693 Qpathinfo 382 16.219 138.920 Qfileinfo 108 1.814 10.751 Qfsinfo 55 3.705 33.765 Sfileinfo 50 64.104 136.736 Find 131 11.479 57.428 WriteX 351 12.783 95.490 ReadX 633 1.484 78.758 LockX 2 5.144 6.207 UnlockX 2 15.011 19.619 Flush 36 64.957 171.807 Throughput 0.181081 MB/sec 1 clients 1 procs max_latency=35860.728 ms stopping dbench on /mnt/lustre at Sat Sep 5 17:48:14 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 2348 1268956 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2156 1269148 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 2196 3604600 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 47276 3556792 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 49472 7161392 1% /mnt/lustre striped dir -i0 -c2 -H fnv_1a_64 /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 Sat Sep 5 17:48:23 EDT 2026 waiting for dbench pid 67957 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 0 11 0.00 MB/sec warmup 1 sec latency 9.880 ms 1 62 1.31 MB/sec warmup 2 sec latency 112.128 ms 1 113 1.74 MB/sec warmup 3 sec latency 199.438 ms test_26 fail mds1 3 times 1 137 1.50 MB/sec warmup 4 sec latency 192.334 ms 1 159 1.31 MB/sec warmup 5 sec latency 275.428 ms Failing mds1 on oleg216-server 1 184 1.23 MB/sec warmup 6 sec latency 202.518 ms Stopping /mnt/lustre-mds1 (opts:) on oleg216-server 1 222 1.23 MB/sec warmup 7 sec latency 263.779 ms 1 271 1.27 MB/sec warmup 8 sec latency 122.812 ms 1 315 1.27 MB/sec warmup 9 sec latency 129.210 ms 1 339 1.22 MB/sec warmup 10 sec latency 694.974 ms 1 339 1.11 MB/sec warmup 11 sec latency 1695.370 ms 1 339 1.02 MB/sec warmup 12 sec latency 2695.994 ms 1 339 0.94 MB/sec warmup 13 sec latency 3696.481 ms 1 339 0.87 MB/sec warmup 14 sec latency 4696.652 ms 1 339 0.82 MB/sec warmup 15 sec latency 5697.936 ms 17:48:38 (1788644918) shut down facet: mds1 facet_host: oleg216-server facet_failover_host: oleg216-server 1 339 0.77 MB/sec warmup 16 sec latency 6698.223 ms 1 339 0.72 MB/sec warmup 17 sec latency 7699.627 ms 1 339 0.68 MB/sec warmup 18 sec latency 8699.875 ms 1 339 0.64 MB/sec warmup 19 sec latency 9700.109 ms 1 339 0.00 MB/sec execute 1 sec latency 11708.491 ms 1 339 0.00 MB/sec execute 2 sec latency 12708.710 ms 1 339 0.00 MB/sec execute 3 sec latency 13709.236 ms 1 339 0.00 MB/sec execute 4 sec latency 14711.065 ms 1 339 0.00 MB/sec execute 5 sec latency 15711.368 ms Failover mds1 to oleg216-server 1 339 0.00 MB/sec execute 6 sec latency 16711.636 ms mount facets: mds1 1 339 0.00 MB/sec execute 7 sec latency 17711.847 ms 1 339 0.00 MB/sec execute 8 sec latency 18712.157 ms 1 339 0.00 MB/sec execute 9 sec latency 19712.331 ms 1 339 0.00 MB/sec execute 10 sec latency 20714.974 ms 1 339 0.00 MB/sec execute 11 sec latency 21715.462 ms 1 339 0.00 MB/sec execute 12 sec latency 22715.767 ms 1 339 0.00 MB/sec execute 13 sec latency 23716.260 ms 1 339 0.00 MB/sec execute 14 sec latency 24716.732 ms 1 339 0.00 MB/sec execute 15 sec latency 25717.050 ms 1 339 0.00 MB/sec execute 16 sec latency 26717.325 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 339 0.00 MB/sec execute 17 sec latency 27717.587 ms 1 339 0.00 MB/sec execute 18 sec latency 28717.860 ms 1 339 0.00 MB/sec execute 19 sec latency 29718.431 ms 1 339 0.00 MB/sec execute 20 sec latency 30718.610 ms 1 339 0.00 MB/sec execute 21 sec latency 31718.863 ms 1 339 0.00 MB/sec execute 22 sec latency 32719.070 ms 1 339 0.00 MB/sec execute 23 sec latency 33722.442 ms 1 339 0.00 MB/sec execute 24 sec latency 34725.874 ms 1 339 0.00 MB/sec execute 25 sec latency 35726.192 ms 1 339 0.00 MB/sec execute 26 sec latency 36726.573 ms 1 339 0.00 MB/sec execute 27 sec latency 37728.708 ms 1 339 0.00 MB/sec execute 28 sec latency 38733.475 ms oleg216-server: oleg216-server.virtnet: executing set_default_debug -1 all 1 339 0.00 MB/sec execute 29 sec latency 39779.841 ms pdsh@oleg216-client: oleg216-server: ssh exited with exit code 1 1 349 0.01 MB/sec execute 30 sec latency 40367.743 ms Started lustre-MDT0000 17:49:14 (1788644954) targets are mounted 17:49:14 (1788644954) facet_failover done 1 389 0.05 MB/sec execute 31 sec latency 172.961 ms 1 453 0.11 MB/sec execute 32 sec latency 81.314 ms 1 485 0.14 MB/sec execute 33 sec latency 147.360 ms 1 514 0.16 MB/sec execute 34 sec latency 139.302 ms 1 587 0.22 MB/sec execute 35 sec latency 126.316 ms 1 645 0.24 MB/sec execute 36 sec latency 96.567 ms 1 676 0.24 MB/sec execute 37 sec latency 138.136 ms 1 699 0.23 MB/sec execute 38 sec latency 163.631 ms oleg216-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 721 0.23 MB/sec execute 39 sec latency 163.739 ms 1 759 0.23 MB/sec execute 40 sec latency 163.767 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 796 0.22 MB/sec execute 41 sec latency 113.054 ms 1 818 0.22 MB/sec execute 42 sec latency 161.953 ms 1 870 0.22 MB/sec execute 43 sec latency 132.326 ms 1 884 0.21 MB/sec execute 44 sec latency 668.282 ms 1 901 0.21 MB/sec execute 45 sec latency 1204.881 ms 1 926 0.21 MB/sec execute 46 sec latency 160.542 ms 1 969 0.20 MB/sec execute 47 sec latency 105.569 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1018 0.21 MB/sec execute 48 sec latency 109.127 ms 1 1079 0.22 MB/sec execute 49 sec latency 62.928 ms 1 1134 0.21 MB/sec execute 50 sec latency 83.205 ms 1 1177 0.21 MB/sec execute 51 sec latency 139.974 ms 1 1224 0.21 MB/sec execute 52 sec latency 75.819 ms 1 1252 0.20 MB/sec execute 53 sec latency 165.342 ms 1 1353 0.24 MB/sec execute 54 sec latency 111.303 ms 1 1413 0.25 MB/sec execute 55 sec latency 109.400 ms 1 1462 0.25 MB/sec execute 56 sec latency 191.967 ms 1 1512 0.24 MB/sec execute 57 sec latency 258.053 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Sat Sep 5 17:49:41 EDT 2026 with return code 0 1 1580 0.24 MB/sec execute 58 sec latency 76.429 ms 67957 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67957 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished