== replay-dual test 26: dbench and tar with mds failover ========================================================== 10:20:37 (1786803637) Starting client oleg445-client.virtnet: -o user_xattr,flock 192.168.204.145@tcp:/lustre /mnt/lustre Started clients oleg445-client.virtnet: 192.168.204.145@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 44938 Started dbench loop with 44939 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 2210560 2048 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 2048 3734528 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3751936 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7486464 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 Aug 15 10:20:43 EDT 2026 waiting for dbench pid 45008 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 1 31 1.05 MB/sec warmup 1 sec latency 30.282 ms 1 64 1.38 MB/sec warmup 2 sec latency 200.408 ms 1 112 1.75 MB/sec warmup 3 sec latency 170.704 ms 1 148 1.57 MB/sec warmup 4 sec latency 121.029 ms 1 181 1.46 MB/sec warmup 5 sec latency 145.771 ms test_26 fail mds1 1 times 1 214 1.39 MB/sec warmup 6 sec latency 134.576 ms 1 248 1.34 MB/sec warmup 7 sec latency 149.692 ms Failing mds1 on oleg445-server 1 287 1.34 MB/sec warmup 8 sec latency 155.142 ms Stopping /mnt/lustre-mds1 (opts:) on oleg445-server 1 324 1.30 MB/sec warmup 9 sec latency 123.509 ms 1 349 1.25 MB/sec warmup 10 sec latency 245.012 ms 1 349 1.14 MB/sec warmup 11 sec latency 1247.734 ms 1 349 1.04 MB/sec warmup 12 sec latency 2248.474 ms 10:20:56 (1786803656) shut down facet: mds1 facet_host: oleg445-server facet_failover_host: oleg445-server 1 349 0.96 MB/sec warmup 13 sec latency 3249.530 ms 1 349 0.89 MB/sec warmup 14 sec latency 4249.800 ms 1 349 0.83 MB/sec warmup 15 sec latency 5251.901 ms 1 349 0.78 MB/sec warmup 16 sec latency 6253.326 ms 1 349 0.74 MB/sec warmup 17 sec latency 7253.685 ms 1 349 0.70 MB/sec warmup 18 sec latency 8255.274 ms 1 349 0.66 MB/sec warmup 19 sec latency 9256.034 ms 1 349 0.00 MB/sec execute 1 sec latency 11258.036 ms 1 349 0.00 MB/sec execute 2 sec latency 12260.610 ms 1 349 0.00 MB/sec execute 3 sec latency 13261.736 ms Failover mds1 to oleg445-server mount facets: mds1 1 349 0.00 MB/sec execute 4 sec latency 14264.269 ms 1 349 0.00 MB/sec execute 5 sec latency 15264.645 ms 1 349 0.00 MB/sec execute 6 sec latency 16265.162 ms 1 349 0.00 MB/sec execute 7 sec latency 17268.383 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 349 0.00 MB/sec execute 8 sec latency 18268.598 ms 1 349 0.00 MB/sec execute 9 sec latency 19272.474 ms 1 349 0.00 MB/sec execute 10 sec latency 20272.754 ms 1 349 0.00 MB/sec execute 11 sec latency 21273.174 ms 1 349 0.00 MB/sec execute 12 sec latency 22273.404 ms 1 349 0.00 MB/sec execute 13 sec latency 23273.795 ms 1 357 0.02 MB/sec execute 14 sec latency 24169.126 ms oleg445-server: oleg445-server.virtnet: executing set_default_debug -1 all 1 404 0.12 MB/sec execute 15 sec latency 111.790 ms 1 436 0.18 MB/sec execute 16 sec latency 164.327 ms pdsh@oleg445-client: oleg445-server: ssh exited with exit code 1 1 470 0.23 MB/sec execute 17 sec latency 158.943 ms Started lustre-MDT0000 10:21:21 (1786803681) targets are mounted 10:21:21 (1786803681) facet_failover done 1 513 0.29 MB/sec execute 18 sec latency 172.732 ms 1 549 0.35 MB/sec execute 19 sec latency 224.249 ms 1 638 0.43 MB/sec execute 20 sec latency 143.076 ms 1 664 0.41 MB/sec execute 21 sec latency 154.831 ms 1 678 0.39 MB/sec execute 22 sec latency 359.226 ms 1 710 0.38 MB/sec execute 23 sec latency 117.383 ms 1 733 0.37 MB/sec execute 24 sec latency 220.349 ms 1 762 0.35 MB/sec execute 25 sec latency 159.778 ms oleg445-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 789 0.34 MB/sec execute 26 sec latency 153.810 ms 1 803 0.33 MB/sec execute 27 sec latency 211.246 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 845 0.32 MB/sec execute 28 sec latency 123.648 ms 1 874 0.31 MB/sec execute 29 sec latency 242.144 ms 1 903 0.30 MB/sec execute 30 sec latency 131.569 ms 1 921 0.30 MB/sec execute 31 sec latency 310.663 ms 1 959 0.29 MB/sec execute 32 sec latency 120.336 ms 1 983 0.28 MB/sec execute 33 sec latency 189.714 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2432 2206080 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 49152 3667968 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 9216 3734528 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 58368 7402496 1% /mnt/lustre 1 1037 0.30 MB/sec execute 34 sec latency 142.696 ms 1 1084 0.30 MB/sec execute 35 sec latency 94.822 ms 1 1135 0.29 MB/sec execute 36 sec latency 85.159 ms 1 1180 0.28 MB/sec execute 37 sec latency 103.798 ms 1 1225 0.28 MB/sec execute 38 sec latency 95.049 ms 1 1263 0.27 MB/sec execute 39 sec latency 81.040 ms test_26 fail mds1 2 times 1 1396 0.34 MB/sec execute 40 sec latency 103.356 ms 1 1426 0.33 MB/sec execute 41 sec latency 171.245 ms Failing mds1 on oleg445-server 1 1474 0.32 MB/sec execute 42 sec latency 110.475 ms Stopping /mnt/lustre-mds1 (opts:) on oleg445-server 1 1509 0.31 MB/sec execute 43 sec latency 169.854 ms 1 1532 0.31 MB/sec execute 44 sec latency 571.246 ms 1 1532 0.30 MB/sec execute 45 sec latency 1572.714 ms 1 1532 0.29 MB/sec execute 46 sec latency 2573.141 ms 10:21:50 (1786803710) shut down facet: mds1 facet_host: oleg445-server facet_failover_host: oleg445-server 1 1532 0.29 MB/sec execute 47 sec latency 3573.437 ms 1 1532 0.28 MB/sec execute 48 sec latency 4573.933 ms 1 1532 0.28 MB/sec execute 49 sec latency 5575.197 ms 1 1532 0.27 MB/sec execute 50 sec latency 6575.529 ms 1 1532 0.27 MB/sec execute 51 sec latency 7575.842 ms 1 1532 0.26 MB/sec execute 52 sec latency 8576.286 ms 1 1532 0.26 MB/sec execute 53 sec latency 9576.687 ms 1 1532 0.25 MB/sec execute 54 sec latency 10577.032 ms 1 1532 0.25 MB/sec execute 55 sec latency 11577.468 ms 1 1532 0.24 MB/sec execute 56 sec latency 12577.801 ms Failover mds1 to oleg445-server mount facets: mds1 1 1532 0.24 MB/sec execute 57 sec latency 13578.030 ms 1 1532 0.23 MB/sec execute 58 sec latency 14578.467 ms 1 1532 0.23 MB/sec execute 59 sec latency 15579.675 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1532 0.23 MB/sec execute 60 sec latency 16579.881 ms 1 1532 0.22 MB/sec execute 61 sec latency 17580.830 ms 1 1532 0.22 MB/sec execute 62 sec latency 18581.699 ms 1 1532 0.22 MB/sec execute 63 sec latency 19581.910 ms 1 1532 0.21 MB/sec execute 64 sec latency 20582.104 ms 1 1532 0.21 MB/sec execute 65 sec latency 21582.733 ms 1 1532 0.21 MB/sec execute 66 sec latency 22584.260 ms oleg445-server: oleg445-server.virtnet: executing set_default_debug -1 all 1 1532 0.20 MB/sec execute 67 sec latency 23584.603 ms pdsh@oleg445-client: oleg445-server: ssh exited with exit code 1 1 1534 0.20 MB/sec execute 68 sec latency 24439.003 ms Started lustre-MDT0000 10:22:12 (1786803732) targets are mounted 10:22:12 (1786803732) facet_failover done 1 1588 0.20 MB/sec execute 69 sec latency 151.434 ms 1 1634 0.19 MB/sec execute 70 sec latency 258.336 ms 1 1675 0.19 MB/sec execute 71 sec latency 171.249 ms 1 1721 0.19 MB/sec execute 72 sec latency 110.578 ms 1 1779 0.19 MB/sec execute 73 sec latency 140.721 ms 1 1834 0.19 MB/sec execute 74 sec latency 115.403 ms 1 1877 0.18 MB/sec execute 75 sec latency 139.100 ms oleg445-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1949 0.18 MB/sec execute 76 sec latency 141.469 ms 1 1984 0.18 MB/sec execute 77 sec latency 124.753 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2006 0.18 MB/sec execute 78 sec latency 199.384 ms 1 2043 0.18 MB/sec execute 79 sec latency 114.984 ms 1 2089 0.18 MB/sec execute 80 sec latency 136.628 ms 1 2146 0.17 MB/sec execute 81 sec latency 129.007 ms 1 2166 0.17 MB/sec execute 82 sec latency 129.126 ms 1 2228 0.17 MB/sec execute 83 sec latency 132.577 ms 1 2298 0.18 MB/sec execute 84 sec latency 122.565 ms 1 2345 0.18 MB/sec execute 85 sec latency 101.705 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2816 2205696 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 63488 3687424 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 10240 3736576 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7424000 1% /mnt/lustre 1 2358 0.18 MB/sec execute 86 sec latency 404.494 ms 1 2387 0.18 MB/sec execute 87 sec latency 284.061 ms 1 2416 0.18 MB/sec execute 88 sec latency 150.361 ms 1 2436 0.17 MB/sec execute 89 sec latency 301.406 ms 1 2477 0.18 MB/sec execute 90 sec latency 91.151 ms 1 2507 0.18 MB/sec execute 91 sec latency 303.120 ms 1 2566 0.18 MB/sec execute 92 sec latency 534.138 ms test_26 fail mds1 3 times 1 2568 0.18 MB/sec execute 93 sec latency 1435.318 ms 1 2596 0.17 MB/sec execute 94 sec latency 125.546 ms Failing mds1 on oleg445-server 1 2716 0.20 MB/sec execute 95 sec latency 144.854 ms Stopping /mnt/lustre-mds1 (opts:) on oleg445-server 1 2770 0.20 MB/sec execute 96 sec latency 234.603 ms 1 2889 0.21 MB/sec execute 97 sec latency 124.231 ms 1 2894 0.21 MB/sec execute 98 sec latency 951.553 ms 1 2894 0.20 MB/sec execute 99 sec latency 1951.874 ms 10:22:43 (1786803763) shut down facet: mds1 facet_host: oleg445-server facet_failover_host: oleg445-server 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec Failover mds1 to oleg445-server mount facets: mds1 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 cleanup 114 sec 1 cleanup 115 sec 1 cleanup 116 sec 1 cleanup 117 sec 1 cleanup 118 sec 1 cleanup 119 sec 1 cleanup 120 sec 1 cleanup 121 sec 1 cleanup 122 sec 1 cleanup 123 sec 1 cleanup 124 sec 1 cleanup 125 sec 1 cleanup 126 sec 1 cleanup 127 sec 1 cleanup 128 sec 1 cleanup 129 sec oleg445-server: oleg445-server.virtnet: executing set_default_debug -1 all 1 cleanup 130 sec pdsh@oleg445-client: oleg445-server: ssh exited with exit code 1 1 cleanup 131 sec Started lustre-MDT0000 10:23:15 (1786803795) targets are mounted 10:23:15 (1786803795) facet_failover done 1 cleanup 132 sec 1 cleanup 133 sec 1 cleanup 134 sec 1 cleanup 135 sec 1 cleanup 136 sec 1 cleanup 137 sec 1 cleanup 138 sec 1 cleanup 139 sec 1 cleanup 140 sec 0 cleanup 141 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 400 183.305 24438.977 Close 342 128.804 39895.579 Rename 18 98.178 199.099 Unlink 42 33.335 64.225 Qpathinfo 364 19.822 151.397 Qfileinfo 112 2.628 22.116 Qfsinfo 54 4.653 35.358 Sfileinfo 50 71.250 143.899 Find 128 8.084 59.675 WriteX 383 14.240 122.552 ReadX 614 2.187 124.211 LockX 2 24.985 32.798 UnlockX 2 19.366 20.364 Flush 35 174.247 404.478 Throughput 0.204618 MB/sec 1 clients 1 procs max_latency=24439.003 ms stopping dbench on /mnt/lustre at Sat Aug 15 10:23:25 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre oleg445-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 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 Aug 15 10:23:32 EDT 2026 waiting for dbench pid 47960 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 31 1.05 MB/sec warmup 1 sec latency 128.622 ms 1 91 2.10 MB/sec warmup 2 sec latency 154.195 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3200 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 25600 3741696 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 28672 3722240 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 54272 7463936 1% /mnt/lustre 1 121 1.83 MB/sec warmup 3 sec latency 206.504 ms 1 155 1.63 MB/sec warmup 4 sec latency 178.134 ms 1 187 1.50 MB/sec warmup 5 sec latency 145.043 ms 1 223 1.43 MB/sec warmup 6 sec latency 132.295 ms 1 271 1.45 MB/sec warmup 7 sec latency 117.442 ms 1 318 1.43 MB/sec warmup 8 sec latency 106.405 ms test_26 fail mds1 4 times 1 357 1.42 MB/sec warmup 9 sec latency 152.116 ms 1 392 1.38 MB/sec warmup 10 sec latency 132.910 ms Failing mds1 on oleg445-server 1 429 1.37 MB/sec warmup 11 sec latency 142.283 ms Stopping /mnt/lustre-mds1 (opts:) on oleg445-server 1 469 1.37 MB/sec warmup 12 sec latency 120.357 ms 1 508 1.35 MB/sec warmup 13 sec latency 151.952 ms 1 510 1.26 MB/sec warmup 14 sec latency 985.080 ms 1 510 1.18 MB/sec warmup 15 sec latency 1985.258 ms 10:23:49 (1786803829) shut down 1 510 1.11 MB/sec warmup 16 sec latency 2994.629 ms facet: mds1 facet_host: oleg445-server facet_failover_host: oleg445-server 1 510 1.04 MB/sec warmup 17 sec latency 3994.806 ms 1 510 0.98 MB/sec warmup 18 sec latency 4995.688 ms 1 510 0.93 MB/sec warmup 19 sec latency 6000.716 ms 1 510 0.00 MB/sec execute 1 sec latency 8001.370 ms 1 510 0.00 MB/sec execute 2 sec latency 9001.813 ms 1 510 0.00 MB/sec execute 3 sec latency 10002.994 ms 1 510 0.00 MB/sec execute 4 sec latency 11003.211 ms 1 510 0.00 MB/sec execute 5 sec latency 12004.637 ms 1 510 0.00 MB/sec execute 6 sec latency 13005.508 ms Failover mds1 to oleg445-server mount facets: mds1 1 510 0.00 MB/sec execute 7 sec latency 14005.704 ms 1 510 0.00 MB/sec execute 8 sec latency 15006.190 ms 1 510 0.00 MB/sec execute 9 sec latency 16006.556 ms 1 510 0.00 MB/sec execute 10 sec latency 17006.897 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 510 0.00 MB/sec execute 11 sec latency 18007.139 ms 1 510 0.00 MB/sec execute 12 sec latency 19007.938 ms 1 510 0.00 MB/sec execute 13 sec latency 20008.127 ms 1 510 0.00 MB/sec execute 14 sec latency 21008.727 ms 1 510 0.00 MB/sec execute 15 sec latency 22010.204 ms 1 510 0.00 MB/sec execute 16 sec latency 23019.062 ms 1 510 0.00 MB/sec execute 17 sec latency 24019.317 ms oleg445-server: oleg445-server.virtnet: executing set_default_debug -1 all 1 510 0.00 MB/sec execute 18 sec latency 25020.138 ms pdsh@oleg445-client: oleg445-server: ssh exited with exit code 1 1 510 0.00 MB/sec execute 19 sec latency 26020.339 ms Started lustre-MDT0000 10:24:12 (1786803852) targets are mounted 10:24:12 (1786803852) facet_failover done 1 510 0.00 MB/sec execute 20 sec latency 27021.442 ms 1 510 0.00 MB/sec execute 21 sec latency 28021.674 ms 1 510 0.00 MB/sec execute 22 sec latency 29021.919 ms 1 510 0.00 MB/sec execute 23 sec latency 30022.261 ms 1 510 0.00 MB/sec execute 24 sec latency 31023.205 ms 1 510 0.00 MB/sec execute 25 sec latency 32024.796 ms 1 510 0.00 MB/sec execute 26 sec latency 33025.033 ms 1 510 0.00 MB/sec execute 27 sec latency 34025.540 ms 1 510 0.00 MB/sec execute 28 sec latency 35026.644 ms 1 510 0.00 MB/sec execute 29 sec latency 36026.971 ms 1 510 0.00 MB/sec execute 30 sec latency 37027.544 ms 1 510 0.00 MB/sec execute 31 sec latency 38029.038 ms 1 510 0.00 MB/sec execute 32 sec latency 39029.215 ms 1 510 0.00 MB/sec execute 33 sec latency 40029.880 ms 1 510 0.00 MB/sec execute 34 sec latency 41030.049 ms 1 511 0.00 MB/sec execute 35 sec latency 41943.382 ms 1 581 0.06 MB/sec execute 36 sec latency 227.633 ms 1 642 0.09 MB/sec execute 37 sec latency 102.863 ms 1 669 0.09 MB/sec execute 38 sec latency 400.242 ms 1 695 0.09 MB/sec execute 39 sec latency 175.851 ms 1 730 0.09 MB/sec execute 40 sec latency 155.941 ms oleg445-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 772 0.09 MB/sec execute 41 sec latency 108.358 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 794 0.09 MB/sec execute 42 sec latency 232.858 ms 1 817 0.09 MB/sec execute 43 sec latency 130.044 ms 1 863 0.09 MB/sec execute 44 sec latency 149.284 ms 1 888 0.09 MB/sec execute 45 sec latency 206.577 ms 1 913 0.09 MB/sec execute 46 sec latency 126.446 ms 1 949 0.09 MB/sec execute 47 sec latency 212.547 ms 1 980 0.09 MB/sec execute 48 sec latency 244.072 ms 1 1041 0.11 MB/sec execute 49 sec latency 254.959 ms 1 1084 0.10 MB/sec execute 50 sec latency 100.736 ms 1 1145 0.10 MB/sec execute 51 sec latency 92.873 ms 1 1192 0.10 MB/sec execute 52 sec latency 176.062 ms 1 1231 0.10 MB/sec execute 53 sec latency 94.770 ms 1 1274 0.10 MB/sec execute 54 sec latency 77.007 ms 1 1406 0.15 MB/sec execute 55 sec latency 120.719 ms 1 1468 0.15 MB/sec execute 56 sec latency 76.613 ms 1 1508 0.15 MB/sec execute 57 sec latency 253.086 ms 1 1560 0.14 MB/sec execute 58 sec latency 82.177 ms 1 1596 0.14 MB/sec execute 59 sec latency 89.325 ms 1 1646 0.14 MB/sec execute 60 sec latency 133.385 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Sat Aug 15 10:24:53 EDT 2026 with return code 0 47960 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47960 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished