== replay-dual test 26: dbench and tar with mds failover ========================================================== 22:48:42 (1788576522) Starting client oleg336-client.virtnet: -o user_xattr,flock 192.168.203.136@tcp:/lustre /mnt/lustre Started clients oleg336-client.virtnet: 192.168.203.136@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 45261 Started dbench loop with 45262 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 14336 3740672 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3762176 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 16384 7502848 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 Fri Sep 4 22:48:48 EDT 2026 waiting for dbench pid 45329 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 41 1.51 MB/sec warmup 1 sec latency 128.141 ms 1 99 2.26 MB/sec warmup 2 sec latency 161.772 ms 1 139 2.00 MB/sec warmup 3 sec latency 176.893 ms 1 189 1.89 MB/sec warmup 4 sec latency 187.723 ms test_26 fail mds1 1 times 1 231 1.77 MB/sec warmup 5 sec latency 115.217 ms Failing mds1 on oleg336-server 1 279 1.74 MB/sec warmup 6 sec latency 128.389 ms Stopping /mnt/lustre-mds1 (opts:) on oleg336-server 1 313 1.64 MB/sec warmup 7 sec latency 144.255 ms 1 330 1.50 MB/sec warmup 8 sec latency 710.354 ms 1 330 1.33 MB/sec warmup 9 sec latency 1710.593 ms 22:48:58 (1788576538) shut down facet: mds1 facet_host: oleg336-server facet_failover_host: oleg336-server 1 330 1.20 MB/sec warmup 10 sec latency 2711.982 ms 1 330 1.09 MB/sec warmup 11 sec latency 3712.194 ms 1 330 1.00 MB/sec warmup 12 sec latency 4713.519 ms 1 330 0.92 MB/sec warmup 13 sec latency 5713.870 ms 1 330 0.86 MB/sec warmup 14 sec latency 6714.234 ms 1 330 0.80 MB/sec warmup 15 sec latency 7714.383 ms 1 330 0.75 MB/sec warmup 16 sec latency 8715.337 ms 1 330 0.71 MB/sec warmup 17 sec latency 9715.672 ms 1 330 0.67 MB/sec warmup 18 sec latency 10715.903 ms 1 330 0.63 MB/sec warmup 19 sec latency 11717.273 ms Failover mds1 to oleg336-server mount facets: mds1 1 330 0.00 MB/sec execute 1 sec latency 13717.584 ms 1 330 0.00 MB/sec execute 2 sec latency 14718.589 ms 1 330 0.00 MB/sec execute 3 sec latency 15722.083 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 330 0.00 MB/sec execute 4 sec latency 16722.358 ms 1 330 0.00 MB/sec execute 5 sec latency 17723.149 ms 1 330 0.00 MB/sec execute 6 sec latency 18724.325 ms 1 330 0.00 MB/sec execute 7 sec latency 19724.643 ms 1 330 0.00 MB/sec execute 8 sec latency 20724.814 ms 1 330 0.00 MB/sec execute 9 sec latency 21725.290 ms oleg336-server: oleg336-server.virtnet: executing set_default_debug -1 all 1 331 0.00 MB/sec execute 10 sec latency 22632.450 ms pdsh@oleg336-client: oleg336-server: ssh exited with exit code 1 1 365 0.09 MB/sec execute 11 sec latency 241.295 ms Started lustre-MDT0000 22:49:20 (1788576560) targets are mounted 22:49:20 (1788576560) facet_failover done 1 411 0.21 MB/sec execute 12 sec latency 123.238 ms 1 449 0.28 MB/sec execute 13 sec latency 106.059 ms 1 494 0.37 MB/sec execute 14 sec latency 122.093 ms 1 542 0.47 MB/sec execute 15 sec latency 125.750 ms 1 636 0.57 MB/sec execute 16 sec latency 169.014 ms 1 673 0.54 MB/sec execute 17 sec latency 145.318 ms oleg336-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 711 0.51 MB/sec execute 18 sec latency 106.170 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 735 0.49 MB/sec execute 19 sec latency 191.323 ms 1 776 0.47 MB/sec execute 20 sec latency 121.665 ms 1 804 0.45 MB/sec execute 21 sec latency 209.622 ms 1 864 0.43 MB/sec execute 22 sec latency 100.585 ms 1 902 0.42 MB/sec execute 23 sec latency 194.863 ms 1 952 0.41 MB/sec execute 24 sec latency 118.692 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 43008 3668992 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 11264 3702784 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 54272 7371776 1% /mnt/lustre 1 983 0.40 MB/sec execute 25 sec latency 243.119 ms 1 1050 0.42 MB/sec execute 26 sec latency 142.007 ms 1 1105 0.41 MB/sec execute 27 sec latency 86.188 ms 1 1149 0.39 MB/sec execute 28 sec latency 143.916 ms 1 1201 0.38 MB/sec execute 29 sec latency 75.811 ms test_26 fail mds1 2 times 1 1252 0.37 MB/sec execute 30 sec latency 73.919 ms 1 1389 0.45 MB/sec execute 31 sec latency 97.109 ms Failing mds1 on oleg336-server 1 1426 0.44 MB/sec execute 32 sec latency 144.749 ms Stopping /mnt/lustre-mds1 (opts:) on oleg336-server 1 1489 0.42 MB/sec execute 33 sec latency 120.217 ms 1 1509 0.41 MB/sec execute 34 sec latency 759.034 ms 1 1509 0.40 MB/sec execute 35 sec latency 1759.172 ms 1 1509 0.39 MB/sec execute 36 sec latency 2759.412 ms 22:49:45 (1788576585) shut down facet: mds1 facet_host: oleg336-server facet_failover_host: oleg336-server 1 1509 0.38 MB/sec execute 37 sec latency 3759.606 ms 1 1509 0.37 MB/sec execute 38 sec latency 4761.650 ms 1 1509 0.36 MB/sec execute 39 sec latency 5761.956 ms 1 1509 0.35 MB/sec execute 40 sec latency 6762.515 ms 1 1509 0.34 MB/sec execute 41 sec latency 7762.759 ms 1 1509 0.33 MB/sec execute 42 sec latency 8762.964 ms 1 1509 0.33 MB/sec execute 43 sec latency 9763.158 ms 1 1509 0.32 MB/sec execute 44 sec latency 10763.458 ms 1 1509 0.31 MB/sec execute 45 sec latency 11763.654 ms 1 1509 0.31 MB/sec execute 46 sec latency 12765.197 ms Failover mds1 to oleg336-server mount facets: mds1 1 1509 0.30 MB/sec execute 47 sec latency 13765.414 ms 1 1509 0.29 MB/sec execute 48 sec latency 14765.613 ms 1 1509 0.29 MB/sec execute 49 sec latency 15765.875 ms 1 1509 0.28 MB/sec execute 50 sec latency 16766.409 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1509 0.28 MB/sec execute 51 sec latency 17767.613 ms 1 1509 0.27 MB/sec execute 52 sec latency 18767.809 ms 1 1509 0.26 MB/sec execute 53 sec latency 19770.301 ms 1 1509 0.26 MB/sec execute 54 sec latency 20771.817 ms 1 1509 0.26 MB/sec execute 55 sec latency 21781.018 ms 1 1509 0.25 MB/sec execute 56 sec latency 22781.278 ms oleg336-server: oleg336-server.virtnet: executing set_default_debug -1 all 1 1524 0.25 MB/sec execute 57 sec latency 23502.674 ms pdsh@oleg336-client: oleg336-server: ssh exited with exit code 1 1 1588 0.24 MB/sec execute 58 sec latency 72.130 ms Started lustre-MDT0000 22:50:07 (1788576607) targets are mounted 22:50:07 (1788576607) facet_failover done 1 1634 0.24 MB/sec execute 59 sec latency 222.342 ms 1 1686 0.24 MB/sec execute 60 sec latency 100.179 ms 1 1747 0.23 MB/sec execute 61 sec latency 102.163 ms 1 1820 0.23 MB/sec execute 62 sec latency 88.357 ms 1 1861 0.23 MB/sec execute 63 sec latency 119.266 ms oleg336-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1924 0.23 MB/sec execute 64 sec latency 162.524 ms 1 1986 0.22 MB/sec execute 65 sec latency 86.911 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2024 0.22 MB/sec execute 66 sec latency 106.492 ms 1 2102 0.22 MB/sec execute 67 sec latency 82.903 ms 1 2160 0.22 MB/sec execute 68 sec latency 97.602 ms 1 2193 0.21 MB/sec execute 69 sec latency 140.810 ms 1 2291 0.22 MB/sec execute 70 sec latency 72.734 ms 1 2350 0.22 MB/sec execute 71 sec latency 250.390 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2816 2205696 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 57344 3661824 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 16384 3730432 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7392256 1% /mnt/lustre 1 2383 0.22 MB/sec execute 72 sec latency 197.997 ms 1 2416 0.22 MB/sec execute 73 sec latency 188.546 ms 1 2453 0.22 MB/sec execute 74 sec latency 189.720 ms 1 2488 0.22 MB/sec execute 75 sec latency 232.183 ms 1 2566 0.22 MB/sec execute 76 sec latency 147.577 ms test_26 fail mds1 3 times 1 2566 0.22 MB/sec execute 77 sec latency 1153.015 ms 1 2594 0.22 MB/sec execute 78 sec latency 1305.448 ms Failing mds1 on oleg336-server 1 2754 0.25 MB/sec execute 79 sec latency 84.916 ms Stopping /mnt/lustre-mds1 (opts:) on oleg336-server 1 2876 0.25 MB/sec execute 80 sec latency 213.526 ms 1 2894 0.26 MB/sec execute 81 sec latency 667.987 ms 1 2894 0.25 MB/sec execute 82 sec latency 1668.207 ms 22:50:32 (1788576632) shut down 1 2894 0.25 MB/sec execute 83 sec latency 2668.994 ms facet: mds1 facet_host: oleg336-server facet_failover_host: oleg336-server 1 2894 0.25 MB/sec execute 84 sec latency 3669.207 ms 1 2894 0.24 MB/sec execute 85 sec latency 4669.404 ms 1 2894 0.24 MB/sec execute 86 sec latency 5670.042 ms 1 2894 0.24 MB/sec execute 87 sec latency 6671.243 ms 1 2894 0.24 MB/sec execute 88 sec latency 7671.394 ms 1 2894 0.23 MB/sec execute 89 sec latency 8671.538 ms 1 2894 0.23 MB/sec execute 90 sec latency 9676.581 ms 1 2894 0.23 MB/sec execute 91 sec latency 10676.798 ms 1 2894 0.23 MB/sec execute 92 sec latency 11677.501 ms 1 2894 0.22 MB/sec execute 93 sec latency 12678.415 ms Failover mds1 to oleg336-server mount facets: mds1 1 2894 0.22 MB/sec execute 94 sec latency 13680.748 ms 1 2894 0.22 MB/sec execute 95 sec latency 14680.984 ms 1 2894 0.22 MB/sec execute 96 sec latency 15682.849 ms 1 2894 0.21 MB/sec execute 97 sec latency 16683.494 ms 1 2894 0.21 MB/sec execute 98 sec latency 17683.929 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2894 0.21 MB/sec execute 99 sec latency 18684.344 ms 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 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec oleg336-server: oleg336-server.virtnet: executing set_default_debug -1 all 1 cleanup 114 sec pdsh@oleg336-client: oleg336-server: ssh exited with exit code 1 1 cleanup 115 sec Started lustre-MDT0000 22:51:04 (1788576664) targets are mounted 22:51:04 (1788576664) facet_failover done 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 0 cleanup 126 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 403 109.611 23502.658 Close 346 198.150 41895.205 Rename 18 79.922 143.892 Unlink 42 23.377 53.156 Qpathinfo 364 14.558 86.135 Qfileinfo 114 1.745 14.032 Qfsinfo 54 2.793 16.579 Sfileinfo 50 49.575 106.155 Find 128 5.205 49.737 WriteX 393 11.817 123.223 ReadX 614 1.297 88.951 LockX 2 13.369 15.209 UnlockX 2 10.072 12.135 Flush 35 123.143 250.375 Throughput 0.210047 MB/sec 1 clients 1 procs max_latency=23502.674 ms stopping dbench on /mnt/lustre at Fri Sep 4 22:51:15 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre oleg336-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 Fri Sep 4 22:51:20 EDT 2026 waiting for dbench pid 48261 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 51 2.10 MB/sec warmup 1 sec latency 89.864 ms 1 122 2.75 MB/sec warmup 2 sec latency 118.467 ms 1 165 2.27 MB/sec warmup 3 sec latency 143.487 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3072 2205440 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 51200 3710976 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 28672 3718144 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 79872 7429120 2% /mnt/lustre 1 199 1.96 MB/sec warmup 4 sec latency 131.405 ms 1 247 1.88 MB/sec warmup 5 sec latency 107.981 ms 1 294 1.80 MB/sec warmup 6 sec latency 120.429 ms 1 339 1.75 MB/sec warmup 7 sec latency 123.125 ms 1 389 1.73 MB/sec warmup 8 sec latency 95.906 ms test_26 fail mds1 4 times 1 446 1.74 MB/sec warmup 9 sec latency 90.531 ms Failing mds1 on oleg336-server 1 494 1.72 MB/sec warmup 10 sec latency 106.541 ms Stopping /mnt/lustre-mds1 (opts:) on oleg336-server 1 542 1.73 MB/sec warmup 11 sec latency 170.545 ms 1 636 1.75 MB/sec warmup 12 sec latency 161.014 ms 1 636 1.62 MB/sec warmup 13 sec latency 1152.531 ms 1 636 1.50 MB/sec warmup 14 sec latency 2155.377 ms 22:51:34 (1788576694) shut down facet: mds1 facet_host: oleg336-server facet_failover_host: oleg336-server 1 636 1.40 MB/sec warmup 15 sec latency 3155.702 ms 1 636 1.31 MB/sec warmup 16 sec latency 4156.844 ms 1 636 1.24 MB/sec warmup 17 sec latency 5157.096 ms 1 636 1.17 MB/sec warmup 18 sec latency 6157.482 ms 1 636 1.11 MB/sec warmup 19 sec latency 7157.831 ms 1 636 0.00 MB/sec execute 1 sec latency 9158.290 ms 1 636 0.00 MB/sec execute 2 sec latency 10158.562 ms 1 636 0.00 MB/sec execute 3 sec latency 11162.503 ms 1 636 0.00 MB/sec execute 4 sec latency 12164.833 ms Failover mds1 to oleg336-server mount facets: mds1 1 636 0.00 MB/sec execute 5 sec latency 13166.251 ms 1 636 0.00 MB/sec execute 6 sec latency 14166.760 ms 1 636 0.00 MB/sec execute 7 sec latency 15167.113 ms 1 636 0.00 MB/sec execute 8 sec latency 16167.327 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 636 0.00 MB/sec execute 9 sec latency 17167.544 ms 1 636 0.00 MB/sec execute 10 sec latency 18167.704 ms 1 636 0.00 MB/sec execute 11 sec latency 19168.912 ms 1 636 0.00 MB/sec execute 12 sec latency 20172.768 ms 1 636 0.00 MB/sec execute 13 sec latency 21172.950 ms 1 636 0.00 MB/sec execute 14 sec latency 22173.836 ms 1 636 0.00 MB/sec execute 15 sec latency 23177.183 ms 1 636 0.00 MB/sec execute 16 sec latency 24177.317 ms 1 636 0.00 MB/sec execute 17 sec latency 25177.524 ms 1 636 0.00 MB/sec execute 18 sec latency 26177.697 ms 1 636 0.00 MB/sec execute 19 sec latency 27179.081 ms 1 636 0.00 MB/sec execute 20 sec latency 28179.331 ms 1 636 0.00 MB/sec execute 21 sec latency 29181.369 ms 1 636 0.00 MB/sec execute 22 sec latency 30182.564 ms oleg336-server: oleg336-server.virtnet: executing set_default_debug -1 all 1 636 0.00 MB/sec execute 23 sec latency 31184.713 ms pdsh@oleg336-client: oleg336-server: ssh exited with exit code 1 1 636 0.00 MB/sec execute 24 sec latency 32186.493 ms Started lustre-MDT0000 22:52:05 (1788576725) targets are mounted 22:52:05 (1788576725) facet_failover done 1 636 0.00 MB/sec execute 25 sec latency 33186.736 ms 1 636 0.00 MB/sec execute 26 sec latency 34188.058 ms 1 636 0.00 MB/sec execute 27 sec latency 35188.319 ms 1 636 0.00 MB/sec execute 28 sec latency 36188.584 ms 1 636 0.00 MB/sec execute 29 sec latency 37191.980 ms 1 636 0.00 MB/sec execute 30 sec latency 38192.405 ms 1 636 0.00 MB/sec execute 31 sec latency 39192.752 ms 1 636 0.00 MB/sec execute 32 sec latency 40192.917 ms 1 642 0.00 MB/sec execute 33 sec latency 40897.537 ms 1 669 0.00 MB/sec execute 34 sec latency 234.823 ms 1 700 0.00 MB/sec execute 35 sec latency 198.289 ms 1 728 0.01 MB/sec execute 36 sec latency 214.640 ms 1 759 0.01 MB/sec execute 37 sec latency 172.426 ms oleg336-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 789 0.01 MB/sec execute 38 sec latency 196.228 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 808 0.01 MB/sec execute 39 sec latency 255.258 ms 1 865 0.01 MB/sec execute 40 sec latency 112.515 ms 1 888 0.02 MB/sec execute 41 sec latency 389.015 ms 1 921 0.02 MB/sec execute 42 sec latency 192.681 ms 1 972 0.02 MB/sec execute 43 sec latency 89.701 ms 1 1006 0.02 MB/sec execute 44 sec latency 188.005 ms 1 1074 0.04 MB/sec execute 45 sec latency 175.904 ms 1 1138 0.04 MB/sec execute 46 sec latency 68.731 ms 1 1215 0.04 MB/sec execute 47 sec latency 50.630 ms 1 1263 0.04 MB/sec execute 48 sec latency 70.604 ms 1 1398 0.10 MB/sec execute 49 sec latency 85.718 ms 1 1457 0.10 MB/sec execute 50 sec latency 82.189 ms 1 1504 0.10 MB/sec execute 51 sec latency 263.344 ms 1 1569 0.10 MB/sec execute 52 sec latency 68.922 ms 1 1632 0.10 MB/sec execute 53 sec latency 108.513 ms 1 1686 0.10 MB/sec execute 54 sec latency 237.923 ms 1 1759 0.09 MB/sec execute 55 sec latency 84.124 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Sep 4 22:52:36 EDT 2026 with return code 0 1 1843 0.09 MB/sec execute 56 sec latency 65.386 ms 48261 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48261 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished