== replay-dual test 26: dbench and tar with mds failover ========================================================== 08:29:55 (1789129795) Starting client oleg250-client.virtnet: -o user_xattr,flock 192.168.202.150@tcp:/lustre /mnt/lustre Started clients oleg250-client.virtnet: 192.168.202.150@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 45502 Started dbench loop with 45503 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 18432 3727360 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3751936 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 20480 7479296 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 11 08:30:00 EDT 2026 waiting for dbench pid 45561 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 28 0.91 MB/sec warmup 1 sec latency 25.854 ms 1 89 2.06 MB/sec warmup 2 sec latency 158.546 ms 1 114 1.74 MB/sec warmup 3 sec latency 214.865 ms 1 142 1.50 MB/sec warmup 4 sec latency 284.282 ms 1 179 1.45 MB/sec warmup 5 sec latency 121.045 ms test_26 fail mds1 1 times 1 199 1.30 MB/sec warmup 6 sec latency 167.770 ms 1 231 1.27 MB/sec warmup 7 sec latency 208.684 ms Failing mds1 on oleg250-server 1 271 1.27 MB/sec warmup 8 sec latency 136.745 ms Stopping /mnt/lustre-mds1 (opts:) on oleg250-server 1 297 1.22 MB/sec warmup 9 sec latency 154.925 ms 1 323 1.17 MB/sec warmup 10 sec latency 401.180 ms 1 323 1.07 MB/sec warmup 11 sec latency 1406.594 ms 1 323 0.98 MB/sec warmup 12 sec latency 2407.922 ms 1 323 0.90 MB/sec warmup 13 sec latency 3409.765 ms 1 323 0.84 MB/sec warmup 14 sec latency 4411.009 ms 08:30:14 (1789129814) shut down facet: mds1 facet_host: oleg250-server facet_failover_host: oleg250-server 1 323 0.78 MB/sec warmup 15 sec latency 5411.451 ms 1 323 0.73 MB/sec warmup 16 sec latency 6411.659 ms 1 323 0.69 MB/sec warmup 17 sec latency 7412.119 ms 1 323 0.65 MB/sec warmup 18 sec latency 8412.614 ms 1 323 0.62 MB/sec warmup 19 sec latency 9412.855 ms 1 323 0.00 MB/sec execute 1 sec latency 11413.919 ms 1 323 0.00 MB/sec execute 2 sec latency 12414.367 ms 1 323 0.00 MB/sec execute 3 sec latency 13414.643 ms 1 323 0.00 MB/sec execute 4 sec latency 14415.985 ms Failover mds1 to oleg250-server mount facets: mds1 1 323 0.00 MB/sec execute 5 sec latency 15421.469 ms 1 323 0.00 MB/sec execute 6 sec latency 16424.895 ms 1 323 0.00 MB/sec execute 7 sec latency 17427.168 ms 1 323 0.00 MB/sec execute 8 sec latency 18427.368 ms 1 323 0.00 MB/sec execute 9 sec latency 19428.374 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 323 0.00 MB/sec execute 10 sec latency 20428.623 ms 1 323 0.00 MB/sec execute 11 sec latency 21429.909 ms 1 323 0.00 MB/sec execute 12 sec latency 22430.133 ms 1 323 0.00 MB/sec execute 13 sec latency 23431.718 ms 1 323 0.00 MB/sec execute 14 sec latency 24432.116 ms 1 323 0.00 MB/sec execute 15 sec latency 25432.333 ms 1 323 0.00 MB/sec execute 16 sec latency 26432.707 ms 1 323 0.00 MB/sec execute 17 sec latency 27433.009 ms 1 323 0.00 MB/sec execute 18 sec latency 28433.444 ms 1 323 0.00 MB/sec execute 19 sec latency 29433.894 ms 1 323 0.00 MB/sec execute 20 sec latency 30436.518 ms 1 323 0.00 MB/sec execute 21 sec latency 31439.411 ms 1 323 0.00 MB/sec execute 22 sec latency 32439.637 ms 1 323 0.00 MB/sec execute 23 sec latency 33445.881 ms 1 323 0.00 MB/sec execute 24 sec latency 34446.172 ms oleg250-server: oleg250-server.virtnet: executing set_default_debug -1 all 1 323 0.00 MB/sec execute 25 sec latency 35447.661 ms pdsh@oleg250-client: oleg250-server: ssh exited with exit code 1 1 323 0.00 MB/sec execute 26 sec latency 36449.621 ms Started lustre-MDT0000 08:30:47 (1789129847) targets are mounted 08:30:47 (1789129847) facet_failover done 1 323 0.00 MB/sec execute 27 sec latency 37451.689 ms 1 323 0.00 MB/sec execute 28 sec latency 38451.988 ms 1 323 0.00 MB/sec execute 29 sec latency 39452.233 ms 1 323 0.00 MB/sec execute 30 sec latency 40454.405 ms 1 323 0.00 MB/sec execute 31 sec latency 41455.060 ms 1 323 0.00 MB/sec execute 32 sec latency 42455.402 ms 1 323 0.00 MB/sec execute 33 sec latency 43455.830 ms 1 323 0.00 MB/sec execute 34 sec latency 44456.186 ms 1 323 0.00 MB/sec execute 35 sec latency 45456.597 ms 1 323 0.00 MB/sec execute 36 sec latency 46459.386 ms 1 323 0.00 MB/sec execute 37 sec latency 47464.000 ms 1 323 0.00 MB/sec execute 38 sec latency 48464.684 ms 1 323 0.00 MB/sec execute 39 sec latency 49465.061 ms 1 323 0.00 MB/sec execute 40 sec latency 50465.469 ms 1 323 0.00 MB/sec execute 41 sec latency 51470.327 ms 1 323 0.00 MB/sec execute 42 sec latency 52471.137 ms 1 323 0.00 MB/sec execute 43 sec latency 53471.465 ms 1 324 0.00 MB/sec execute 44 sec latency 54429.873 ms 1 365 0.03 MB/sec execute 45 sec latency 127.753 ms 1 398 0.05 MB/sec execute 46 sec latency 139.258 ms 1 429 0.07 MB/sec execute 47 sec latency 144.601 ms 1 461 0.09 MB/sec execute 48 sec latency 220.760 ms 1 494 0.11 MB/sec execute 49 sec latency 178.644 ms oleg250-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 519 0.12 MB/sec execute 50 sec latency 194.318 ms 1 588 0.17 MB/sec execute 51 sec latency 140.523 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 618 0.18 MB/sec execute 52 sec latency 187.440 ms 1 664 0.18 MB/sec execute 53 sec latency 178.147 ms 1 695 0.17 MB/sec execute 54 sec latency 206.408 ms 1 721 0.17 MB/sec execute 55 sec latency 185.349 ms 1 732 0.17 MB/sec execute 56 sec latency 427.083 ms 1 769 0.17 MB/sec execute 57 sec latency 113.540 ms 1 796 0.17 MB/sec execute 58 sec latency 218.006 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 36864 3686400 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 12288 3723264 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 49152 7409664 1% /mnt/lustre 1 816 0.16 MB/sec execute 59 sec latency 132.213 ms 1 864 0.16 MB/sec execute 60 sec latency 124.278 ms 1 885 0.16 MB/sec execute 61 sec latency 297.246 ms 1 910 0.16 MB/sec execute 62 sec latency 208.937 ms 1 933 0.16 MB/sec execute 63 sec latency 194.703 ms 1 970 0.16 MB/sec execute 64 sec latency 118.521 ms 1 1057 0.17 MB/sec execute 65 sec latency 146.099 ms test_26 fail mds1 2 times 1 1099 0.17 MB/sec execute 66 sec latency 152.353 ms 1 1136 0.17 MB/sec execute 67 sec latency 111.083 ms Failing mds1 on oleg250-server 1 1178 0.17 MB/sec execute 68 sec latency 137.144 ms Stopping /mnt/lustre-mds1 (opts:) on oleg250-server 1 1215 0.16 MB/sec execute 69 sec latency 104.349 ms 1 1225 0.16 MB/sec execute 70 sec latency 557.087 ms 1 1225 0.16 MB/sec execute 71 sec latency 1557.262 ms 1 1225 0.16 MB/sec execute 72 sec latency 2557.510 ms 08:31:33 (1789129893) shut down facet: mds1 facet_host: oleg250-server facet_failover_host: oleg250-server 1 1225 0.15 MB/sec execute 73 sec latency 3558.119 ms 1 1225 0.15 MB/sec execute 74 sec latency 4558.436 ms 1 1225 0.15 MB/sec execute 75 sec latency 5558.614 ms 1 1225 0.15 MB/sec execute 76 sec latency 6560.582 ms 1 1225 0.15 MB/sec execute 77 sec latency 7560.784 ms 1 1225 0.15 MB/sec execute 78 sec latency 8560.958 ms 1 1225 0.14 MB/sec execute 79 sec latency 9562.028 ms 1 1225 0.14 MB/sec execute 80 sec latency 10566.631 ms 1 1225 0.14 MB/sec execute 81 sec latency 11568.424 ms 1 1225 0.14 MB/sec execute 82 sec latency 12568.606 ms Failover mds1 to oleg250-server 1 1225 0.14 MB/sec execute 83 sec latency 13579.515 ms mount facets: mds1 1 1225 0.13 MB/sec execute 84 sec latency 14580.166 ms 1 1225 0.13 MB/sec execute 85 sec latency 15580.450 ms 1 1225 0.13 MB/sec execute 86 sec latency 16580.813 ms 1 1225 0.13 MB/sec execute 87 sec latency 17582.925 ms 1 1225 0.13 MB/sec execute 88 sec latency 18583.737 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1225 0.13 MB/sec execute 89 sec latency 19586.819 ms 1 1225 0.13 MB/sec execute 90 sec latency 20590.876 ms 1 1225 0.12 MB/sec execute 91 sec latency 21595.482 ms 1 1225 0.12 MB/sec execute 92 sec latency 22595.691 ms 1 1225 0.12 MB/sec execute 93 sec latency 23596.041 ms 1 1225 0.12 MB/sec execute 94 sec latency 24596.284 ms 1 1225 0.12 MB/sec execute 95 sec latency 25596.605 ms 1 1225 0.12 MB/sec execute 96 sec latency 26597.508 ms 1 1225 0.12 MB/sec execute 97 sec latency 27599.062 ms 1 1225 0.12 MB/sec execute 98 sec latency 28599.283 ms 1 1225 0.11 MB/sec execute 99 sec latency 29599.500 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg250-server: oleg250-server.virtnet: executing set_default_debug -1 all 1 cleanup 104 sec pdsh@oleg250-client: oleg250-server: ssh exited with exit code 1 1 cleanup 105 sec Started lustre-MDT0000 08:32:06 (1789129926) targets are mounted 08:32:06 (1789129926) facet_failover done 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec 1 cleanup 111 sec 0 cleanup 112 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 128 505.052 54429.858 Close 116 12.872 45.533 Rename 8 113.307 208.914 Unlink 14 31.960 60.783 Qpathinfo 80 518.466 39564.128 Qfileinfo 54 2.154 12.532 Qfsinfo 28 3.407 20.233 Sfileinfo 29 69.071 160.376 Find 37 10.266 120.259 WriteX 258 13.805 66.912 ReadX 127 6.091 124.261 Flush 24 143.846 427.071 Throughput 0.114285 MB/sec 1 clients 1 procs max_latency=54429.873 ms stopping dbench on /mnt/lustre at Fri Sep 11 08:32:12 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg250-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 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 11 08:32:18 EDT 2026 waiting for dbench pid 47530 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 2.08 MB/sec warmup 1 sec latency 78.225 ms 1 104 2.42 MB/sec warmup 2 sec latency 203.140 ms 1 137 2.00 MB/sec warmup 3 sec latency 187.845 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2560 2205952 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 14336 3746816 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 27648 3694592 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 41984 7441408 1% /mnt/lustre 1 155 1.63 MB/sec warmup 4 sec latency 230.608 ms 1 193 1.53 MB/sec warmup 5 sec latency 191.212 ms 1 223 1.43 MB/sec warmup 6 sec latency 182.893 ms 1 254 1.38 MB/sec warmup 7 sec latency 169.869 ms 1 279 1.30 MB/sec warmup 8 sec latency 206.543 ms 1 305 1.24 MB/sec warmup 9 sec latency 224.821 ms 1 331 1.20 MB/sec warmup 10 sec latency 174.148 ms test_26 fail mds1 3 times 1 349 1.14 MB/sec warmup 11 sec latency 315.159 ms 1 389 1.15 MB/sec warmup 12 sec latency 129.659 ms Failing mds1 on oleg250-server 1 413 1.12 MB/sec warmup 13 sec latency 188.593 ms Stopping /mnt/lustre-mds1 (opts:) on oleg250-server 1 445 1.11 MB/sec warmup 14 sec latency 174.660 ms 1 476 1.11 MB/sec warmup 15 sec latency 189.652 ms 1 476 1.04 MB/sec warmup 16 sec latency 1023.265 ms 1 476 0.98 MB/sec warmup 17 sec latency 2023.967 ms 1 476 0.93 MB/sec warmup 18 sec latency 3024.179 ms 08:32:37 (1789129957) shut down facet: mds1 facet_host: oleg250-server facet_failover_host: oleg250-server 1 476 0.88 MB/sec warmup 19 sec latency 4028.139 ms 1 476 0.00 MB/sec execute 1 sec latency 6028.805 ms 1 476 0.00 MB/sec execute 2 sec latency 7029.626 ms 1 476 0.00 MB/sec execute 3 sec latency 8029.832 ms 1 476 0.00 MB/sec execute 4 sec latency 9030.449 ms 1 476 0.00 MB/sec execute 5 sec latency 10031.050 ms 1 476 0.00 MB/sec execute 6 sec latency 11031.247 ms 1 476 0.00 MB/sec execute 7 sec latency 12032.069 ms 1 476 0.00 MB/sec execute 8 sec latency 13035.075 ms Failover mds1 to oleg250-server mount facets: mds1 1 476 0.00 MB/sec execute 9 sec latency 14036.922 ms 1 476 0.00 MB/sec execute 10 sec latency 15037.145 ms 1 476 0.00 MB/sec execute 11 sec latency 16037.412 ms 1 476 0.00 MB/sec execute 12 sec latency 17041.550 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 476 0.00 MB/sec execute 13 sec latency 18043.232 ms 1 476 0.00 MB/sec execute 14 sec latency 19044.096 ms 1 476 0.00 MB/sec execute 15 sec latency 20044.287 ms 1 476 0.00 MB/sec execute 16 sec latency 21046.630 ms 1 476 0.00 MB/sec execute 17 sec latency 22046.830 ms 1 476 0.00 MB/sec execute 18 sec latency 23047.028 ms 1 476 0.00 MB/sec execute 19 sec latency 24049.658 ms 1 476 0.00 MB/sec execute 20 sec latency 25050.137 ms 1 476 0.00 MB/sec execute 21 sec latency 26050.357 ms 1 476 0.00 MB/sec execute 22 sec latency 27050.562 ms 1 476 0.00 MB/sec execute 23 sec latency 28051.084 ms 1 476 0.00 MB/sec execute 24 sec latency 29051.331 ms 1 476 0.00 MB/sec execute 25 sec latency 30058.621 ms 1 476 0.00 MB/sec execute 26 sec latency 31058.915 ms 1 476 0.00 MB/sec execute 27 sec latency 32059.238 ms 1 476 0.00 MB/sec execute 28 sec latency 33059.573 ms oleg250-server: oleg250-server.virtnet: executing set_default_debug -1 all 1 476 0.00 MB/sec execute 29 sec latency 34061.901 ms 1 476 0.00 MB/sec execute 30 sec latency 35062.110 ms pdsh@oleg250-client: oleg250-server: ssh exited with exit code 1 1 476 0.00 MB/sec execute 31 sec latency 36064.604 ms Started lustre-MDT0000 08:33:10 (1789129990) targets are mounted 08:33:10 (1789129990) facet_failover done 1 476 0.00 MB/sec execute 32 sec latency 37064.832 ms 1 476 0.00 MB/sec execute 33 sec latency 38065.121 ms 1 476 0.00 MB/sec execute 34 sec latency 39065.319 ms 1 476 0.00 MB/sec execute 35 sec latency 40070.115 ms 1 476 0.00 MB/sec execute 36 sec latency 41073.308 ms 1 477 0.00 MB/sec execute 37 sec latency 41866.508 ms 1 489 0.01 MB/sec execute 38 sec latency 551.638 ms 1 511 0.03 MB/sec execute 39 sec latency 200.730 ms 1 554 0.06 MB/sec execute 40 sec latency 193.836 ms 1 636 0.11 MB/sec execute 41 sec latency 95.372 ms 1 664 0.11 MB/sec execute 42 sec latency 199.219 ms oleg250-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 692 0.10 MB/sec execute 43 sec latency 225.157 ms 1 721 0.10 MB/sec execute 44 sec latency 219.959 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 745 0.10 MB/sec execute 45 sec latency 323.703 ms 1 789 0.10 MB/sec execute 46 sec latency 145.553 ms 1 815 0.10 MB/sec execute 47 sec latency 147.580 ms 1 872 0.10 MB/sec execute 48 sec latency 127.047 ms 1 905 0.10 MB/sec execute 49 sec latency 207.232 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 937 0.10 MB/sec execute 50 sec latency 226.590 ms 1 977 0.10 MB/sec execute 51 sec latency 150.308 ms 1 1051 0.12 MB/sec execute 52 sec latency 118.284 ms 1 1143 0.12 MB/sec execute 53 sec latency 60.481 ms 1 1192 0.12 MB/sec execute 54 sec latency 135.120 ms 1 1244 0.12 MB/sec execute 55 sec latency 66.124 ms 1 1382 0.17 MB/sec execute 56 sec latency 82.395 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 1 1430 0.16 MB/sec execute 57 sec latency 107.511 ms stopping dbench on /mnt/lustre at Fri Sep 11 08:33:36 EDT 2026 with return code 0 47530 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47530 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished