== replay-dual test 26: dbench and tar with mds failover ========================================================== 02:35:10 (1775198110) Starting client oleg440-client.virtnet: -o user_xattr,flock 192.168.204.140@tcp:/lustre /mnt/lustre Started clients oleg440-client.virtnet: 192.168.204.140@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,encrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65562 Started dbench loop with 65563 striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H all_char /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 1968 1269336 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3588920 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7194396 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 Apr 3 02:35:17 EDT 2026 waiting for dbench pid 65640 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 64.410 ms 1 51 1.04 MB/sec warmup 2 sec latency 192.853 ms 1 92 1.39 MB/sec warmup 3 sec latency 163.317 ms 1 129 1.43 MB/sec warmup 4 sec latency 155.551 ms 1 157 1.30 MB/sec warmup 5 sec latency 203.346 ms 1 184 1.22 MB/sec warmup 6 sec latency 135.076 ms 1 200 1.11 MB/sec warmup 7 sec latency 499.647 ms 1 231 1.11 MB/sec warmup 8 sec latency 144.790 ms 1 271 1.13 MB/sec warmup 9 sec latency 141.806 ms test_26 fail mds1 1 times 1 305 1.12 MB/sec warmup 10 sec latency 140.169 ms 1 331 1.09 MB/sec warmup 11 sec latency 228.076 ms Failing mds1 on oleg440-server 1 357 1.06 MB/sec warmup 12 sec latency 159.890 ms Stopping /mnt/lustre-mds1 (opts:) on oleg440-server 1 382 1.04 MB/sec warmup 13 sec latency 163.073 ms 1 413 1.04 MB/sec warmup 14 sec latency 243.794 ms 1 445 1.04 MB/sec warmup 15 sec latency 283.533 ms 1 485 1.06 MB/sec warmup 16 sec latency 136.660 ms 02:35:33 (1775198133) shut down facet: mds1 facet_host: oleg440-server facet_failover_host: oleg440-server 1 501 1.02 MB/sec warmup 17 sec latency 560.150 ms 1 501 0.97 MB/sec warmup 18 sec latency 1562.322 ms 1 501 0.92 MB/sec warmup 19 sec latency 2562.656 ms 1 501 0.00 MB/sec execute 1 sec latency 4564.719 ms 1 501 0.00 MB/sec execute 2 sec latency 5565.435 ms 1 501 0.00 MB/sec execute 3 sec latency 6567.048 ms 1 501 0.00 MB/sec execute 4 sec latency 7568.068 ms 1 501 0.00 MB/sec execute 5 sec latency 8568.519 ms 1 501 0.00 MB/sec execute 6 sec latency 9575.238 ms Failover mds1 to oleg440-server 1 501 0.00 MB/sec execute 7 sec latency 10575.628 ms mount facets: mds1 1 501 0.00 MB/sec execute 8 sec latency 11575.908 ms 1 501 0.00 MB/sec execute 9 sec latency 12576.275 ms 1 501 0.00 MB/sec execute 10 sec latency 13577.717 ms 1 501 0.00 MB/sec execute 11 sec latency 14579.633 ms 1 501 0.00 MB/sec execute 12 sec latency 15580.020 ms 1 501 0.00 MB/sec execute 13 sec latency 16580.504 ms 1 501 0.00 MB/sec execute 14 sec latency 17580.832 ms 1 501 0.00 MB/sec execute 15 sec latency 18581.130 ms 1 501 0.00 MB/sec execute 16 sec latency 19583.653 ms 1 501 0.00 MB/sec execute 17 sec latency 20583.885 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 501 0.00 MB/sec execute 18 sec latency 21584.237 ms 1 501 0.00 MB/sec execute 19 sec latency 22584.543 ms 1 501 0.00 MB/sec execute 20 sec latency 23584.830 ms 1 501 0.00 MB/sec execute 21 sec latency 24585.095 ms 1 501 0.00 MB/sec execute 22 sec latency 25585.342 ms 1 501 0.00 MB/sec execute 23 sec latency 26585.712 ms 1 501 0.00 MB/sec execute 24 sec latency 27586.106 ms 1 501 0.00 MB/sec execute 25 sec latency 28586.937 ms 1 501 0.00 MB/sec execute 26 sec latency 29587.297 ms 1 501 0.00 MB/sec execute 27 sec latency 30587.703 ms 1 501 0.00 MB/sec execute 28 sec latency 31588.093 ms oleg440-server: oleg440-server.virtnet: executing set_default_debug -1 all 1 501 0.00 MB/sec execute 29 sec latency 32588.348 ms pdsh@oleg440-client: oleg440-server: ssh exited with exit code 1 1 501 0.00 MB/sec execute 30 sec latency 33588.642 ms Started lustre-MDT0000 02:36:08 (1775198168) targets are mounted 02:36:08 (1775198168) facet_failover done 1 501 0.00 MB/sec execute 31 sec latency 34589.444 ms 1 511 0.01 MB/sec execute 32 sec latency 35310.620 ms 1 552 0.05 MB/sec execute 33 sec latency 138.082 ms 1 603 0.10 MB/sec execute 34 sec latency 444.095 ms 1 652 0.10 MB/sec execute 35 sec latency 181.211 ms oleg440-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 689 0.10 MB/sec execute 36 sec latency 106.486 ms 1 713 0.10 MB/sec execute 37 sec latency 150.099 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 741 0.10 MB/sec execute 38 sec latency 130.044 ms 1 780 0.10 MB/sec execute 39 sec latency 117.717 ms 1 817 0.10 MB/sec execute 40 sec latency 128.313 ms 1 873 0.10 MB/sec execute 41 sec latency 103.591 ms 1 902 0.10 MB/sec execute 42 sec latency 111.991 ms 1 942 0.10 MB/sec execute 43 sec latency 106.735 ms 1 980 0.10 MB/sec execute 44 sec latency 105.452 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2100 1269204 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1872 1269432 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 38296 3562916 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 9100 3595320 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 47396 7158236 1% /mnt/lustre 1 1020 0.11 MB/sec execute 45 sec latency 123.511 ms 1 1067 0.12 MB/sec execute 46 sec latency 79.753 ms 1 1117 0.12 MB/sec execute 47 sec latency 131.010 ms 1 1147 0.12 MB/sec execute 48 sec latency 118.295 ms 1 1172 0.11 MB/sec execute 49 sec latency 263.394 ms 1 1173 0.11 MB/sec execute 50 sec latency 1244.783 ms 1 1173 0.11 MB/sec execute 51 sec latency 1019.678 ms 1 1178 0.11 MB/sec execute 52 sec latency 1772.813 ms 1 1211 0.11 MB/sec execute 53 sec latency 116.037 ms 1 1242 0.10 MB/sec execute 54 sec latency 111.565 ms 1 1278 0.10 MB/sec execute 55 sec latency 116.253 ms test_26 fail mds2 2 times 1 1406 0.15 MB/sec execute 56 sec latency 137.850 ms 1 1433 0.15 MB/sec execute 57 sec latency 162.093 ms Failing mds2 on oleg440-server 1 1473 0.15 MB/sec execute 58 sec latency 105.225 ms Stopping /mnt/lustre-mds2 (opts:) on oleg440-server 1 1509 0.15 MB/sec execute 59 sec latency 116.618 ms 1 1538 0.14 MB/sec execute 60 sec latency 436.946 ms 1 1538 0.14 MB/sec execute 61 sec latency 1440.208 ms 1 1538 0.14 MB/sec execute 62 sec latency 2442.569 ms 1 1538 0.14 MB/sec execute 63 sec latency 3444.390 ms 1 1538 0.13 MB/sec execute 64 sec latency 4444.714 ms 1 1538 0.13 MB/sec execute 65 sec latency 5445.100 ms 1 1538 0.13 MB/sec execute 66 sec latency 6445.376 ms 1 1538 0.13 MB/sec execute 67 sec latency 7445.584 ms 1 1538 0.13 MB/sec execute 68 sec latency 8446.548 ms 02:36:45 (1775198205) shut down facet: mds2 facet_host: oleg440-server facet_failover_host: oleg440-server 1 1538 0.12 MB/sec execute 69 sec latency 9447.044 ms 1 1538 0.12 MB/sec execute 70 sec latency 10447.382 ms 1 1538 0.12 MB/sec execute 71 sec latency 11448.518 ms 1 1538 0.12 MB/sec execute 72 sec latency 12448.841 ms 1 1538 0.12 MB/sec execute 73 sec latency 13449.214 ms 1 1538 0.12 MB/sec execute 74 sec latency 14449.885 ms 1 1538 0.11 MB/sec execute 75 sec latency 15452.535 ms 1 1538 0.11 MB/sec execute 76 sec latency 16452.810 ms 1 1538 0.11 MB/sec execute 77 sec latency 17453.511 ms 1 1538 0.11 MB/sec execute 78 sec latency 18453.890 ms Failover mds2 to oleg440-server mount facets: mds2 1 1538 0.11 MB/sec execute 79 sec latency 19459.326 ms 1 1538 0.11 MB/sec execute 80 sec latency 20459.537 ms 1 1538 0.11 MB/sec execute 81 sec latency 21459.921 ms 1 1538 0.11 MB/sec execute 82 sec latency 22461.154 ms 1 1538 0.10 MB/sec execute 83 sec latency 23461.382 ms 1 1538 0.10 MB/sec execute 84 sec latency 24461.758 ms 1 1538 0.10 MB/sec execute 85 sec latency 25462.213 ms 1 1538 0.10 MB/sec execute 86 sec latency 26463.317 ms 1 1538 0.10 MB/sec execute 87 sec latency 27466.898 ms 1 1538 0.10 MB/sec execute 88 sec latency 28467.087 ms 1 1538 0.10 MB/sec execute 89 sec latency 29468.659 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 1538 0.10 MB/sec execute 90 sec latency 30469.192 ms 1 1538 0.09 MB/sec execute 91 sec latency 31469.672 ms 1 1538 0.09 MB/sec execute 92 sec latency 32469.861 ms 1 1538 0.09 MB/sec execute 93 sec latency 33470.290 ms 1 1538 0.09 MB/sec execute 94 sec latency 34475.598 ms 1 1538 0.09 MB/sec execute 95 sec latency 35477.168 ms 1 1538 0.09 MB/sec execute 96 sec latency 36480.495 ms 1 1538 0.09 MB/sec execute 97 sec latency 37480.830 ms oleg440-server: oleg440-server.virtnet: executing set_default_debug -1 all 1 1538 0.09 MB/sec execute 98 sec latency 38481.237 ms 1 1538 0.09 MB/sec execute 99 sec latency 39481.456 ms pdsh@oleg440-client: oleg440-server: ssh exited with exit code 1 1 cleanup 100 sec Started lustre-MDT0001 02:37:18 (1775198238) targets are mounted 02:37:18 (1775198238) facet_failover done 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 0 cleanup 105 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 157 562.029 40543.343 Close 132 14.627 55.323 Rename 10 106.149 160.892 Unlink 20 28.693 51.724 Qpathinfo 125 21.564 141.226 Qfileinfo 41 3.609 21.409 Qfsinfo 33 5.882 47.564 Sfileinfo 34 73.057 130.029 Find 54 13.991 82.181 WriteX 170 15.148 96.983 ReadX 237 0.084 2.841 Flush 25 56.480 128.296 Throughput 0.0870934 MB/sec 1 clients 1 procs max_latency=39481.456 ms stopping dbench on /mnt/lustre at Fri Apr 3 02:37:22 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg440-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench mdc.lustre-MDT0001-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 Apr 3 02:37:33 EDT 2026 waiting for dbench pid 67744 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 8 0.00 MB/sec warmup 1 sec latency 160.219 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2372 1268932 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2112 1269192 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 16032 3585804 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 26440 3579044 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 42472 7164848 1% /mnt/lustre 1 49 1.01 MB/sec warmup 2 sec latency 127.315 ms 1 92 1.40 MB/sec warmup 3 sec latency 163.735 ms 1 121 1.37 MB/sec warmup 4 sec latency 225.616 ms 1 146 1.25 MB/sec warmup 5 sec latency 211.545 ms 1 171 1.17 MB/sec warmup 6 sec latency 188.831 ms 1 190 1.08 MB/sec warmup 7 sec latency 334.362 ms 1 215 1.04 MB/sec warmup 8 sec latency 244.422 ms 1 247 1.04 MB/sec warmup 9 sec latency 146.466 ms 1 275 1.02 MB/sec warmup 10 sec latency 149.790 ms 1 308 1.02 MB/sec warmup 11 sec latency 130.697 ms 1 341 1.02 MB/sec warmup 12 sec latency 110.893 ms test_26 fail mds1 3 times 1 379 1.04 MB/sec warmup 13 sec latency 134.250 ms 1 406 1.02 MB/sec warmup 14 sec latency 140.933 ms 1 437 1.02 MB/sec warmup 15 sec latency 199.441 ms Failing mds1 on oleg440-server 1 468 1.03 MB/sec warmup 16 sec latency 155.141 ms Stopping /mnt/lustre-mds1 (opts:) on oleg440-server 1 499 1.02 MB/sec warmup 17 sec latency 152.484 ms 1 527 1.01 MB/sec warmup 18 sec latency 175.179 ms 1 606 1.10 MB/sec warmup 19 sec latency 125.828 ms 02:37:54 (1775198274) shut down facet: mds1 facet_host: oleg440-server facet_failover_host: oleg440-server 1 606 0.00 MB/sec execute 1 sec latency 2065.219 ms 1 606 0.00 MB/sec execute 2 sec latency 3065.738 ms 1 606 0.00 MB/sec execute 3 sec latency 4065.943 ms 1 606 0.00 MB/sec execute 4 sec latency 5066.168 ms 1 606 0.00 MB/sec execute 5 sec latency 6066.392 ms 1 606 0.00 MB/sec execute 6 sec latency 7070.070 ms 1 606 0.00 MB/sec execute 7 sec latency 8070.282 ms 1 606 0.00 MB/sec execute 8 sec latency 9071.299 ms 1 606 0.00 MB/sec execute 9 sec latency 10072.313 ms 1 606 0.00 MB/sec execute 10 sec latency 11072.531 ms Failover mds1 to oleg440-server mount facets: mds1 1 606 0.00 MB/sec execute 11 sec latency 12079.087 ms 1 606 0.00 MB/sec execute 12 sec latency 13079.312 ms 1 606 0.00 MB/sec execute 13 sec latency 14079.609 ms 1 606 0.00 MB/sec execute 14 sec latency 15079.823 ms 1 606 0.00 MB/sec execute 15 sec latency 16096.909 ms 1 606 0.00 MB/sec execute 16 sec latency 17097.220 ms 1 606 0.00 MB/sec execute 17 sec latency 18097.845 ms 1 606 0.00 MB/sec execute 18 sec latency 19098.435 ms 1 606 0.00 MB/sec execute 19 sec latency 20101.889 ms 1 606 0.00 MB/sec execute 20 sec latency 21102.198 ms 1 606 0.00 MB/sec execute 21 sec latency 22119.849 ms 1 606 0.00 MB/sec execute 22 sec latency 23122.098 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 606 0.00 MB/sec execute 23 sec latency 24122.973 ms 1 606 0.00 MB/sec execute 24 sec latency 25124.377 ms 1 606 0.00 MB/sec execute 25 sec latency 26126.113 ms 1 606 0.00 MB/sec execute 26 sec latency 27126.396 ms 1 606 0.00 MB/sec execute 27 sec latency 28128.858 ms 1 606 0.00 MB/sec execute 28 sec latency 29129.156 ms 1 606 0.00 MB/sec execute 29 sec latency 30130.895 ms 1 606 0.00 MB/sec execute 30 sec latency 31131.752 ms 1 606 0.00 MB/sec execute 31 sec latency 32132.026 ms 1 606 0.00 MB/sec execute 32 sec latency 33132.640 ms 1 606 0.00 MB/sec execute 33 sec latency 34134.207 ms oleg440-server: oleg440-server.virtnet: executing set_default_debug -1 all 1 606 0.00 MB/sec execute 34 sec latency 35134.397 ms pdsh@oleg440-client: oleg440-server: ssh exited with exit code 1 1 606 0.00 MB/sec execute 35 sec latency 36134.640 ms Started lustre-MDT0000 02:38:29 (1775198309) targets are mounted 02:38:29 (1775198309) facet_failover done 1 606 0.00 MB/sec execute 36 sec latency 37136.296 ms 1 616 0.00 MB/sec execute 37 sec latency 37889.749 ms 1 661 0.00 MB/sec execute 38 sec latency 108.312 ms 1 695 0.01 MB/sec execute 39 sec latency 147.395 ms 1 720 0.01 MB/sec execute 40 sec latency 180.946 ms oleg440-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 728 0.01 MB/sec execute 41 sec latency 875.700 ms 1 767 0.01 MB/sec execute 42 sec latency 122.515 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 796 0.01 MB/sec execute 43 sec latency 185.549 ms 1 821 0.01 MB/sec execute 44 sec latency 126.420 ms 1 874 0.02 MB/sec execute 45 sec latency 106.829 ms 1 899 0.02 MB/sec execute 46 sec latency 129.440 ms 1 919 0.02 MB/sec execute 47 sec latency 165.962 ms 1 955 0.02 MB/sec execute 48 sec latency 166.296 ms 1 983 0.02 MB/sec execute 49 sec latency 121.285 ms 1 1041 0.04 MB/sec execute 50 sec latency 138.887 ms 1 1082 0.04 MB/sec execute 51 sec latency 86.059 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1132 0.04 MB/sec execute 52 sec latency 84.754 ms 1 1172 0.04 MB/sec execute 53 sec latency 123.115 ms 1 1210 0.04 MB/sec execute 54 sec latency 92.194 ms 1 1236 0.04 MB/sec execute 55 sec latency 113.371 ms 1 1269 0.04 MB/sec execute 56 sec latency 170.406 ms 1 1319 0.06 MB/sec execute 57 sec latency 710.133 ms 1 1399 0.09 MB/sec execute 58 sec latency 729.599 ms 1 1426 0.09 MB/sec execute 59 sec latency 155.242 ms 1 1459 0.08 MB/sec execute 60 sec latency 99.906 ms 1 1489 0.08 MB/sec execute 61 sec latency 142.643 ms 1 1523 0.08 MB/sec execute 62 sec latency 132.734 ms 1 1560 0.08 MB/sec execute 63 sec latency 112.499 ms 1 1580 0.08 MB/sec execute 64 sec latency 123.846 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Apr 3 02:38:58 EDT 2026 with return code 0 1 1609 0.08 MB/sec execute 65 sec latency 128.242 ms 67744 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67744 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished