== replay-dual test 26: dbench and tar with mds failover ========================================================== 16:57:23 (1790715443) Starting client oleg354-client.virtnet: -o user_xattr,flock 192.168.203.154@tcp:/lustre /mnt/lustre Started clients oleg354-client.virtnet: 192.168.203.154@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 65614 Started dbench loop with 65615 striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre/d26.replay-dual/run_tar 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 1768 1269536 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3588900 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7194376 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 Tue Sep 29 16:57:29 EDT 2026 waiting for dbench pid 65694 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 29 0.98 MB/sec warmup 1 sec latency 5.632 ms 1 91 2.09 MB/sec warmup 2 sec latency 108.257 ms 1 129 1.92 MB/sec warmup 3 sec latency 204.887 ms 1 170 1.73 MB/sec warmup 4 sec latency 146.875 ms 1 206 1.62 MB/sec warmup 5 sec latency 262.124 ms 1 239 1.52 MB/sec warmup 6 sec latency 120.425 ms 1 287 1.53 MB/sec warmup 7 sec latency 140.983 ms 1 324 1.47 MB/sec warmup 8 sec latency 181.187 ms test_26 fail mds1 1 times 1 358 1.42 MB/sec warmup 9 sec latency 134.984 ms 1 398 1.41 MB/sec warmup 10 sec latency 98.833 ms Failing mds1 on oleg354-server 1 437 1.40 MB/sec warmup 11 sec latency 146.384 ms Stopping /mnt/lustre-mds1 (opts:) on oleg354-server 1 477 1.39 MB/sec warmup 12 sec latency 107.731 ms 1 485 1.30 MB/sec warmup 13 sec latency 830.808 ms 1 485 1.21 MB/sec warmup 14 sec latency 1830.974 ms 16:57:44 (1790715464) shut down facet: mds1 facet_host: oleg354-server facet_failover_host: oleg354-server 1 485 1.13 MB/sec warmup 15 sec latency 2834.316 ms 1 485 1.06 MB/sec warmup 16 sec latency 3834.527 ms 1 485 1.00 MB/sec warmup 17 sec latency 4834.790 ms 1 485 0.94 MB/sec warmup 18 sec latency 5837.113 ms 1 485 0.89 MB/sec warmup 19 sec latency 6837.290 ms 1 485 0.00 MB/sec execute 1 sec latency 8838.314 ms 1 485 0.00 MB/sec execute 2 sec latency 9838.466 ms 1 485 0.00 MB/sec execute 3 sec latency 10841.673 ms 1 485 0.00 MB/sec execute 4 sec latency 11842.335 ms Failover mds1 to oleg354-server 1 485 0.00 MB/sec execute 5 sec latency 12850.472 ms mount facets: mds1 1 485 0.00 MB/sec execute 6 sec latency 13853.278 ms 1 485 0.00 MB/sec execute 7 sec latency 14853.481 ms 1 485 0.00 MB/sec execute 8 sec latency 15853.701 ms 1 485 0.00 MB/sec execute 9 sec latency 16853.996 ms 1 485 0.00 MB/sec execute 10 sec latency 17854.171 ms 1 485 0.00 MB/sec execute 11 sec latency 18863.885 ms 1 485 0.00 MB/sec execute 12 sec latency 19864.027 ms 1 485 0.00 MB/sec execute 13 sec latency 20867.493 ms 1 485 0.00 MB/sec execute 14 sec latency 21868.222 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 485 0.00 MB/sec execute 15 sec latency 22868.514 ms 1 485 0.00 MB/sec execute 16 sec latency 23868.920 ms 1 485 0.00 MB/sec execute 17 sec latency 24870.305 ms 1 485 0.00 MB/sec execute 18 sec latency 25871.450 ms 1 485 0.00 MB/sec execute 19 sec latency 26871.638 ms 1 485 0.00 MB/sec execute 20 sec latency 27872.159 ms 1 485 0.00 MB/sec execute 21 sec latency 28873.256 ms 1 485 0.00 MB/sec execute 22 sec latency 29873.441 ms 1 485 0.00 MB/sec execute 23 sec latency 30873.779 ms 1 485 0.00 MB/sec execute 24 sec latency 31873.951 ms 1 485 0.00 MB/sec execute 25 sec latency 32874.205 ms 1 485 0.00 MB/sec execute 26 sec latency 33876.252 ms 1 485 0.00 MB/sec execute 27 sec latency 34877.519 ms 1 485 0.00 MB/sec execute 28 sec latency 35880.817 ms oleg354-server: oleg354-server.virtnet: executing set_default_debug -1 all 1 485 0.00 MB/sec execute 29 sec latency 36881.389 ms pdsh@oleg354-client: oleg354-server: ssh exited with exit code 1 1 485 0.00 MB/sec execute 30 sec latency 37881.564 ms Started lustre-MDT0000 16:58:20 (1790715500) targets are mounted 16:58:20 (1790715500) facet_failover done 1 492 0.01 MB/sec execute 31 sec latency 38816.171 ms 1 542 0.07 MB/sec execute 32 sec latency 99.497 ms 1 574 0.07 MB/sec execute 33 sec latency 757.890 ms 1 639 0.12 MB/sec execute 34 sec latency 94.637 ms 1 678 0.12 MB/sec execute 35 sec latency 100.676 ms 1 712 0.12 MB/sec execute 36 sec latency 123.863 ms oleg354-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 747 0.12 MB/sec execute 37 sec latency 137.294 ms 1 780 0.12 MB/sec execute 38 sec latency 115.031 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 815 0.12 MB/sec execute 39 sec latency 131.326 ms 1 870 0.12 MB/sec execute 40 sec latency 90.638 ms 1 902 0.12 MB/sec execute 41 sec latency 148.322 ms 1 936 0.11 MB/sec execute 42 sec latency 89.665 ms 1 980 0.12 MB/sec execute 43 sec latency 106.394 ms 1 1028 0.13 MB/sec execute 44 sec latency 131.155 ms 1 1074 0.13 MB/sec execute 45 sec latency 91.791 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2180 1269124 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1956 1269348 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 42532 3560136 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 12284 3594220 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 54816 7154356 1% /mnt/lustre 1 1119 0.13 MB/sec execute 46 sec latency 118.300 ms 1 1150 0.13 MB/sec execute 47 sec latency 131.991 ms 1 1172 0.13 MB/sec execute 48 sec latency 497.380 ms 1 1178 0.12 MB/sec execute 49 sec latency 1072.201 ms 1 1221 0.12 MB/sec execute 50 sec latency 88.884 ms 1 1252 0.12 MB/sec execute 51 sec latency 141.867 ms 1 1384 0.17 MB/sec execute 52 sec latency 84.159 ms 1 1426 0.17 MB/sec execute 53 sec latency 97.701 ms 1 1470 0.17 MB/sec execute 54 sec latency 123.387 ms 1 1512 0.17 MB/sec execute 55 sec latency 96.721 ms test_26 fail mds2 2 times 1 1560 0.16 MB/sec execute 56 sec latency 94.505 ms 1 1588 0.16 MB/sec execute 57 sec latency 78.858 ms Failing mds2 on oleg354-server 1 1632 0.16 MB/sec execute 58 sec latency 105.843 ms Stopping /mnt/lustre-mds2 (opts:) on oleg354-server 1 1665 0.16 MB/sec execute 59 sec latency 135.153 ms 1 1713 0.15 MB/sec execute 60 sec latency 141.657 ms 1 1775 0.15 MB/sec execute 61 sec latency 81.930 ms 1 1836 0.15 MB/sec execute 62 sec latency 91.053 ms 16:58:52 (1790715532) shut down facet: mds2 facet_host: oleg354-server facet_failover_host: oleg354-server 1 1896 0.15 MB/sec execute 63 sec latency 85.016 ms 1 1986 0.15 MB/sec execute 64 sec latency 73.351 ms 1 2069 0.15 MB/sec execute 65 sec latency 72.164 ms 1 2154 0.15 MB/sec execute 66 sec latency 108.160 ms 1 2226 0.15 MB/sec execute 67 sec latency 78.828 ms 1 2259 0.14 MB/sec execute 68 sec latency 749.540 ms 1 2259 0.14 MB/sec execute 69 sec latency 1749.750 ms 1 2259 0.14 MB/sec execute 70 sec latency 2751.617 ms 1 2259 0.14 MB/sec execute 71 sec latency 3752.124 ms 1 2259 0.14 MB/sec execute 72 sec latency 4753.195 ms Failover mds2 to oleg354-server mount facets: mds2 1 2259 0.13 MB/sec execute 73 sec latency 5753.682 ms 1 2259 0.13 MB/sec execute 74 sec latency 6758.579 ms 1 2259 0.13 MB/sec execute 75 sec latency 7758.798 ms 1 2259 0.13 MB/sec execute 76 sec latency 8766.406 ms 1 2259 0.13 MB/sec execute 77 sec latency 9766.630 ms 1 2259 0.13 MB/sec execute 78 sec latency 10766.885 ms 1 2259 0.12 MB/sec execute 79 sec latency 11767.065 ms 1 2259 0.12 MB/sec execute 80 sec latency 12768.528 ms 1 2259 0.12 MB/sec execute 81 sec latency 13768.651 ms 1 2259 0.12 MB/sec execute 82 sec latency 14769.339 ms 1 2259 0.12 MB/sec execute 83 sec latency 15769.640 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.12 MB/sec execute 84 sec latency 16769.833 ms 1 2259 0.12 MB/sec execute 85 sec latency 17770.059 ms 1 2259 0.11 MB/sec execute 86 sec latency 18771.078 ms 1 2259 0.11 MB/sec execute 87 sec latency 19779.352 ms 1 2259 0.11 MB/sec execute 88 sec latency 20779.787 ms 1 2259 0.11 MB/sec execute 89 sec latency 21779.976 ms oleg354-server: oleg354-server.virtnet: executing set_default_debug -1 all 1 2259 0.11 MB/sec execute 90 sec latency 22780.221 ms pdsh@oleg354-client: oleg354-server: ssh exited with exit code 1 1 2259 0.11 MB/sec execute 91 sec latency 23780.442 ms Started lustre-MDT0001 16:59:21 (1790715561) targets are mounted 16:59:21 (1790715561) facet_failover done 1 2264 0.11 MB/sec execute 92 sec latency 24653.150 ms 1 2342 0.12 MB/sec execute 93 sec latency 132.869 ms 1 2377 0.12 MB/sec execute 94 sec latency 121.152 ms 1 2412 0.12 MB/sec execute 95 sec latency 167.326 ms 1 2441 0.12 MB/sec execute 96 sec latency 115.961 ms 1 2479 0.12 MB/sec execute 97 sec latency 104.839 ms 1 2558 0.12 MB/sec execute 98 sec latency 165.680 ms oleg354-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2588 0.12 MB/sec execute 99 sec latency 94.822 ms 1 cleanup 100 sec 1 cleanup 101 sec mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 0 cleanup 105 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 365 224.563 38816.156 Close 312 11.438 70.701 Rename 17 108.394 181.696 Unlink 40 23.923 55.043 Qpathinfo 349 16.657 118.674 Qfileinfo 85 1.999 15.309 Qfsinfo 47 3.737 19.887 Sfileinfo 50 65.243 148.308 Find 123 13.692 43.243 WriteX 285 12.575 63.780 ReadX 431 2.803 118.287 Flush 34 56.974 122.851 Throughput 0.121564 MB/sec 1 clients 1 procs max_latency=38816.171 ms stopping dbench on /mnt/lustre at Tue Sep 29 16:59:34 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H all_char /mnt/lustre2/d26.replay-dual/run_dbench UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2404 1268900 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2196 1269108 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13500 3593404 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 13576 3593268 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27076 7186672 1% /mnt/lustre 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 Tue Sep 29 16:59:43 EDT 2026 waiting for dbench pid 67892 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 371.127 ms 0 8 0.00 MB/sec warmup 2 sec latency 1371.485 ms 1 38 0.44 MB/sec warmup 3 sec latency 82.966 ms 1 91 1.05 MB/sec warmup 4 sec latency 143.617 ms 1 134 1.18 MB/sec warmup 5 sec latency 146.221 ms test_26 fail mds1 3 times 1 164 1.13 MB/sec warmup 6 sec latency 187.645 ms 1 186 1.06 MB/sec warmup 7 sec latency 469.018 ms Failing mds1 on oleg354-server 1 211 1.02 MB/sec warmup 8 sec latency 176.447 ms Stopping /mnt/lustre-mds1 (opts:) on oleg354-server 1 247 1.04 MB/sec warmup 9 sec latency 105.443 ms 1 287 1.07 MB/sec warmup 10 sec latency 237.968 ms 1 287 0.97 MB/sec warmup 11 sec latency 1238.262 ms 1 287 0.89 MB/sec warmup 12 sec latency 2238.498 ms 1 287 0.82 MB/sec warmup 13 sec latency 3238.704 ms 1 287 0.76 MB/sec warmup 14 sec latency 4238.961 ms 1 287 0.71 MB/sec warmup 15 sec latency 5239.221 ms 1 287 0.67 MB/sec warmup 16 sec latency 6239.576 ms 1 287 0.63 MB/sec warmup 17 sec latency 7243.754 ms 17:00:01 (1790715601) shut down 1 287 0.59 MB/sec warmup 18 sec latency 8245.938 ms facet: mds1 facet_host: oleg354-server facet_failover_host: oleg354-server 1 287 0.56 MB/sec warmup 19 sec latency 9249.295 ms 1 287 0.00 MB/sec execute 1 sec latency 11250.656 ms 1 287 0.00 MB/sec execute 2 sec latency 12252.436 ms 1 287 0.00 MB/sec execute 3 sec latency 13252.737 ms 1 287 0.00 MB/sec execute 4 sec latency 14252.971 ms 1 287 0.00 MB/sec execute 5 sec latency 15254.358 ms 1 287 0.00 MB/sec execute 6 sec latency 16255.720 ms 1 287 0.00 MB/sec execute 7 sec latency 17255.908 ms 1 287 0.00 MB/sec execute 8 sec latency 18257.943 ms Failover mds1 to oleg354-server mount facets: mds1 1 287 0.00 MB/sec execute 9 sec latency 19258.143 ms 1 287 0.00 MB/sec execute 10 sec latency 20258.608 ms 1 287 0.00 MB/sec execute 11 sec latency 21258.820 ms 1 287 0.00 MB/sec execute 12 sec latency 22261.033 ms 1 287 0.00 MB/sec execute 13 sec latency 23265.238 ms 1 287 0.00 MB/sec execute 14 sec latency 24265.854 ms 1 287 0.00 MB/sec execute 15 sec latency 25266.171 ms 1 287 0.00 MB/sec execute 16 sec latency 26274.570 ms 1 287 0.00 MB/sec execute 17 sec latency 27280.003 ms 1 287 0.00 MB/sec execute 18 sec latency 28280.184 ms 1 287 0.00 MB/sec execute 19 sec latency 29281.961 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 287 0.00 MB/sec execute 20 sec latency 30282.341 ms 1 287 0.00 MB/sec execute 21 sec latency 31282.659 ms 1 287 0.00 MB/sec execute 22 sec latency 32282.821 ms 1 287 0.00 MB/sec execute 23 sec latency 33283.283 ms 1 287 0.00 MB/sec execute 24 sec latency 34284.451 ms 1 287 0.00 MB/sec execute 25 sec latency 35285.593 ms 1 287 0.00 MB/sec execute 26 sec latency 36286.630 ms 1 287 0.00 MB/sec execute 27 sec latency 37286.867 ms 1 287 0.00 MB/sec execute 28 sec latency 38292.123 ms 1 287 0.00 MB/sec execute 29 sec latency 39293.087 ms oleg354-server: oleg354-server.virtnet: executing set_default_debug -1 all 1 287 0.00 MB/sec execute 30 sec latency 40295.670 ms pdsh@oleg354-client: oleg354-server: ssh exited with exit code 1 1 287 0.00 MB/sec execute 31 sec latency 41304.339 ms Started lustre-MDT0000 17:00:35 (1790715635) targets are mounted 17:00:35 (1790715635) facet_failover done 1 289 0.00 MB/sec execute 32 sec latency 42289.395 ms 1 320 0.03 MB/sec execute 33 sec latency 178.656 ms 1 353 0.06 MB/sec execute 34 sec latency 127.150 ms 1 370 0.07 MB/sec execute 35 sec latency 429.811 ms 1 408 0.10 MB/sec execute 36 sec latency 138.057 ms 1 446 0.13 MB/sec execute 37 sec latency 120.805 ms 1 493 0.17 MB/sec execute 38 sec latency 119.720 ms oleg354-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 522 0.19 MB/sec execute 39 sec latency 164.295 ms 1 612 0.26 MB/sec execute 40 sec latency 126.780 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 666 0.25 MB/sec execute 41 sec latency 90.999 ms 1 700 0.25 MB/sec execute 42 sec latency 132.817 ms 1 731 0.25 MB/sec execute 43 sec latency 147.877 ms 1 779 0.24 MB/sec execute 44 sec latency 90.356 ms 1 821 0.24 MB/sec execute 45 sec latency 88.554 ms 1 872 0.24 MB/sec execute 46 sec latency 123.778 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 908 0.23 MB/sec execute 47 sec latency 109.673 ms 1 937 0.23 MB/sec execute 48 sec latency 130.779 ms 1 980 0.23 MB/sec execute 49 sec latency 137.492 ms 1 1033 0.24 MB/sec execute 50 sec latency 176.144 ms 1 1050 0.24 MB/sec execute 51 sec latency 793.960 ms 1 1091 0.23 MB/sec execute 52 sec latency 98.736 ms 1 1134 0.23 MB/sec execute 53 sec latency 136.394 ms 1 1175 0.23 MB/sec execute 54 sec latency 114.749 ms 1 1214 0.22 MB/sec execute 55 sec latency 106.512 ms 1 1252 0.22 MB/sec execute 56 sec latency 89.309 ms 1 1382 0.27 MB/sec execute 57 sec latency 126.932 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Tue Sep 29 17:01:02 EDT 2026 with return code 0 1 1405 0.26 MB/sec execute 58 sec latency 228.237 ms 67892 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67892 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished