== replay-dual test 26: dbench and tar with mds failover ========================================================== 08:15:49 (1788524149) Starting client oleg623-client.virtnet: -o user_xattr,flock 192.168.206.123@tcp:/lustre /mnt/lustre Started clients oleg623-client.virtnet: 192.168.206.123@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 65625 Started dbench loop with 65626 striped dir -i0 -c2 -H crush /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 1940 1269364 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3580680 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7186136 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 08:15:54 EDT 2026 waiting for dbench pid 65700 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 37 1.24 MB/sec warmup 1 sec latency 77.173 ms 1 91 2.10 MB/sec warmup 2 sec latency 116.039 ms 1 137 2.01 MB/sec warmup 3 sec latency 141.304 ms 1 173 1.76 MB/sec warmup 4 sec latency 140.680 ms 1 197 1.57 MB/sec warmup 5 sec latency 473.946 ms 1 235 1.49 MB/sec warmup 6 sec latency 163.422 ms 1 287 1.53 MB/sec warmup 7 sec latency 89.211 ms 1 331 1.50 MB/sec warmup 8 sec latency 102.184 ms test_26 fail mds1 1 times 1 364 1.45 MB/sec warmup 9 sec latency 140.828 ms 1 407 1.43 MB/sec warmup 10 sec latency 92.253 ms Failing mds1 on oleg623-server Stopping /mnt/lustre-mds1 (opts:) on oleg623-server 1 453 1.44 MB/sec warmup 11 sec latency 123.394 ms 1 493 1.43 MB/sec warmup 12 sec latency 226.890 ms 1 493 1.32 MB/sec warmup 13 sec latency 1227.712 ms 08:16:08 (1788524168) shut down facet: mds1 facet_host: oleg623-server facet_failover_host: oleg623-server 1 493 1.23 MB/sec warmup 14 sec latency 2230.443 ms 1 493 1.15 MB/sec warmup 15 sec latency 3230.833 ms 1 493 1.07 MB/sec warmup 16 sec latency 4231.053 ms 1 493 1.01 MB/sec warmup 17 sec latency 5233.564 ms 1 493 0.95 MB/sec warmup 18 sec latency 6233.785 ms 1 493 0.90 MB/sec warmup 19 sec latency 7233.922 ms 1 493 0.00 MB/sec execute 1 sec latency 9235.925 ms 1 493 0.00 MB/sec execute 2 sec latency 10236.219 ms 1 493 0.00 MB/sec execute 3 sec latency 11236.516 ms 1 493 0.00 MB/sec execute 4 sec latency 12236.706 ms Failover mds1 to oleg623-server mount facets: mds1 1 493 0.00 MB/sec execute 5 sec latency 13236.932 ms 1 493 0.00 MB/sec execute 6 sec latency 14237.197 ms 1 493 0.00 MB/sec execute 7 sec latency 15237.602 ms 1 493 0.00 MB/sec execute 8 sec latency 16244.175 ms 1 493 0.00 MB/sec execute 9 sec latency 17244.348 ms 1 493 0.00 MB/sec execute 10 sec latency 18244.665 ms 1 493 0.00 MB/sec execute 11 sec latency 19245.628 ms 1 493 0.00 MB/sec execute 12 sec latency 20247.405 ms 1 493 0.00 MB/sec execute 13 sec latency 21247.801 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 493 0.00 MB/sec execute 14 sec latency 22248.478 ms 1 493 0.00 MB/sec execute 15 sec latency 23249.628 ms 1 493 0.00 MB/sec execute 16 sec latency 24250.200 ms 1 493 0.00 MB/sec execute 17 sec latency 25250.586 ms 1 493 0.00 MB/sec execute 18 sec latency 26250.917 ms 1 493 0.00 MB/sec execute 19 sec latency 27251.161 ms 1 493 0.00 MB/sec execute 20 sec latency 28251.473 ms 1 493 0.00 MB/sec execute 21 sec latency 29253.318 ms 1 493 0.00 MB/sec execute 22 sec latency 30255.846 ms 1 493 0.00 MB/sec execute 23 sec latency 31256.216 ms 1 493 0.00 MB/sec execute 24 sec latency 32259.782 ms oleg623-server: oleg623-server.virtnet: executing set_default_debug -1 all 1 493 0.00 MB/sec execute 25 sec latency 33262.190 ms pdsh@oleg623-client: oleg623-server: ssh exited with exit code 1 1 493 0.00 MB/sec execute 26 sec latency 34263.008 ms Started lustre-MDT0000 08:16:41 (1788524201) targets are mounted 08:16:41 (1788524201) facet_failover done 1 493 0.00 MB/sec execute 27 sec latency 35263.508 ms 1 493 0.00 MB/sec execute 28 sec latency 36264.167 ms 1 513 0.02 MB/sec execute 29 sec latency 36586.520 ms 1 552 0.06 MB/sec execute 30 sec latency 395.418 ms 1 639 0.12 MB/sec execute 31 sec latency 453.972 ms 1 674 0.12 MB/sec execute 32 sec latency 166.458 ms 1 708 0.12 MB/sec execute 33 sec latency 122.818 ms oleg623-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 735 0.12 MB/sec execute 34 sec latency 124.815 ms 1 767 0.12 MB/sec execute 35 sec latency 126.249 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 798 0.12 MB/sec execute 36 sec latency 137.668 ms 1 845 0.12 MB/sec execute 37 sec latency 96.911 ms 1 878 0.12 MB/sec execute 38 sec latency 101.837 ms 1 914 0.12 MB/sec execute 39 sec latency 104.734 ms 1 955 0.11 MB/sec execute 40 sec latency 96.545 ms 1 986 0.11 MB/sec execute 41 sec latency 107.060 ms UUID 1K-blocks Used Available Use% Mounted on 1 1050 0.14 MB/sec execute 42 sec latency 105.060 ms lustre-MDT0000_UUID 1414116 2128 1269176 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1940 1269364 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 17848 3586944 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 37468 3566632 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 55316 7153576 1% /mnt/lustre 1 1105 0.13 MB/sec execute 43 sec latency 98.055 ms 1 1156 0.13 MB/sec execute 44 sec latency 114.514 ms 1 1172 0.13 MB/sec execute 45 sec latency 678.262 ms 1 1208 0.13 MB/sec execute 46 sec latency 864.458 ms 1 1255 0.12 MB/sec execute 47 sec latency 79.059 ms 1 1381 0.18 MB/sec execute 48 sec latency 79.727 ms 1 1413 0.18 MB/sec execute 49 sec latency 128.554 ms 1 1468 0.18 MB/sec execute 50 sec latency 67.928 ms test_26 fail mds2 2 times 1 1512 0.17 MB/sec execute 51 sec latency 104.382 ms 1 1564 0.17 MB/sec execute 52 sec latency 74.764 ms Failing mds2 on oleg623-server 1 1596 0.17 MB/sec execute 53 sec latency 81.941 ms Stopping /mnt/lustre-mds2 (opts:) on oleg623-server 1 1643 0.17 MB/sec execute 54 sec latency 103.088 ms 1 1689 0.16 MB/sec execute 55 sec latency 108.575 ms 1 1771 0.16 MB/sec execute 56 sec latency 109.556 ms 08:17:11 (1788524231) shut down facet: mds2 facet_host: oleg623-server facet_failover_host: oleg623-server 1 1849 0.16 MB/sec execute 57 sec latency 67.844 ms 1 1938 0.16 MB/sec execute 58 sec latency 57.380 ms 1 2024 0.16 MB/sec execute 59 sec latency 60.449 ms 1 2115 0.16 MB/sec execute 60 sec latency 68.106 ms 1 2185 0.16 MB/sec execute 61 sec latency 66.071 ms 1 2259 0.15 MB/sec execute 62 sec latency 196.776 ms 1 2259 0.15 MB/sec execute 63 sec latency 1197.059 ms 1 2259 0.15 MB/sec execute 64 sec latency 2197.265 ms 1 2259 0.15 MB/sec execute 65 sec latency 3198.563 ms 1 2259 0.14 MB/sec execute 66 sec latency 4198.819 ms Failover mds2 to oleg623-server 1 2259 0.14 MB/sec execute 67 sec latency 5199.015 ms mount facets: mds2 1 2259 0.14 MB/sec execute 68 sec latency 6199.191 ms 1 2259 0.14 MB/sec execute 69 sec latency 7199.416 ms 1 2259 0.14 MB/sec execute 70 sec latency 8199.658 ms 1 2259 0.13 MB/sec execute 71 sec latency 9204.336 ms 1 2259 0.13 MB/sec execute 72 sec latency 10204.848 ms 1 2259 0.13 MB/sec execute 73 sec latency 11204.972 ms 1 2259 0.13 MB/sec execute 74 sec latency 12205.202 ms 1 2259 0.13 MB/sec execute 75 sec latency 13207.060 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.13 MB/sec execute 76 sec latency 14207.264 ms 1 2259 0.12 MB/sec execute 77 sec latency 15207.929 ms 1 2259 0.12 MB/sec execute 78 sec latency 16210.360 ms 1 2259 0.12 MB/sec execute 79 sec latency 17211.031 ms 1 2259 0.12 MB/sec execute 80 sec latency 18211.396 ms 1 2259 0.12 MB/sec execute 81 sec latency 19212.322 ms oleg623-server: oleg623-server.virtnet: executing set_default_debug -1 all 1 2259 0.12 MB/sec execute 82 sec latency 20212.588 ms pdsh@oleg623-client: oleg623-server: ssh exited with exit code 1 Started lustre-MDT0001 08:17:37 (1788524257) targets are mounted 08:17:37 (1788524257) facet_failover done 1 2259 0.12 MB/sec execute 83 sec latency 21214.059 ms 1 2259 0.11 MB/sec execute 84 sec latency 22214.283 ms 1 2328 0.12 MB/sec execute 85 sec latency 22596.846 ms 1 2377 0.12 MB/sec execute 86 sec latency 93.774 ms 1 2419 0.13 MB/sec execute 87 sec latency 99.788 ms 1 2477 0.13 MB/sec execute 88 sec latency 66.038 ms oleg623-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2567 0.13 MB/sec execute 89 sec latency 89.518 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2605 0.13 MB/sec execute 90 sec latency 98.808 ms 1 2768 0.16 MB/sec execute 91 sec latency 74.454 ms 1 2902 0.17 MB/sec execute 92 sec latency 88.552 ms 1 2978 0.18 MB/sec execute 93 sec latency 91.236 ms 1 3019 0.17 MB/sec execute 94 sec latency 92.484 ms 1 3232 0.18 MB/sec execute 95 sec latency 83.900 ms 1 3322 0.19 MB/sec execute 96 sec latency 108.595 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2344 1268960 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2144 1269160 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20608 3584008 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 48560 3557236 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 69168 7141244 1% /mnt/lustre 1 3374 0.19 MB/sec execute 97 sec latency 77.883 ms 1 3516 0.22 MB/sec execute 98 sec latency 94.419 ms 1 3572 0.21 MB/sec execute 99 sec latency 103.052 ms 1 cleanup 100 sec 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 462 174.066 36586.506 Close 387 10.567 39.645 Rename 23 78.143 114.485 Unlink 57 24.227 71.866 Qpathinfo 449 14.693 103.024 Qfileinfo 112 1.803 17.718 Qfsinfo 88 2.515 21.043 Sfileinfo 50 54.565 124.800 Find 189 10.525 36.821 WriteX 349 11.478 62.658 ReadX 928 1.219 77.077 LockX 2 12.292 19.498 UnlockX 2 6.156 6.726 Flush 43 54.502 166.443 Throughput 0.214153 MB/sec 1 clients 1 procs max_latency=36586.520 ms stopping dbench on /mnt/lustre at Fri Sep 4 08:17:59 EDT 2026 with return code 0 test_26 fail mds1 3 times clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished Failing mds1 on oleg623-server Stopping /mnt/lustre-mds1 (opts:) on oleg623-server striped dir -i0 -c2 -H all_char /mnt/lustre2/d26.replay-dual/run_dbench 08:18:05 (1788524285) shut down facet: mds1 facet_host: oleg623-server facet_failover_host: oleg623-server Failover mds1 to oleg623-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg623-server: oleg623-server.virtnet: executing set_default_debug -1 all pdsh@oleg623-client: oleg623-server: ssh exited with exit code 1 Started lustre-MDT0000 08:18:41 (1788524321) targets are mounted 08:18:41 (1788524321) facet_failover done 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 08:18:46 EDT 2026 waiting for dbench pid 68470 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 10 0.00 MB/sec warmup 1 sec latency 99.546 ms 1 64 1.37 MB/sec warmup 2 sec latency 140.084 ms oleg623-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 121 1.83 MB/sec warmup 3 sec latency 132.362 ms 1 156 1.63 MB/sec warmup 4 sec latency 174.098 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 184 1.47 MB/sec warmup 5 sec latency 297.686 ms 1 214 1.39 MB/sec warmup 6 sec latency 446.922 ms 1 256 1.38 MB/sec warmup 7 sec latency 117.491 ms 1 297 1.37 MB/sec warmup 8 sec latency 141.720 ms 1 349 1.39 MB/sec warmup 9 sec latency 102.182 ms 1 382 1.35 MB/sec warmup 10 sec latency 126.943 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2856 1268448 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2624 1268680 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 12940 3583556 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 35756 3569616 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 48696 7153172 1% /mnt/lustre 1 429 1.37 MB/sec warmup 11 sec latency 105.907 ms 1 461 1.34 MB/sec warmup 12 sec latency 151.593 ms 1 501 1.34 MB/sec warmup 13 sec latency 124.584 ms 1 526 1.29 MB/sec warmup 14 sec latency 166.843 ms 1 612 1.40 MB/sec warmup 15 sec latency 84.437 ms 1 664 1.32 MB/sec warmup 16 sec latency 134.916 ms 1 664 1.24 MB/sec warmup 17 sec latency 1139.493 ms 1 704 1.18 MB/sec warmup 18 sec latency 1154.487 ms 1 744 1.12 MB/sec warmup 19 sec latency 91.296 ms test_26 fail mds2 4 times 1 845 0.10 MB/sec execute 1 sec latency 150.355 ms Failing mds2 on oleg623-server 1 874 0.10 MB/sec execute 2 sec latency 123.038 ms Stopping /mnt/lustre-mds2 (opts:) on oleg623-server 1 884 0.07 MB/sec execute 3 sec latency 688.812 ms 1 892 0.05 MB/sec execute 4 sec latency 1070.617 ms 1 892 0.04 MB/sec execute 5 sec latency 1209.086 ms 1 892 0.04 MB/sec execute 6 sec latency 2209.299 ms 1 892 0.03 MB/sec execute 7 sec latency 3209.610 ms 1 892 0.03 MB/sec execute 8 sec latency 4209.826 ms 1 892 0.02 MB/sec execute 9 sec latency 5210.966 ms 1 892 0.02 MB/sec execute 10 sec latency 6211.641 ms 1 892 0.02 MB/sec execute 11 sec latency 7215.489 ms 08:19:18 (1788524358) shut down 1 892 0.02 MB/sec execute 12 sec latency 8215.712 ms facet: mds2 facet_host: oleg623-server facet_failover_host: oleg623-server 1 892 0.02 MB/sec execute 13 sec latency 9216.069 ms 1 892 0.02 MB/sec execute 14 sec latency 10216.283 ms 1 892 0.01 MB/sec execute 15 sec latency 11217.681 ms 1 892 0.01 MB/sec execute 16 sec latency 12219.050 ms 1 892 0.01 MB/sec execute 17 sec latency 13219.283 ms 1 892 0.01 MB/sec execute 18 sec latency 14219.495 ms 1 892 0.01 MB/sec execute 19 sec latency 15219.878 ms 1 892 0.01 MB/sec execute 20 sec latency 16223.107 ms 1 892 0.01 MB/sec execute 21 sec latency 17223.431 ms 1 892 0.01 MB/sec execute 22 sec latency 18223.652 ms Failover mds2 to oleg623-server mount facets: mds2 1 892 0.01 MB/sec execute 23 sec latency 19223.979 ms 1 892 0.01 MB/sec execute 24 sec latency 20224.768 ms 1 892 0.01 MB/sec execute 25 sec latency 21225.216 ms 1 892 0.01 MB/sec execute 26 sec latency 22225.472 ms 1 892 0.01 MB/sec execute 27 sec latency 23226.676 ms 1 892 0.01 MB/sec execute 28 sec latency 24226.904 ms 1 892 0.01 MB/sec execute 29 sec latency 25230.916 ms 1 892 0.01 MB/sec execute 30 sec latency 26231.179 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 892 0.01 MB/sec execute 31 sec latency 27231.356 ms 1 892 0.01 MB/sec execute 32 sec latency 28231.568 ms 1 892 0.01 MB/sec execute 33 sec latency 29231.765 ms 1 892 0.01 MB/sec execute 34 sec latency 30234.494 ms 1 892 0.01 MB/sec execute 35 sec latency 31237.544 ms 1 892 0.01 MB/sec execute 36 sec latency 32237.764 ms 1 892 0.01 MB/sec execute 37 sec latency 33237.984 ms oleg623-server: oleg623-server.virtnet: executing set_default_debug -1 all 1 892 0.01 MB/sec execute 38 sec latency 34238.221 ms pdsh@oleg623-client: oleg623-server: ssh exited with exit code 1 1 892 0.01 MB/sec execute 39 sec latency 35245.812 ms Started lustre-MDT0001 08:19:45 (1788524385) targets are mounted 08:19:45 (1788524385) facet_failover done 1 892 0.01 MB/sec execute 40 sec latency 36247.483 ms 1 914 0.01 MB/sec execute 41 sec latency 36390.643 ms 1 959 0.01 MB/sec execute 42 sec latency 99.367 ms 1 1005 0.01 MB/sec execute 43 sec latency 102.150 ms 1 1074 0.03 MB/sec execute 44 sec latency 77.359 ms 1 1126 0.03 MB/sec execute 45 sec latency 87.360 ms oleg623-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1172 0.03 MB/sec execute 46 sec latency 116.895 ms 1 1215 0.03 MB/sec execute 47 sec latency 82.780 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1252 0.03 MB/sec execute 48 sec latency 110.138 ms 1 1382 0.09 MB/sec execute 49 sec latency 80.266 ms 1 1421 0.09 MB/sec execute 50 sec latency 88.924 ms 1 1467 0.09 MB/sec execute 51 sec latency 85.282 ms 1 1508 0.09 MB/sec execute 52 sec latency 326.005 ms 1 1564 0.09 MB/sec execute 53 sec latency 75.037 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1620 0.09 MB/sec execute 54 sec latency 83.492 ms 1 1662 0.09 MB/sec execute 55 sec latency 97.158 ms 1 1717 0.09 MB/sec execute 56 sec latency 121.010 ms 1 1775 0.08 MB/sec execute 57 sec latency 97.776 ms 1 1840 0.08 MB/sec execute 58 sec latency 94.603 ms 1 1884 0.08 MB/sec execute 59 sec latency 93.490 ms 1 1956 0.08 MB/sec execute 60 sec latency 149.575 ms 1 2010 0.08 MB/sec execute 61 sec latency 97.812 ms 1 2097 0.08 MB/sec execute 62 sec latency 95.757 ms 1 2158 0.08 MB/sec execute 63 sec latency 95.949 ms 1 2209 0.08 MB/sec execute 64 sec latency 73.901 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Sep 4 08:20:11 EDT 2026 with return code 0 1 2305 0.10 MB/sec execute 65 sec latency 80.479 ms 68470 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 68470 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished