== replay-dual test 26: dbench and tar with mds failover ========================================================== 15:04:05 (1783969445) Starting client oleg407-client.virtnet: -o user_xattr,flock 192.168.204.107@tcp:/lustre /mnt/lustre Started clients oleg407-client.virtnet: 192.168.204.107@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 44942 Started dbench loop with 44944 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 3765248 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 16384 7505920 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 Mon Jul 13 15:04:11 EDT 2026 waiting for dbench pid 45012 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 31 1.05 MB/sec warmup 1 sec latency 169.658 ms 1 78 1.70 MB/sec warmup 2 sec latency 146.326 ms 1 121 1.83 MB/sec warmup 3 sec latency 194.233 ms 1 164 1.70 MB/sec warmup 4 sec latency 117.023 ms test_26 fail mds1 1 times 1 197 1.57 MB/sec warmup 5 sec latency 197.309 ms 1 223 1.43 MB/sec warmup 6 sec latency 169.419 ms Failing mds1 on oleg407-server 1 260 1.40 MB/sec warmup 7 sec latency 145.142 ms 1 292 1.34 MB/sec warmup 8 sec latency 138.051 ms Stopping /mnt/lustre-mds1 (opts:) on oleg407-server 1 331 1.33 MB/sec warmup 9 sec latency 116.973 ms 1 331 1.20 MB/sec warmup 10 sec latency 1018.065 ms 1 331 1.09 MB/sec warmup 11 sec latency 2018.314 ms 15:04:23 (1783969463) shut down facet: mds1 facet_host: oleg407-server facet_failover_host: oleg407-server 1 331 1.00 MB/sec warmup 12 sec latency 3018.464 ms 1 331 0.92 MB/sec warmup 13 sec latency 4019.549 ms 1 331 0.86 MB/sec warmup 14 sec latency 5019.821 ms 1 331 0.80 MB/sec warmup 15 sec latency 6020.220 ms 1 331 0.75 MB/sec warmup 16 sec latency 7020.779 ms 1 331 0.71 MB/sec warmup 17 sec latency 8021.071 ms 1 331 0.67 MB/sec warmup 18 sec latency 9021.316 ms 1 331 0.63 MB/sec warmup 19 sec latency 10021.547 ms 1 331 0.00 MB/sec execute 1 sec latency 12021.920 ms 1 331 0.00 MB/sec execute 2 sec latency 13022.098 ms Failover mds1 to oleg407-server mount facets: mds1 1 331 0.00 MB/sec execute 3 sec latency 14023.709 ms 1 331 0.00 MB/sec execute 4 sec latency 15024.991 ms 1 331 0.00 MB/sec execute 5 sec latency 16025.330 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 331 0.00 MB/sec execute 6 sec latency 17025.718 ms 1 331 0.00 MB/sec execute 7 sec latency 18026.023 ms 1 331 0.00 MB/sec execute 8 sec latency 19026.314 ms 1 331 0.00 MB/sec execute 9 sec latency 20026.585 ms 1 331 0.00 MB/sec execute 10 sec latency 21027.498 ms 1 331 0.00 MB/sec execute 11 sec latency 22029.227 ms 1 331 0.00 MB/sec execute 12 sec latency 23029.825 ms oleg407-server: oleg407-server.virtnet: executing set_default_debug -1 all 1 331 0.00 MB/sec execute 13 sec latency 24030.545 ms pdsh@oleg407-client: oleg407-server: ssh exited with exit code 1 1 364 0.07 MB/sec execute 14 sec latency 24195.630 ms Started lustre-MDT0000 15:04:46 (1783969486) targets are mounted 15:04:46 (1783969486) facet_failover done 1 405 0.16 MB/sec execute 15 sec latency 114.193 ms 1 453 0.24 MB/sec execute 16 sec latency 91.181 ms 1 488 0.29 MB/sec execute 17 sec latency 116.181 ms 1 520 0.33 MB/sec execute 18 sec latency 175.884 ms 1 608 0.47 MB/sec execute 19 sec latency 99.910 ms 1 664 0.46 MB/sec execute 20 sec latency 83.918 ms oleg407-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 692 0.44 MB/sec execute 21 sec latency 213.491 ms 1 721 0.42 MB/sec execute 22 sec latency 118.717 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 738 0.40 MB/sec execute 23 sec latency 303.730 ms 1 777 0.39 MB/sec execute 24 sec latency 100.815 ms 1 804 0.38 MB/sec execute 25 sec latency 157.831 ms 1 851 0.37 MB/sec execute 26 sec latency 93.670 ms 1 888 0.36 MB/sec execute 27 sec latency 159.944 ms 1 923 0.35 MB/sec execute 28 sec latency 149.694 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 35840 3678208 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 19456 3691520 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 55296 7369728 1% /mnt/lustre 1 969 0.34 MB/sec execute 29 sec latency 87.664 ms 1 1008 0.34 MB/sec execute 30 sec latency 147.658 ms 1 1079 0.35 MB/sec execute 31 sec latency 81.149 ms 1 1135 0.34 MB/sec execute 32 sec latency 62.200 ms 1 1190 0.33 MB/sec execute 33 sec latency 73.828 ms test_26 fail mds1 2 times 1 1244 0.33 MB/sec execute 34 sec latency 66.741 ms 1 1378 0.40 MB/sec execute 35 sec latency 109.565 ms Failing mds1 on oleg407-server 1 1421 0.39 MB/sec execute 36 sec latency 118.610 ms Stopping /mnt/lustre-mds1 (opts:) on oleg407-server 1 1471 0.38 MB/sec execute 37 sec latency 97.792 ms 1 1496 0.37 MB/sec execute 38 sec latency 423.842 ms 1 1496 0.36 MB/sec execute 39 sec latency 1424.887 ms 1 1496 0.35 MB/sec execute 40 sec latency 2425.141 ms 15:05:11 (1783969511) shut down facet: mds1 facet_host: oleg407-server facet_failover_host: oleg407-server 1 1496 0.34 MB/sec execute 41 sec latency 3425.595 ms 1 1496 0.33 MB/sec execute 42 sec latency 4425.786 ms 1 1496 0.33 MB/sec execute 43 sec latency 5426.017 ms 1 1496 0.32 MB/sec execute 44 sec latency 6427.621 ms 1 1496 0.31 MB/sec execute 45 sec latency 7427.815 ms 1 1496 0.30 MB/sec execute 46 sec latency 8428.013 ms 1 1496 0.30 MB/sec execute 47 sec latency 9428.201 ms 1 1496 0.29 MB/sec execute 48 sec latency 10428.687 ms 1 1496 0.29 MB/sec execute 49 sec latency 11429.095 ms 1 1496 0.28 MB/sec execute 50 sec latency 12431.062 ms Failover mds1 to oleg407-server mount facets: mds1 1 1496 0.28 MB/sec execute 51 sec latency 13432.147 ms 1 1496 0.27 MB/sec execute 52 sec latency 14435.505 ms 1 1496 0.26 MB/sec execute 53 sec latency 15435.784 ms 1 1496 0.26 MB/sec execute 54 sec latency 16444.907 ms 1 1496 0.25 MB/sec execute 55 sec latency 17445.277 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1496 0.25 MB/sec execute 56 sec latency 18445.504 ms 1 1496 0.25 MB/sec execute 57 sec latency 19445.679 ms 1 1496 0.24 MB/sec execute 58 sec latency 20446.434 ms 1 1496 0.24 MB/sec execute 59 sec latency 21446.664 ms 1 1496 0.23 MB/sec execute 60 sec latency 22446.928 ms 1 1496 0.23 MB/sec execute 61 sec latency 23447.133 ms 1 1496 0.23 MB/sec execute 62 sec latency 24447.342 ms 1 1496 0.22 MB/sec execute 63 sec latency 25449.120 ms 1 1496 0.22 MB/sec execute 64 sec latency 26449.466 ms 1 1496 0.22 MB/sec execute 65 sec latency 27449.836 ms 1 1496 0.21 MB/sec execute 66 sec latency 28451.730 ms 1 1496 0.21 MB/sec execute 67 sec latency 29451.941 ms 1 1496 0.21 MB/sec execute 68 sec latency 30452.279 ms 1 1496 0.20 MB/sec execute 69 sec latency 31453.507 ms oleg407-server: oleg407-server.virtnet: executing set_default_debug -1 all 1 1496 0.20 MB/sec execute 70 sec latency 32456.768 ms pdsh@oleg407-client: oleg407-server: ssh exited with exit code 1 1 1496 0.20 MB/sec execute 71 sec latency 33457.187 ms Started lustre-MDT0000 15:05:43 (1783969543) targets are mounted 15:05:43 (1783969543) facet_failover done 1 1496 0.19 MB/sec execute 72 sec latency 34460.034 ms 1 1496 0.19 MB/sec execute 73 sec latency 35460.314 ms 1 1496 0.19 MB/sec execute 74 sec latency 36460.515 ms 1 1496 0.19 MB/sec execute 75 sec latency 37460.766 ms 1 1496 0.18 MB/sec execute 76 sec latency 38461.493 ms 1 1496 0.18 MB/sec execute 77 sec latency 39461.718 ms 1 1496 0.18 MB/sec execute 78 sec latency 40461.974 ms 1 1496 0.18 MB/sec execute 79 sec latency 41462.153 ms 1 1496 0.18 MB/sec execute 80 sec latency 42462.547 ms 1 1496 0.17 MB/sec execute 81 sec latency 43463.015 ms 1 1515 0.17 MB/sec execute 82 sec latency 43634.926 ms 1 1574 0.17 MB/sec execute 83 sec latency 93.203 ms 1 1625 0.17 MB/sec execute 84 sec latency 105.031 ms 1 1653 0.17 MB/sec execute 85 sec latency 315.997 ms 1 1692 0.17 MB/sec execute 86 sec latency 119.469 ms oleg407-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1753 0.16 MB/sec execute 87 sec latency 82.829 ms 1 1808 0.16 MB/sec execute 88 sec latency 133.892 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1848 0.16 MB/sec execute 89 sec latency 135.866 ms 1 1884 0.16 MB/sec execute 90 sec latency 113.337 ms 1 1919 0.16 MB/sec execute 91 sec latency 238.145 ms 1 1974 0.16 MB/sec execute 92 sec latency 111.379 ms 1 2008 0.16 MB/sec execute 93 sec latency 128.971 ms 1 2082 0.16 MB/sec execute 94 sec latency 103.378 ms 1 2135 0.15 MB/sec execute 95 sec latency 85.997 ms 1 2160 0.15 MB/sec execute 96 sec latency 123.849 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2688 2205824 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 39936 3717120 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 33792 3718144 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7435264 1% /mnt/lustre 1 2184 0.15 MB/sec execute 97 sec latency 169.928 ms 1 2228 0.15 MB/sec execute 98 sec latency 134.992 ms 1 2300 0.16 MB/sec execute 99 sec latency 86.703 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec test_26 fail mds1 3 times 1 cleanup 103 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 347 129.688 24195.605 Close 302 157.631 43634.893 Rename 11 78.229 118.682 Unlink 31 29.183 51.827 Qpathinfo 307 15.708 108.798 Qfileinfo 92 2.719 21.679 Qfsinfo 37 2.842 18.581 Sfileinfo 36 50.863 99.962 Find 100 6.461 53.464 WriteX 344 12.562 100.413 ReadX 377 1.811 106.923 Flush 31 131.249 315.943 Throughput 0.158945 MB/sec 1 clients 1 procs max_latency=43634.926 ms stopping dbench on /mnt/lustre at Mon Jul 13 15:06:15 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished Failing mds1 on oleg407-server Stopping /mnt/lustre-mds1 (opts:) on oleg407-server looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt 15:06:21 (1783969581) shut down facet: mds1 facet_host: oleg407-server facet_failover_host: oleg407-server Failover mds1 to oleg407-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 oleg407-server: oleg407-server.virtnet: executing set_default_debug -1 all pdsh@oleg407-client: oleg407-server: ssh exited with exit code 1 Started lustre-MDT0000 15:06:43 (1783969603) targets are mounted 15:06:43 (1783969603) facet_failover done '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Mon Jul 13 15:07:03 EDT 2026 waiting for dbench pid 47558 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 38 1.31 MB/sec warmup 1 sec latency 103.241 ms 1 90 2.09 MB/sec warmup 2 sec latency 150.137 ms oleg407-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 129 1.92 MB/sec warmup 3 sec latency 158.985 ms 1 155 1.63 MB/sec warmup 4 sec latency 167.949 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 184 1.48 MB/sec warmup 5 sec latency 176.116 ms 1 208 1.35 MB/sec warmup 6 sec latency 174.631 ms 1 247 1.34 MB/sec warmup 7 sec latency 124.882 ms 1 287 1.34 MB/sec warmup 8 sec latency 124.076 ms 1 319 1.28 MB/sec warmup 9 sec latency 152.798 ms 1 357 1.28 MB/sec warmup 10 sec latency 142.479 ms 1 385 1.24 MB/sec warmup 11 sec latency 148.933 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3200 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 9216 3707904 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 57344 3664896 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 66560 7372800 1% /mnt/lustre 1 413 1.22 MB/sec warmup 12 sec latency 169.583 ms 1 445 1.20 MB/sec warmup 13 sec latency 138.462 ms 1 485 1.21 MB/sec warmup 14 sec latency 161.997 ms 1 512 1.18 MB/sec warmup 15 sec latency 154.168 ms 1 591 1.27 MB/sec warmup 16 sec latency 148.210 ms 1 642 1.24 MB/sec warmup 17 sec latency 199.135 ms test_26 fail mds1 4 times 1 671 1.17 MB/sec warmup 18 sec latency 213.300 ms 1 695 1.11 MB/sec warmup 19 sec latency 171.213 ms Failing mds1 on oleg407-server 1 733 0.03 MB/sec execute 1 sec latency 213.741 ms Stopping /mnt/lustre-mds1 (opts:) on oleg407-server 1 762 0.03 MB/sec execute 2 sec latency 152.326 ms 1 780 0.03 MB/sec execute 3 sec latency 185.466 ms 1 785 0.04 MB/sec execute 4 sec latency 893.608 ms 1 785 0.03 MB/sec execute 5 sec latency 1893.864 ms 1 785 0.03 MB/sec execute 6 sec latency 2896.535 ms 1 785 0.02 MB/sec execute 7 sec latency 3896.765 ms 15:07:31 (1783969651) shut down facet: mds1 facet_host: oleg407-server facet_failover_host: oleg407-server 1 785 0.02 MB/sec execute 8 sec latency 4903.590 ms 1 785 0.02 MB/sec execute 9 sec latency 5903.777 ms 1 785 0.02 MB/sec execute 10 sec latency 6903.975 ms 1 785 0.01 MB/sec execute 11 sec latency 7904.162 ms 1 785 0.01 MB/sec execute 12 sec latency 8904.598 ms 1 785 0.01 MB/sec execute 13 sec latency 9907.878 ms 1 785 0.01 MB/sec execute 14 sec latency 10908.308 ms 1 785 0.01 MB/sec execute 15 sec latency 11908.739 ms 1 785 0.01 MB/sec execute 16 sec latency 12909.440 ms 1 785 0.01 MB/sec execute 17 sec latency 13909.889 ms 1 785 0.01 MB/sec execute 18 sec latency 14913.315 ms Failover mds1 to oleg407-server mount facets: mds1 1 785 0.01 MB/sec execute 19 sec latency 15913.927 ms 1 785 0.01 MB/sec execute 20 sec latency 16914.406 ms 1 785 0.01 MB/sec execute 21 sec latency 17914.779 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 785 0.01 MB/sec execute 22 sec latency 18915.139 ms 1 785 0.01 MB/sec execute 23 sec latency 19917.461 ms 1 785 0.01 MB/sec execute 24 sec latency 20918.879 ms 1 785 0.01 MB/sec execute 25 sec latency 21919.130 ms 1 785 0.01 MB/sec execute 26 sec latency 22919.323 ms 1 785 0.01 MB/sec execute 27 sec latency 23936.714 ms 1 785 0.01 MB/sec execute 28 sec latency 24937.192 ms 1 785 0.01 MB/sec execute 29 sec latency 25938.042 ms oleg407-server: oleg407-server.virtnet: executing set_default_debug -1 all 1 786 0.01 MB/sec execute 30 sec latency 26781.605 ms 1 801 0.01 MB/sec execute 31 sec latency 218.677 ms pdsh@oleg407-client: oleg407-server: ssh exited with exit code 1 1 825 0.01 MB/sec execute 32 sec latency 183.339 ms Started lustre-MDT0000 15:07:56 (1783969676) targets are mounted 15:07:56 (1783969676) facet_failover done 1 873 0.01 MB/sec execute 33 sec latency 128.920 ms 1 887 0.01 MB/sec execute 34 sec latency 484.459 ms 1 905 0.01 MB/sec execute 35 sec latency 159.372 ms 1 920 0.01 MB/sec execute 36 sec latency 332.849 ms 1 951 0.01 MB/sec execute 37 sec latency 199.673 ms 1 980 0.02 MB/sec execute 38 sec latency 156.031 ms 1 1002 0.02 MB/sec execute 39 sec latency 165.439 ms 1 1050 0.04 MB/sec execute 40 sec latency 162.166 ms oleg407-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1081 0.04 MB/sec execute 41 sec latency 139.312 ms 1 1128 0.04 MB/sec execute 42 sec latency 122.377 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1147 0.04 MB/sec execute 43 sec latency 171.351 ms 1 1180 0.04 MB/sec execute 44 sec latency 134.136 ms 1 1221 0.04 MB/sec execute 45 sec latency 100.678 ms 1 1249 0.04 MB/sec execute 46 sec latency 118.044 ms 1 1296 0.05 MB/sec execute 47 sec latency 94.217 ms 1 1405 0.10 MB/sec execute 48 sec latency 131.231 ms 1 1451 0.10 MB/sec execute 49 sec latency 141.687 ms 1 1497 0.10 MB/sec execute 50 sec latency 197.078 ms 1 1548 0.09 MB/sec execute 51 sec latency 110.270 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1580 0.09 MB/sec execute 52 sec latency 100.460 ms 1 1625 0.09 MB/sec execute 53 sec latency 113.931 ms 1 1653 0.09 MB/sec execute 54 sec latency 341.232 ms 1 1687 0.09 MB/sec execute 55 sec latency 115.470 ms 1 1738 0.09 MB/sec execute 56 sec latency 115.583 ms 1 1808 0.09 MB/sec execute 57 sec latency 72.539 ms 1 1849 0.09 MB/sec execute 58 sec latency 110.497 ms 1 1884 0.09 MB/sec execute 59 sec latency 134.301 ms 1 1924 0.09 MB/sec execute 60 sec latency 322.391 ms 1 1974 0.08 MB/sec execute 61 sec latency 100.960 ms 1 2012 0.08 MB/sec execute 62 sec latency 102.591 ms 1 2065 0.08 MB/sec execute 63 sec latency 107.540 ms 1 2117 0.08 MB/sec execute 64 sec latency 127.394 ms 1 2150 0.08 MB/sec execute 65 sec latency 180.787 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Jul 13 15:08:29 EDT 2026 with return code 0 1 2168 0.08 MB/sec execute 66 sec latency 123.985 ms 47558 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47558 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished