== replay-dual test 26: dbench and tar with mds failover ========================================================== 02:27:48 (1790922468) Starting client oleg306-client.virtnet: -o user_xattr,flock 192.168.203.106@tcp:/lustre /mnt/lustre Started clients oleg306-client.virtnet: 192.168.203.106@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 64016 Started dbench loop with 64017 striped dir -i0 -c2 -H fnv_1a_64 /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 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210688 2176 2206464 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 2048 3741696 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3762176 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7503872 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 Oct 2 02:27:54 EDT 2026 waiting for dbench pid 64097 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 5 0.00 MB/sec warmup 1 sec latency 77.742 ms 1 35 0.56 MB/sec warmup 2 sec latency 170.707 ms 1 111 1.74 MB/sec warmup 3 sec latency 123.796 ms 1 147 1.57 MB/sec warmup 4 sec latency 173.111 ms test_26 fail mds1 1 times 1 181 1.46 MB/sec warmup 5 sec latency 130.604 ms 1 205 1.33 MB/sec warmup 6 sec latency 268.508 ms Failing mds1 on oleg306-server 1 236 1.28 MB/sec warmup 7 sec latency 146.538 ms Stopping /mnt/lustre-mds1 (opts:) on oleg306-server 1 271 1.27 MB/sec warmup 8 sec latency 182.134 ms 1 305 1.24 MB/sec warmup 9 sec latency 194.076 ms 1 339 1.22 MB/sec warmup 10 sec latency 213.952 ms 1 339 1.11 MB/sec warmup 11 sec latency 1214.156 ms 02:28:05 (1790922485) shut down facet: mds1 facet_host: oleg306-server facet_failover_host: oleg306-server 1 339 1.02 MB/sec warmup 12 sec latency 2214.378 ms 1 339 0.94 MB/sec warmup 13 sec latency 3214.899 ms 1 339 0.87 MB/sec warmup 14 sec latency 4215.095 ms 1 339 0.82 MB/sec warmup 15 sec latency 5217.070 ms 1 339 0.77 MB/sec warmup 16 sec latency 6218.450 ms 1 339 0.72 MB/sec warmup 17 sec latency 7218.739 ms 1 339 0.68 MB/sec warmup 18 sec latency 8218.945 ms 1 339 0.64 MB/sec warmup 19 sec latency 9223.027 ms 1 339 0.00 MB/sec execute 1 sec latency 11223.712 ms Failover mds1 to oleg306-server mount facets: mds1 1 339 0.00 MB/sec execute 2 sec latency 12223.866 ms 1 339 0.00 MB/sec execute 3 sec latency 13224.365 ms 1 339 0.00 MB/sec execute 4 sec latency 14229.220 ms 1 339 0.00 MB/sec execute 5 sec latency 15229.491 ms 1 339 0.00 MB/sec execute 6 sec latency 16229.835 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 339 0.00 MB/sec execute 7 sec latency 17230.394 ms 1 339 0.00 MB/sec execute 8 sec latency 18232.197 ms 1 339 0.00 MB/sec execute 9 sec latency 19233.551 ms 1 339 0.00 MB/sec execute 10 sec latency 20236.122 ms 1 339 0.00 MB/sec execute 11 sec latency 21238.730 ms 1 339 0.00 MB/sec execute 12 sec latency 22239.229 ms oleg306-server: oleg306-server.virtnet: executing set_default_debug -1 all 1 339 0.00 MB/sec execute 13 sec latency 23239.445 ms pdsh@oleg306-client: oleg306-server: ssh exited with exit code 1 1 339 0.00 MB/sec execute 14 sec latency 24243.271 ms Started lustre-MDT0000 1 339 0.00 MB/sec execute 15 sec latency 25243.755 ms 02:28:29 (1790922509) targets are mounted 02:28:29 (1790922509) facet_failover done 1 361 0.04 MB/sec execute 16 sec latency 25751.942 ms 1 397 0.11 MB/sec execute 17 sec latency 141.873 ms 1 434 0.17 MB/sec execute 18 sec latency 125.617 ms 1 478 0.23 MB/sec execute 19 sec latency 161.307 ms 1 513 0.27 MB/sec execute 20 sec latency 155.982 ms 1 590 0.38 MB/sec execute 21 sec latency 137.307 ms oleg306-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 648 0.40 MB/sec execute 22 sec latency 118.173 ms 1 673 0.39 MB/sec execute 23 sec latency 226.793 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 699 0.37 MB/sec execute 24 sec latency 133.082 ms 1 726 0.36 MB/sec execute 25 sec latency 208.939 ms 1 749 0.35 MB/sec execute 26 sec latency 133.538 ms 1 789 0.34 MB/sec execute 27 sec latency 104.804 ms 1 805 0.33 MB/sec execute 28 sec latency 263.719 ms 1 870 0.32 MB/sec execute 29 sec latency 94.523 ms 1 902 0.31 MB/sec execute 30 sec latency 120.825 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210432 2560 2205824 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210688 2304 2206336 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 36864 3671040 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 10240 3715072 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 47104 7386112 1% /mnt/lustre 1 923 0.31 MB/sec execute 31 sec latency 168.907 ms 1 967 0.30 MB/sec execute 32 sec latency 104.838 ms 1 986 0.29 MB/sec execute 33 sec latency 277.089 ms 1 1050 0.31 MB/sec execute 34 sec latency 85.721 ms 1 1102 0.30 MB/sec execute 35 sec latency 84.404 ms 1 1147 0.30 MB/sec execute 36 sec latency 103.166 ms test_26 fail mds2 2 times 1 1180 0.29 MB/sec execute 37 sec latency 144.936 ms 1 1207 0.28 MB/sec execute 38 sec latency 120.500 ms Failing mds2 on oleg306-server 1 1235 0.28 MB/sec execute 39 sec latency 184.668 ms 1 1262 0.27 MB/sec execute 40 sec latency 140.776 ms Stopping /mnt/lustre-mds2 (opts:) on oleg306-server 1 1394 0.33 MB/sec execute 41 sec latency 72.026 ms 1 1421 0.33 MB/sec execute 42 sec latency 137.681 ms 1 1433 0.32 MB/sec execute 43 sec latency 722.144 ms 02:28:58 (1790922538) shut down 1 1433 0.31 MB/sec execute 44 sec latency 1724.255 ms facet: mds2 facet_host: oleg306-server facet_failover_host: oleg306-server 1 1433 0.30 MB/sec execute 45 sec latency 2725.194 ms 1 1433 0.30 MB/sec execute 46 sec latency 3725.449 ms 1 1433 0.29 MB/sec execute 47 sec latency 4725.674 ms 1 1433 0.29 MB/sec execute 48 sec latency 5726.464 ms 1 1433 0.28 MB/sec execute 49 sec latency 6726.820 ms 1 1433 0.27 MB/sec execute 50 sec latency 7727.951 ms 1 1433 0.27 MB/sec execute 51 sec latency 8728.200 ms 1 1433 0.26 MB/sec execute 52 sec latency 9728.889 ms 1 1433 0.26 MB/sec execute 53 sec latency 10729.385 ms 1 1433 0.25 MB/sec execute 54 sec latency 11729.643 ms Failover mds2 to oleg306-server mount facets: mds2 1 1433 0.25 MB/sec execute 55 sec latency 12732.294 ms 1 1433 0.25 MB/sec execute 56 sec latency 13732.548 ms 1 1433 0.24 MB/sec execute 57 sec latency 14733.123 ms 1 1433 0.24 MB/sec execute 58 sec latency 15734.749 ms 1 1433 0.23 MB/sec execute 59 sec latency 16735.053 ms Start mds2: mount -t lustre -o localrecov lustre-mdt2/mdt2 /mnt/lustre-mds2 1 1433 0.23 MB/sec execute 60 sec latency 17735.656 ms 1 1433 0.23 MB/sec execute 61 sec latency 18736.007 ms 1 1433 0.22 MB/sec execute 62 sec latency 19741.837 ms 1 1433 0.22 MB/sec execute 63 sec latency 20744.402 ms 1 1433 0.21 MB/sec execute 64 sec latency 21744.743 ms 1 1433 0.21 MB/sec execute 65 sec latency 22745.351 ms oleg306-server: oleg306-server.virtnet: executing set_default_debug -1 all 1 1433 0.21 MB/sec execute 66 sec latency 23745.655 ms 1 1433 0.20 MB/sec execute 67 sec latency 24749.677 ms pdsh@oleg306-client: oleg306-server: ssh exited with exit code 1 1 1443 0.20 MB/sec execute 68 sec latency 25515.582 ms Started lustre-MDT0001 02:29:23 (1790922563) targets are mounted 02:29:23 (1790922563) facet_failover done 1 1481 0.20 MB/sec execute 69 sec latency 197.008 ms 1 1525 0.20 MB/sec execute 70 sec latency 197.688 ms 1 1584 0.20 MB/sec execute 71 sec latency 80.159 ms 1 1625 0.19 MB/sec execute 72 sec latency 137.946 ms 1 1651 0.19 MB/sec execute 73 sec latency 244.512 ms 1 1686 0.19 MB/sec execute 74 sec latency 149.547 ms 1 1725 0.19 MB/sec execute 75 sec latency 164.612 ms oleg306-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1787 0.18 MB/sec execute 76 sec latency 98.629 ms 1 1825 0.18 MB/sec execute 77 sec latency 101.108 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1868 0.18 MB/sec execute 78 sec latency 125.180 ms 1 1902 0.18 MB/sec execute 79 sec latency 282.440 ms 1 1969 0.18 MB/sec execute 80 sec latency 87.605 ms 1 2002 0.18 MB/sec execute 81 sec latency 116.177 ms 1 2046 0.17 MB/sec execute 82 sec latency 107.215 ms 1 2101 0.17 MB/sec execute 83 sec latency 89.333 ms 1 2152 0.17 MB/sec execute 84 sec latency 134.810 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210432 2816 2205568 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210688 2688 2205952 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 50176 3715072 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 14336 3745792 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 64512 7460864 1% /mnt/lustre 1 2173 0.17 MB/sec execute 85 sec latency 145.115 ms 1 2212 0.17 MB/sec execute 86 sec latency 168.402 ms 1 2294 0.18 MB/sec execute 87 sec latency 82.438 ms 1 2345 0.18 MB/sec execute 88 sec latency 144.517 ms 1 2373 0.18 MB/sec execute 89 sec latency 243.910 ms 1 2400 0.17 MB/sec execute 90 sec latency 198.475 ms test_26 fail mds1 3 times 1 2434 0.17 MB/sec execute 91 sec latency 200.991 ms 1 2468 0.18 MB/sec execute 92 sec latency 103.250 ms 1 2492 0.18 MB/sec execute 93 sec latency 242.617 ms Failing mds1 on oleg306-server 1 2570 0.18 MB/sec execute 94 sec latency 113.953 ms Stopping /mnt/lustre-mds1 (opts:) on oleg306-server 1 2597 0.18 MB/sec execute 95 sec latency 149.024 ms 1 2655 0.19 MB/sec execute 96 sec latency 156.164 ms 1 2729 0.20 MB/sec execute 97 sec latency 746.031 ms 1 2749 0.20 MB/sec execute 98 sec latency 1611.198 ms 1 2779 0.20 MB/sec execute 99 sec latency 208.193 ms 02:29:54 (1790922594) shut down facet: mds1 facet_host: oleg306-server facet_failover_host: oleg306-server 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec Failover mds1 to oleg306-server mount facets: mds1 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec 1 cleanup 114 sec 1 cleanup 115 sec Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 cleanup 116 sec 1 cleanup 117 sec 1 cleanup 118 sec 1 cleanup 119 sec 1 cleanup 120 sec 1 cleanup 121 sec 1 cleanup 122 sec 1 cleanup 123 sec 1 cleanup 124 sec 1 cleanup 125 sec 1 cleanup 126 sec 1 cleanup 127 sec 1 cleanup 128 sec 1 cleanup 129 sec 1 cleanup 130 sec oleg306-server: oleg306-server.virtnet: executing set_default_debug -1 all 1 cleanup 131 sec 1 cleanup 132 sec pdsh@oleg306-client: oleg306-server: ssh exited with exit code 1 1 cleanup 133 sec 1 cleanup 134 sec Started lustre-MDT0000 02:30:29 (1790922629) targets are mounted 02:30:29 (1790922629) facet_failover done 1 cleanup 135 sec 1 cleanup 136 sec 1 cleanup 137 sec 0 cleanup 138 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 406 125.318 25751.921 Close 345 88.270 25515.559 Rename 18 108.577 180.130 Unlink 43 29.546 54.834 Qpathinfo 366 19.047 104.973 Qfileinfo 113 2.291 15.225 Qfsinfo 55 6.799 116.043 Sfileinfo 50 67.757 126.930 Find 128 14.468 79.609 WriteX 389 13.035 71.501 ReadX 614 0.995 93.630 LockX 2 15.530 16.065 UnlockX 2 9.501 13.587 Flush 35 154.136 282.422 Throughput 0.198697 MB/sec 1 clients 1 procs max_latency=25751.942 ms stopping dbench on /mnt/lustre at Fri Oct 2 02:30:32 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 crush /mnt/lustre2/d26.replay-dual/run_dbench oleg306-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec '/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 Oct 2 02:30:40 EDT 2026 waiting for dbench pid 67051 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 5 0.00 MB/sec warmup 1 sec latency 86.771 ms 1 51 1.05 MB/sec warmup 2 sec latency 89.161 ms 1 111 1.74 MB/sec warmup 3 sec latency 221.262 ms 1 146 1.57 MB/sec warmup 4 sec latency 224.473 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210432 3072 2205312 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 2210560 2816 2205696 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3771392 24576 3742720 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 29696 3698688 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 54272 7441408 1% /mnt/lustre 1 174 1.41 MB/sec warmup 5 sec latency 145.366 ms 1 199 1.31 MB/sec warmup 6 sec latency 173.310 ms 1 237 1.29 MB/sec warmup 7 sec latency 164.643 ms 1 279 1.30 MB/sec warmup 8 sec latency 115.505 ms 1 305 1.25 MB/sec warmup 9 sec latency 186.725 ms 1 341 1.22 MB/sec warmup 10 sec latency 164.190 ms test_26 fail mds2 4 times 1 380 1.23 MB/sec warmup 11 sec latency 122.116 ms 1 412 1.21 MB/sec warmup 12 sec latency 151.884 ms Failing mds2 on oleg306-server 1 445 1.20 MB/sec warmup 13 sec latency 115.825 ms 1 485 1.21 MB/sec warmup 14 sec latency 136.829 ms Stopping /mnt/lustre-mds2 (opts:) on oleg306-server 1 513 1.18 MB/sec warmup 15 sec latency 146.818 ms 1 522 1.13 MB/sec warmup 16 sec latency 915.008 ms 1 522 1.06 MB/sec warmup 17 sec latency 1915.269 ms 02:30:58 (1790922658) shut down facet: mds2 facet_host: oleg306-server facet_failover_host: oleg306-server 1 522 1.00 MB/sec warmup 18 sec latency 2915.428 ms 1 522 0.95 MB/sec warmup 19 sec latency 3916.060 ms 1 522 0.00 MB/sec execute 1 sec latency 5916.498 ms 1 522 0.00 MB/sec execute 2 sec latency 6916.896 ms 1 522 0.00 MB/sec execute 3 sec latency 7920.669 ms 1 522 0.00 MB/sec execute 4 sec latency 8920.878 ms 1 522 0.00 MB/sec execute 5 sec latency 9921.347 ms 1 522 0.00 MB/sec execute 6 sec latency 10923.475 ms 1 522 0.00 MB/sec execute 7 sec latency 11923.665 ms 1 522 0.00 MB/sec execute 8 sec latency 12924.203 ms Failover mds2 to oleg306-server mount facets: mds2 1 522 0.00 MB/sec execute 9 sec latency 13925.012 ms 1 522 0.00 MB/sec execute 10 sec latency 14925.231 ms 1 522 0.00 MB/sec execute 11 sec latency 15928.856 ms 1 522 0.00 MB/sec execute 12 sec latency 16929.926 ms Start mds2: mount -t lustre -o localrecov lustre-mdt2/mdt2 /mnt/lustre-mds2 1 522 0.00 MB/sec execute 13 sec latency 17937.060 ms 1 522 0.00 MB/sec execute 14 sec latency 18937.318 ms 1 522 0.00 MB/sec execute 15 sec latency 19937.863 ms 1 522 0.00 MB/sec execute 16 sec latency 20945.313 ms 1 522 0.00 MB/sec execute 17 sec latency 21945.872 ms 1 522 0.00 MB/sec execute 18 sec latency 22946.197 ms 1 522 0.00 MB/sec execute 19 sec latency 23946.444 ms oleg306-server: oleg306-server.virtnet: executing set_default_debug -1 all 1 522 0.00 MB/sec execute 20 sec latency 24946.678 ms pdsh@oleg306-client: oleg306-server: ssh exited with exit code 1 1 522 0.00 MB/sec execute 21 sec latency 25949.783 ms Started lustre-MDT0001 02:31:22 (1790922682) targets are mounted 02:31:22 (1790922682) facet_failover done 1 609 0.13 MB/sec execute 22 sec latency 26156.868 ms 1 669 0.14 MB/sec execute 23 sec latency 147.155 ms 1 699 0.13 MB/sec execute 24 sec latency 133.772 ms 1 728 0.13 MB/sec execute 25 sec latency 179.841 ms 1 764 0.13 MB/sec execute 26 sec latency 120.600 ms 1 789 0.13 MB/sec execute 27 sec latency 199.459 ms oleg306-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 810 0.12 MB/sec execute 28 sec latency 208.799 ms 1 869 0.12 MB/sec execute 29 sec latency 110.251 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 890 0.12 MB/sec execute 30 sec latency 261.268 ms 1 916 0.12 MB/sec execute 31 sec latency 283.042 ms 1 949 0.12 MB/sec execute 32 sec latency 192.108 ms 1 980 0.12 MB/sec execute 33 sec latency 107.812 ms 1 997 0.11 MB/sec execute 34 sec latency 195.693 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1072 0.14 MB/sec execute 35 sec latency 82.643 ms 1 1131 0.14 MB/sec execute 36 sec latency 79.301 ms 1 1173 0.13 MB/sec execute 37 sec latency 99.719 ms 1 1215 0.13 MB/sec execute 38 sec latency 87.419 ms 1 1252 0.13 MB/sec execute 39 sec latency 96.924 ms 1 1387 0.20 MB/sec execute 40 sec latency 84.525 ms 1 1428 0.19 MB/sec execute 41 sec latency 154.822 ms 1 1474 0.19 MB/sec execute 42 sec latency 92.235 ms 1 1497 0.19 MB/sec execute 43 sec latency 495.993 ms 1 1554 0.18 MB/sec execute 44 sec latency 77.761 ms 1 1609 0.18 MB/sec execute 45 sec latency 85.515 ms 1 1656 0.18 MB/sec execute 46 sec latency 141.689 ms 1 1696 0.17 MB/sec execute 47 sec latency 131.074 ms tar: Error is not recoverable: exiting now 1 1764 0.17 MB/sec execute 48 sec latency 94.485 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Oct 2 02:31:49 EDT 2026 with return code 0 67051 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67051 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished