== replay-dual test 26: dbench and tar with mds failover ========================================================== 14:48:25 (1787856505) Starting client oleg110-client.virtnet: -o user_xattr,flock 192.168.201.110@tcp:/lustre /mnt/lustre Started clients oleg110-client.virtnet: 192.168.201.110@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 45242 Started dbench loop with 45243 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 3732480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3762176 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 16384 7494656 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 Thu Aug 27 14:48:33 EDT 2026 waiting for dbench pid 45312 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 50 2.10 MB/sec warmup 1 sec latency 107.364 ms 1 91 2.10 MB/sec warmup 2 sec latency 221.051 ms 1 121 1.83 MB/sec warmup 3 sec latency 189.233 ms 1 155 1.63 MB/sec warmup 4 sec latency 156.938 ms test_26 fail mds1 1 times 1 184 1.47 MB/sec warmup 5 sec latency 176.388 ms 1 210 1.35 MB/sec warmup 6 sec latency 235.321 ms 1 231 1.27 MB/sec warmup 7 sec latency 226.538 ms Failing mds1 on oleg110-server 1 260 1.22 MB/sec warmup 8 sec latency 153.683 ms Stopping /mnt/lustre-mds1 (opts:) on oleg110-server 1 287 1.19 MB/sec warmup 9 sec latency 159.854 ms 1 315 1.15 MB/sec warmup 10 sec latency 135.331 ms 1 322 1.07 MB/sec warmup 11 sec latency 767.398 ms 1 322 0.98 MB/sec warmup 12 sec latency 1767.534 ms 1 322 0.90 MB/sec warmup 13 sec latency 2767.882 ms 14:48:46 (1787856526) shut down facet: mds1 facet_host: oleg110-server facet_failover_host: oleg110-server 1 322 0.84 MB/sec warmup 14 sec latency 3769.764 ms 1 322 0.78 MB/sec warmup 15 sec latency 4769.947 ms 1 322 0.73 MB/sec warmup 16 sec latency 5770.141 ms 1 322 0.69 MB/sec warmup 17 sec latency 6770.722 ms 1 322 0.65 MB/sec warmup 18 sec latency 7770.918 ms 1 322 0.62 MB/sec warmup 19 sec latency 8771.169 ms 1 322 0.00 MB/sec execute 1 sec latency 10774.374 ms 1 322 0.00 MB/sec execute 2 sec latency 11774.689 ms 1 322 0.00 MB/sec execute 3 sec latency 12775.952 ms Failover mds1 to oleg110-server mount facets: mds1 1 322 0.00 MB/sec execute 4 sec latency 13776.184 ms 1 322 0.00 MB/sec execute 5 sec latency 14776.538 ms 1 322 0.00 MB/sec execute 6 sec latency 15776.956 ms 1 322 0.00 MB/sec execute 7 sec latency 16778.341 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 322 0.00 MB/sec execute 8 sec latency 17779.315 ms 1 322 0.00 MB/sec execute 9 sec latency 18783.164 ms 1 322 0.00 MB/sec execute 10 sec latency 19783.354 ms 1 322 0.00 MB/sec execute 11 sec latency 20785.262 ms 1 322 0.00 MB/sec execute 12 sec latency 21785.546 ms 1 338 0.04 MB/sec execute 13 sec latency 22270.877 ms oleg110-server: oleg110-server.virtnet: executing set_default_debug -1 all 1 357 0.07 MB/sec execute 14 sec latency 211.570 ms pdsh@oleg110-client: oleg110-server: ssh exited with exit code 1 1 415 0.19 MB/sec execute 15 sec latency 113.654 ms Started lustre-MDT0000 14:49:09 (1787856549) targets are mounted 14:49:09 (1787856549) facet_failover done 1 461 0.28 MB/sec execute 16 sec latency 123.661 ms 1 501 0.34 MB/sec execute 17 sec latency 109.470 ms 1 541 0.41 MB/sec execute 18 sec latency 157.178 ms 1 607 0.49 MB/sec execute 19 sec latency 183.653 ms 1 661 0.47 MB/sec execute 20 sec latency 107.250 ms 1 676 0.45 MB/sec execute 21 sec latency 226.371 ms 1 702 0.43 MB/sec execute 22 sec latency 214.232 ms 1 721 0.41 MB/sec execute 23 sec latency 223.841 ms oleg110-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 740 0.40 MB/sec execute 24 sec latency 311.563 ms 1 776 0.38 MB/sec execute 25 sec latency 101.984 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 791 0.37 MB/sec execute 26 sec latency 316.982 ms 1 815 0.36 MB/sec execute 27 sec latency 119.156 ms 1 874 0.35 MB/sec execute 28 sec latency 176.632 ms 1 903 0.34 MB/sec execute 29 sec latency 133.764 ms 1 926 0.33 MB/sec execute 30 sec latency 208.357 ms 1 969 0.32 MB/sec execute 31 sec latency 101.311 ms 1 985 0.32 MB/sec execute 32 sec latency 276.787 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2432 2206080 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 48128 3672064 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 9216 3746816 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 57344 7418880 1% /mnt/lustre 1 1045 0.34 MB/sec execute 33 sec latency 112.025 ms 1 1082 0.33 MB/sec execute 34 sec latency 93.879 ms 1 1127 0.32 MB/sec execute 35 sec latency 122.986 ms 1 1161 0.31 MB/sec execute 36 sec latency 146.945 ms 1 1200 0.30 MB/sec execute 37 sec latency 120.957 ms 1 1242 0.30 MB/sec execute 38 sec latency 99.286 ms test_26 fail mds1 2 times 1 1384 0.36 MB/sec execute 39 sec latency 80.401 ms 1 1418 0.36 MB/sec execute 40 sec latency 133.195 ms Failing mds1 on oleg110-server 1 1487 0.35 MB/sec execute 41 sec latency 88.791 ms Stopping /mnt/lustre-mds1 (opts:) on oleg110-server 1 1568 0.34 MB/sec execute 42 sec latency 54.651 ms 1 1603 0.33 MB/sec execute 43 sec latency 477.771 ms 1 1603 0.33 MB/sec execute 44 sec latency 1477.953 ms 14:49:38 (1787856578) shut down 1 1603 0.32 MB/sec execute 45 sec latency 2478.773 ms facet: mds1 facet_host: oleg110-server facet_failover_host: oleg110-server 1 1603 0.31 MB/sec execute 46 sec latency 3480.012 ms 1 1603 0.31 MB/sec execute 47 sec latency 4480.913 ms 1 1603 0.30 MB/sec execute 48 sec latency 5481.114 ms 1 1603 0.29 MB/sec execute 49 sec latency 6481.346 ms 1 1603 0.29 MB/sec execute 50 sec latency 7481.522 ms 1 1603 0.28 MB/sec execute 51 sec latency 8481.745 ms 1 1603 0.28 MB/sec execute 52 sec latency 9483.021 ms 1 1603 0.27 MB/sec execute 53 sec latency 10483.658 ms 1 1603 0.27 MB/sec execute 54 sec latency 11484.146 ms 1 1603 0.26 MB/sec execute 55 sec latency 12485.062 ms Failover mds1 to oleg110-server mount facets: mds1 1 1603 0.26 MB/sec execute 56 sec latency 13489.473 ms 1 1603 0.25 MB/sec execute 57 sec latency 14489.670 ms 1 1603 0.25 MB/sec execute 58 sec latency 15489.815 ms 1 1603 0.24 MB/sec execute 59 sec latency 16494.640 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1603 0.24 MB/sec execute 60 sec latency 17496.131 ms 1 1603 0.24 MB/sec execute 61 sec latency 18496.268 ms 1 1603 0.23 MB/sec execute 62 sec latency 19496.434 ms 1 1603 0.23 MB/sec execute 63 sec latency 20498.679 ms 1 1603 0.22 MB/sec execute 64 sec latency 21499.066 ms 1 1603 0.22 MB/sec execute 65 sec latency 22499.312 ms 1 1603 0.22 MB/sec execute 66 sec latency 23499.783 ms oleg110-server: oleg110-server.virtnet: executing set_default_debug -1 all 1 1634 0.21 MB/sec execute 67 sec latency 23534.195 ms pdsh@oleg110-client: oleg110-server: ssh exited with exit code 1 1 1660 0.21 MB/sec execute 68 sec latency 330.057 ms 1 1694 0.21 MB/sec execute 69 sec latency 183.462 ms Started lustre-MDT0000 14:50:03 (1787856603) targets are mounted 14:50:03 (1787856603) facet_failover done 1 1733 0.21 MB/sec execute 70 sec latency 139.546 ms 1 1810 0.20 MB/sec execute 71 sec latency 64.101 ms 1 1843 0.20 MB/sec execute 72 sec latency 212.562 ms 1 1873 0.20 MB/sec execute 73 sec latency 192.906 ms 1 1888 0.20 MB/sec execute 74 sec latency 445.389 ms 1 1967 0.20 MB/sec execute 75 sec latency 491.345 ms 1 1996 0.19 MB/sec execute 76 sec latency 118.539 ms oleg110-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 2030 0.19 MB/sec execute 77 sec latency 127.837 ms 1 2080 0.19 MB/sec execute 78 sec latency 135.898 ms 1 2117 0.19 MB/sec execute 79 sec latency 212.500 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2150 0.19 MB/sec execute 80 sec latency 119.422 ms 1 2162 0.18 MB/sec execute 81 sec latency 175.542 ms 1 2198 0.18 MB/sec execute 82 sec latency 184.431 ms 1 2272 0.18 MB/sec execute 83 sec latency 98.816 ms 1 2334 0.19 MB/sec execute 84 sec latency 93.582 ms 1 2346 0.19 MB/sec execute 85 sec latency 408.672 ms 1 2376 0.19 MB/sec execute 86 sec latency 107.040 ms 1 2394 0.19 MB/sec execute 87 sec latency 360.348 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2816 2205696 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 62464 3699712 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 11264 3732480 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7432192 1% /mnt/lustre 1 2416 0.19 MB/sec execute 88 sec latency 200.010 ms 1 2439 0.18 MB/sec execute 89 sec latency 412.494 ms 1 2473 0.19 MB/sec execute 90 sec latency 97.227 ms 1 2496 0.19 MB/sec execute 91 sec latency 287.083 ms 1 2562 0.19 MB/sec execute 92 sec latency 107.622 ms 1 2566 0.18 MB/sec execute 93 sec latency 844.901 ms 1 2569 0.18 MB/sec execute 94 sec latency 1698.657 ms test_26 fail mds1 3 times 1 2608 0.18 MB/sec execute 95 sec latency 93.772 ms 1 2752 0.21 MB/sec execute 96 sec latency 108.140 ms 1 2779 0.21 MB/sec execute 97 sec latency 249.856 ms Failing mds1 on oleg110-server 1 2894 0.21 MB/sec execute 98 sec latency 119.828 ms Stopping /mnt/lustre-mds1 (opts:) on oleg110-server 1 2923 0.22 MB/sec execute 99 sec latency 255.098 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 14:50:36 (1787856636) shut down facet: mds1 facet_host: oleg110-server facet_failover_host: oleg110-server 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 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec Failover mds1 to oleg110-server mount facets: mds1 1 cleanup 114 sec 1 cleanup 115 sec 1 cleanup 116 sec 1 cleanup 117 sec Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 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 1 cleanup 131 sec 1 cleanup 132 sec 1 cleanup 133 sec 1 cleanup 134 sec oleg110-server: oleg110-server.virtnet: executing set_default_debug -1 all 1 cleanup 135 sec pdsh@oleg110-client: oleg110-server: ssh exited with exit code 1 1 cleanup 136 sec Started lustre-MDT0000 14:51:10 (1787856670) targets are mounted 14:51:10 (1787856670) facet_failover done 1 cleanup 137 sec 1 cleanup 138 sec 1 cleanup 139 sec 1 cleanup 140 sec 1 cleanup 141 sec 1 cleanup 142 sec 1 cleanup 143 sec 0 cleanup 144 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 414 63.362 212.544 Close 352 77.830 22270.855 Rename 19 109.186 185.945 Unlink 44 31.359 72.324 Qpathinfo 378 187.916 39876.578 Qfileinfo 120 2.494 14.500 Qfsinfo 55 6.012 37.375 Sfileinfo 50 72.699 149.411 Find 130 6.702 38.402 WriteX 411 15.018 140.707 ReadX 633 2.223 127.921 LockX 2 27.812 44.967 UnlockX 2 42.104 64.424 Flush 36 195.100 491.322 Throughput 0.218989 MB/sec 1 clients 1 procs max_latency=23534.195 ms stopping dbench on /mnt/lustre at Thu Aug 27 14:51:17 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre oleg110-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0000-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 Thu Aug 27 14:51:25 EDT 2026 waiting for dbench pid 48281 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 29 0.98 MB/sec warmup 1 sec latency 24.769 ms 1 78 1.70 MB/sec warmup 2 sec latency 163.136 ms 1 111 1.74 MB/sec warmup 3 sec latency 250.149 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3200 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 49152 3680256 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 4096 3729408 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 53248 7409664 1% /mnt/lustre 1 137 1.50 MB/sec warmup 4 sec latency 263.700 ms 1 157 1.31 MB/sec warmup 5 sec latency 239.074 ms 1 196 1.30 MB/sec warmup 6 sec latency 208.564 ms 1 239 1.30 MB/sec warmup 7 sec latency 133.640 ms 1 282 1.30 MB/sec warmup 8 sec latency 125.384 ms 1 331 1.33 MB/sec warmup 9 sec latency 113.939 ms test_26 fail mds1 4 times 1 365 1.30 MB/sec warmup 10 sec latency 133.383 ms 1 399 1.28 MB/sec warmup 11 sec latency 140.745 ms Failing mds1 on oleg110-server 1 429 1.26 MB/sec warmup 12 sec latency 151.503 ms Stopping /mnt/lustre-mds1 (opts:) on oleg110-server 1 477 1.28 MB/sec warmup 13 sec latency 106.479 ms 1 500 1.24 MB/sec warmup 14 sec latency 548.024 ms 1 500 1.16 MB/sec warmup 15 sec latency 1548.419 ms 14:51:41 (1787856701) shut down 1 500 1.09 MB/sec warmup 16 sec latency 2548.546 ms facet: mds1 facet_host: oleg110-server facet_failover_host: oleg110-server 1 500 1.03 MB/sec warmup 17 sec latency 3549.575 ms 1 500 0.97 MB/sec warmup 18 sec latency 4549.806 ms 1 500 0.92 MB/sec warmup 19 sec latency 5550.029 ms 1 500 0.00 MB/sec execute 1 sec latency 7555.021 ms 1 500 0.00 MB/sec execute 2 sec latency 8556.414 ms 1 500 0.00 MB/sec execute 3 sec latency 9556.678 ms 1 500 0.00 MB/sec execute 4 sec latency 10563.935 ms 1 500 0.00 MB/sec execute 5 sec latency 11564.082 ms 1 500 0.00 MB/sec execute 6 sec latency 12566.595 ms Failover mds1 to oleg110-server mount facets: mds1 1 500 0.00 MB/sec execute 7 sec latency 13567.176 ms 1 500 0.00 MB/sec execute 8 sec latency 14571.916 ms 1 500 0.00 MB/sec execute 9 sec latency 15572.185 ms 1 500 0.00 MB/sec execute 10 sec latency 16572.406 ms 1 500 0.00 MB/sec execute 11 sec latency 17572.689 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 500 0.00 MB/sec execute 12 sec latency 18575.744 ms 1 500 0.00 MB/sec execute 13 sec latency 19575.920 ms 1 500 0.00 MB/sec execute 14 sec latency 20576.167 ms 1 500 0.00 MB/sec execute 15 sec latency 21577.397 ms 1 500 0.00 MB/sec execute 16 sec latency 22577.592 ms 1 500 0.00 MB/sec execute 17 sec latency 23578.978 ms 1 500 0.00 MB/sec execute 18 sec latency 24579.232 ms oleg110-server: oleg110-server.virtnet: executing set_default_debug -1 all 1 500 0.00 MB/sec execute 19 sec latency 25581.696 ms 1 500 0.00 MB/sec execute 20 sec latency 26584.990 ms pdsh@oleg110-client: oleg110-server: ssh exited with exit code 1 1 500 0.00 MB/sec execute 21 sec latency 27585.144 ms Started lustre-MDT0000 14:52:06 (1787856726) targets are mounted 14:52:06 (1787856726) facet_failover done 1 500 0.00 MB/sec execute 22 sec latency 28585.289 ms 1 500 0.00 MB/sec execute 23 sec latency 29585.689 ms 1 500 0.00 MB/sec execute 24 sec latency 30585.831 ms 1 500 0.00 MB/sec execute 25 sec latency 31586.022 ms 1 500 0.00 MB/sec execute 26 sec latency 32587.126 ms 1 500 0.00 MB/sec execute 27 sec latency 33587.702 ms 1 500 0.00 MB/sec execute 28 sec latency 34588.150 ms 1 500 0.00 MB/sec execute 29 sec latency 35588.629 ms 1 500 0.00 MB/sec execute 30 sec latency 36588.835 ms 1 500 0.00 MB/sec execute 31 sec latency 37589.773 ms 1 500 0.00 MB/sec execute 32 sec latency 38590.017 ms 1 500 0.00 MB/sec execute 33 sec latency 39591.095 ms 1 500 0.00 MB/sec execute 34 sec latency 40591.309 ms 1 503 0.00 MB/sec execute 35 sec latency 41063.066 ms 1 572 0.05 MB/sec execute 36 sec latency 140.534 ms 1 639 0.10 MB/sec execute 37 sec latency 87.945 ms 1 666 0.10 MB/sec execute 38 sec latency 349.085 ms 1 692 0.10 MB/sec execute 39 sec latency 156.637 ms 1 718 0.10 MB/sec execute 40 sec latency 187.060 ms oleg110-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 733 0.09 MB/sec execute 41 sec latency 278.621 ms 1 762 0.09 MB/sec execute 42 sec latency 195.962 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 779 0.09 MB/sec execute 43 sec latency 192.694 ms 1 796 0.09 MB/sec execute 44 sec latency 373.292 ms 1 824 0.09 MB/sec execute 45 sec latency 130.817 ms 1 874 0.09 MB/sec execute 46 sec latency 328.734 ms 1 903 0.09 MB/sec execute 47 sec latency 177.276 ms 1 933 0.09 MB/sec execute 48 sec latency 223.448 ms 1 977 0.09 MB/sec execute 49 sec latency 102.966 ms 1 1028 0.11 MB/sec execute 50 sec latency 277.849 ms 1 1085 0.11 MB/sec execute 51 sec latency 92.817 ms 1 1139 0.11 MB/sec execute 52 sec latency 87.651 ms 1 1181 0.10 MB/sec execute 53 sec latency 122.167 ms 1 1223 0.10 MB/sec execute 54 sec latency 103.514 ms 1 1249 0.10 MB/sec execute 55 sec latency 205.726 ms 1 1379 0.15 MB/sec execute 56 sec latency 96.657 ms 1 1426 0.15 MB/sec execute 57 sec latency 84.159 ms 1 1474 0.15 MB/sec execute 58 sec latency 90.045 ms 1 1497 0.15 MB/sec execute 59 sec latency 361.443 ms 1 1558 0.14 MB/sec execute 60 sec latency 78.683 ms 1 1583 0.14 MB/sec execute 61 sec latency 76.492 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Aug 27 14:52:46 EDT 2026 with return code 0 48281 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48281 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished