== replay-dual test 26: dbench and tar with mds failover ========================================================== 09:51:54 (1789998714) Starting client oleg351-client.virtnet: -o user_xattr,flock 192.168.203.151@tcp:/lustre /mnt/lustre Started clients oleg351-client.virtnet: 192.168.203.151@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 45236 Started dbench loop with 45237 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 2048 3762176 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3726336 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7488512 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 Sep 21 09:51:59 EDT 2026 waiting for dbench pid 45307 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 42 1.57 MB/sec warmup 1 sec latency 136.475 ms 1 105 2.46 MB/sec warmup 2 sec latency 106.449 ms 1 147 2.09 MB/sec warmup 3 sec latency 142.744 ms 1 190 1.89 MB/sec warmup 4 sec latency 127.783 ms test_26 fail mds1 1 times 1 239 1.83 MB/sec warmup 5 sec latency 105.736 ms 1 279 1.74 MB/sec warmup 6 sec latency 125.577 ms Failing mds1 on oleg351-server Stopping /mnt/lustre-mds1 (opts:) on oleg351-server 1 316 1.64 MB/sec warmup 7 sec latency 112.798 ms 1 349 1.56 MB/sec warmup 8 sec latency 253.032 ms 1 349 1.39 MB/sec warmup 9 sec latency 1253.356 ms 09:52:09 (1789998729) shut down facet: mds1 facet_host: oleg351-server facet_failover_host: oleg351-server 1 349 1.25 MB/sec warmup 10 sec latency 2253.967 ms 1 349 1.14 MB/sec warmup 11 sec latency 3254.527 ms 1 349 1.04 MB/sec warmup 12 sec latency 4254.765 ms 1 349 0.96 MB/sec warmup 13 sec latency 5255.066 ms 1 349 0.89 MB/sec warmup 14 sec latency 6255.727 ms 1 349 0.83 MB/sec warmup 15 sec latency 7256.471 ms 1 349 0.78 MB/sec warmup 16 sec latency 8257.166 ms 1 349 0.74 MB/sec warmup 17 sec latency 9257.422 ms 1 349 0.70 MB/sec warmup 18 sec latency 10257.715 ms 1 349 0.66 MB/sec warmup 19 sec latency 11258.855 ms Failover mds1 to oleg351-server mount facets: mds1 1 349 0.00 MB/sec execute 1 sec latency 13259.284 ms 1 349 0.00 MB/sec execute 2 sec latency 14259.544 ms 1 349 0.00 MB/sec execute 3 sec latency 15259.756 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 349 0.00 MB/sec execute 4 sec latency 16260.076 ms 1 349 0.00 MB/sec execute 5 sec latency 17260.452 ms 1 349 0.00 MB/sec execute 6 sec latency 18266.903 ms 1 349 0.00 MB/sec execute 7 sec latency 19271.735 ms 1 349 0.00 MB/sec execute 8 sec latency 20271.958 ms oleg351-server: oleg351-server.virtnet: executing set_default_debug -1 all 1 362 0.04 MB/sec execute 9 sec latency 21086.454 ms pdsh@oleg351-client: oleg351-server: ssh exited with exit code 1 1 421 0.23 MB/sec execute 10 sec latency 81.921 ms Started lustre-MDT0000 09:52:30 (1789998750) targets are mounted 09:52:30 (1789998750) facet_failover done 1 469 0.35 MB/sec execute 11 sec latency 94.672 ms 1 513 0.43 MB/sec execute 12 sec latency 97.559 ms 1 601 0.65 MB/sec execute 13 sec latency 140.714 ms 1 656 0.61 MB/sec execute 14 sec latency 125.247 ms 1 674 0.58 MB/sec execute 15 sec latency 281.830 ms 1 708 0.54 MB/sec execute 16 sec latency 165.858 ms oleg351-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 731 0.52 MB/sec execute 17 sec latency 175.739 ms 1 767 0.49 MB/sec execute 18 sec latency 114.550 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 798 0.47 MB/sec execute 19 sec latency 201.260 ms 1 827 0.45 MB/sec execute 20 sec latency 120.354 ms 1 881 0.43 MB/sec execute 21 sec latency 152.454 ms 1 913 0.42 MB/sec execute 22 sec latency 142.181 ms 1 943 0.40 MB/sec execute 23 sec latency 233.792 ms 1 981 0.39 MB/sec execute 24 sec latency 190.032 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2432 2206080 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 10240 3704832 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 44032 3651584 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 54272 7356416 1% /mnt/lustre 1 1041 0.41 MB/sec execute 25 sec latency 89.408 ms 1 1103 0.40 MB/sec execute 26 sec latency 64.062 ms 1 1147 0.39 MB/sec execute 27 sec latency 128.078 ms 1 1193 0.37 MB/sec execute 28 sec latency 153.566 ms 1 1244 0.36 MB/sec execute 29 sec latency 72.093 ms test_26 fail mds1 2 times 1 1382 0.45 MB/sec execute 30 sec latency 100.328 ms 1 1426 0.43 MB/sec execute 31 sec latency 93.054 ms Failing mds1 on oleg351-server 1 1476 0.42 MB/sec execute 32 sec latency 75.329 ms Stopping /mnt/lustre-mds1 (opts:) on oleg351-server 1 1522 0.41 MB/sec execute 33 sec latency 178.446 ms 1 1542 0.40 MB/sec execute 34 sec latency 741.020 ms 1 1542 0.39 MB/sec execute 35 sec latency 1741.194 ms 09:52:55 (1789998775) shut down facet: mds1 facet_host: oleg351-server facet_failover_host: oleg351-server 1 1542 0.38 MB/sec execute 36 sec latency 2745.478 ms 1 1542 0.37 MB/sec execute 37 sec latency 3746.955 ms 1 1542 0.36 MB/sec execute 38 sec latency 4747.145 ms 1 1542 0.35 MB/sec execute 39 sec latency 5747.335 ms 1 1542 0.34 MB/sec execute 40 sec latency 6747.900 ms 1 1542 0.33 MB/sec execute 41 sec latency 7748.131 ms 1 1542 0.32 MB/sec execute 42 sec latency 8748.675 ms 1 1542 0.32 MB/sec execute 43 sec latency 9748.922 ms 1 1542 0.31 MB/sec execute 44 sec latency 10749.151 ms 1 1542 0.30 MB/sec execute 45 sec latency 11749.646 ms 1 1542 0.29 MB/sec execute 46 sec latency 12750.848 ms Failover mds1 to oleg351-server mount facets: mds1 1 1542 0.29 MB/sec execute 47 sec latency 13751.356 ms 1 1542 0.28 MB/sec execute 48 sec latency 14751.611 ms 1 1542 0.28 MB/sec execute 49 sec latency 15751.821 ms 1 1542 0.27 MB/sec execute 50 sec latency 16752.153 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1542 0.27 MB/sec execute 51 sec latency 17752.446 ms 1 1542 0.26 MB/sec execute 52 sec latency 18754.606 ms 1 1542 0.26 MB/sec execute 53 sec latency 19756.015 ms 1 1542 0.25 MB/sec execute 54 sec latency 20757.140 ms 1 1558 0.25 MB/sec execute 55 sec latency 21431.323 ms oleg351-server: oleg351-server.virtnet: executing set_default_debug -1 all pdsh@oleg351-client: oleg351-server: ssh exited with exit code 1 1 1616 0.24 MB/sec execute 56 sec latency 83.089 ms Started lustre-MDT0000 09:53:16 (1789998796) targets are mounted 09:53:16 (1789998796) facet_failover done 1 1655 0.24 MB/sec execute 57 sec latency 187.019 ms 1 1704 0.24 MB/sec execute 58 sec latency 105.578 ms 1 1771 0.23 MB/sec execute 59 sec latency 80.613 ms 1 1825 0.23 MB/sec execute 60 sec latency 101.614 ms 1 1869 0.23 MB/sec execute 61 sec latency 93.668 ms 1 1914 0.22 MB/sec execute 62 sec latency 236.517 ms oleg351-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 1978 0.22 MB/sec execute 63 sec latency 87.845 ms 1 2006 0.22 MB/sec execute 64 sec latency 134.608 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2060 0.22 MB/sec execute 65 sec latency 107.437 ms 1 2116 0.21 MB/sec execute 66 sec latency 109.986 ms 1 2162 0.21 MB/sec execute 67 sec latency 119.203 ms 1 2209 0.21 MB/sec execute 68 sec latency 115.014 ms 1 2305 0.22 MB/sec execute 69 sec latency 68.747 ms 1 2354 0.22 MB/sec execute 70 sec latency 301.135 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2816 2205696 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 13312 3741696 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 60416 3694592 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 73728 7436288 1% /mnt/lustre 1 2396 0.22 MB/sec execute 71 sec latency 159.093 ms 1 2424 0.22 MB/sec execute 72 sec latency 284.802 ms 1 2463 0.22 MB/sec execute 73 sec latency 154.665 ms 1 2495 0.22 MB/sec execute 74 sec latency 148.994 ms 1 2566 0.22 MB/sec execute 75 sec latency 313.512 ms 1 2577 0.22 MB/sec execute 76 sec latency 982.623 ms test_26 fail mds1 3 times 1 2724 0.25 MB/sec execute 77 sec latency 86.962 ms 1 2787 0.25 MB/sec execute 78 sec latency 209.798 ms Failing mds1 on oleg351-server 1 2919 0.26 MB/sec execute 79 sec latency 100.890 ms Stopping /mnt/lustre-mds1 (opts:) on oleg351-server 1 2975 0.26 MB/sec execute 80 sec latency 248.885 ms 1 2975 0.26 MB/sec execute 81 sec latency 1250.722 ms 09:53:42 (1789998822) shut down 1 2975 0.26 MB/sec execute 82 sec latency 2250.881 ms facet: mds1 facet_host: oleg351-server facet_failover_host: oleg351-server 1 2975 0.25 MB/sec execute 83 sec latency 3251.124 ms 1 2975 0.25 MB/sec execute 84 sec latency 4251.461 ms 1 2975 0.25 MB/sec execute 85 sec latency 5251.722 ms 1 2975 0.24 MB/sec execute 86 sec latency 6252.095 ms 1 2975 0.24 MB/sec execute 87 sec latency 7252.484 ms 1 2975 0.24 MB/sec execute 88 sec latency 8255.504 ms 1 2975 0.24 MB/sec execute 89 sec latency 9255.752 ms 1 2975 0.23 MB/sec execute 90 sec latency 10256.884 ms 1 2975 0.23 MB/sec execute 91 sec latency 11257.134 ms 1 2975 0.23 MB/sec execute 92 sec latency 12257.801 ms Failover mds1 to oleg351-server mount facets: mds1 1 2975 0.23 MB/sec execute 93 sec latency 13258.051 ms 1 2975 0.22 MB/sec execute 94 sec latency 14258.550 ms 1 2975 0.22 MB/sec execute 95 sec latency 15258.901 ms 1 2975 0.22 MB/sec execute 96 sec latency 16259.151 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2975 0.22 MB/sec execute 97 sec latency 17259.396 ms 1 2975 0.21 MB/sec execute 98 sec latency 18260.375 ms 1 2975 0.21 MB/sec execute 99 sec latency 19260.838 ms 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 1 cleanup 111 sec oleg351-server: oleg351-server.virtnet: executing set_default_debug -1 all 1 cleanup 112 sec pdsh@oleg351-client: oleg351-server: ssh exited with exit code 1 1 cleanup 113 sec Started lustre-MDT0000 09:54:13 (1789998853) targets are mounted 09:54:13 (1789998853) facet_failover done 1 cleanup 114 sec 1 cleanup 115 sec 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 0 cleanup 123 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 412 102.371 21086.434 Close 348 72.639 21431.290 Rename 19 92.615 154.634 Unlink 45 26.937 79.396 Qpathinfo 381 121.553 40166.108 Qfileinfo 117 1.696 13.328 Qfsinfo 55 3.199 18.791 Sfileinfo 50 56.142 112.207 Find 131 6.057 47.754 WriteX 396 10.940 64.454 ReadX 633 1.642 88.729 LockX 2 10.297 12.005 UnlockX 2 11.450 14.918 Flush 36 143.307 301.008 Throughput 0.211641 MB/sec 1 clients 1 procs max_latency=21431.323 ms stopping dbench on /mnt/lustre at Mon Sep 21 09:54:23 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre oleg351-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 Mon Sep 21 09:54:29 EDT 2026 waiting for dbench pid 48243 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 51 2.10 MB/sec warmup 1 sec latency 87.736 ms 1 111 2.62 MB/sec warmup 2 sec latency 138.900 ms 1 146 2.09 MB/sec warmup 3 sec latency 144.119 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 3200 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 28672 3706880 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 23552 3727360 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 52224 7434240 1% /mnt/lustre 1 179 1.81 MB/sec warmup 4 sec latency 136.515 ms 1 212 1.65 MB/sec warmup 5 sec latency 176.121 ms 1 258 1.61 MB/sec warmup 6 sec latency 111.075 ms 1 308 1.60 MB/sec warmup 7 sec latency 104.985 ms 1 358 1.60 MB/sec warmup 8 sec latency 89.008 ms test_26 fail mds1 4 times 1 413 1.62 MB/sec warmup 9 sec latency 107.249 ms 1 460 1.62 MB/sec warmup 10 sec latency 119.203 ms Failing mds1 on oleg351-server 1 501 1.59 MB/sec warmup 11 sec latency 151.216 ms Stopping /mnt/lustre-mds1 (opts:) on oleg351-server 1 543 1.59 MB/sec warmup 12 sec latency 170.330 ms 1 600 1.61 MB/sec warmup 13 sec latency 743.473 ms 1 600 1.50 MB/sec warmup 14 sec latency 1743.709 ms 09:54:43 (1789998883) shut down facet: mds1 facet_host: oleg351-server facet_failover_host: oleg351-server 1 600 1.40 MB/sec warmup 15 sec latency 2744.844 ms 1 600 1.31 MB/sec warmup 16 sec latency 3745.241 ms 1 600 1.23 MB/sec warmup 17 sec latency 4745.473 ms 1 600 1.16 MB/sec warmup 18 sec latency 5747.039 ms 1 600 1.10 MB/sec warmup 19 sec latency 6747.651 ms 1 600 0.00 MB/sec execute 1 sec latency 8748.111 ms 1 600 0.00 MB/sec execute 2 sec latency 9749.509 ms 1 600 0.00 MB/sec execute 3 sec latency 10749.771 ms 1 600 0.00 MB/sec execute 4 sec latency 11752.429 ms Failover mds1 to oleg351-server mount facets: mds1 1 600 0.00 MB/sec execute 5 sec latency 12752.626 ms 1 600 0.00 MB/sec execute 6 sec latency 13752.891 ms 1 600 0.00 MB/sec execute 7 sec latency 14753.137 ms 1 600 0.00 MB/sec execute 8 sec latency 15753.714 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 600 0.00 MB/sec execute 9 sec latency 16753.963 ms 1 600 0.00 MB/sec execute 10 sec latency 17754.137 ms 1 600 0.00 MB/sec execute 11 sec latency 18756.379 ms 1 600 0.00 MB/sec execute 12 sec latency 19757.278 ms oleg351-server: oleg351-server.virtnet: executing set_default_debug -1 all 1 600 0.00 MB/sec execute 13 sec latency 20757.519 ms pdsh@oleg351-client: oleg351-server: ssh exited with exit code 1 1 600 0.00 MB/sec execute 14 sec latency 21757.848 ms Started lustre-MDT0000 09:55:03 (1789998903) targets are mounted 09:55:03 (1789998903) facet_failover done 1 600 0.00 MB/sec execute 15 sec latency 22758.157 ms 1 600 0.00 MB/sec execute 16 sec latency 23758.612 ms 1 600 0.00 MB/sec execute 17 sec latency 24759.076 ms 1 600 0.00 MB/sec execute 18 sec latency 25759.378 ms 1 600 0.00 MB/sec execute 19 sec latency 26760.995 ms 1 600 0.00 MB/sec execute 20 sec latency 27761.270 ms 1 600 0.00 MB/sec execute 21 sec latency 28762.053 ms 1 600 0.00 MB/sec execute 22 sec latency 29764.881 ms 1 600 0.00 MB/sec execute 23 sec latency 30765.148 ms 1 600 0.00 MB/sec execute 24 sec latency 31766.739 ms 1 600 0.00 MB/sec execute 25 sec latency 32767.846 ms 1 600 0.00 MB/sec execute 26 sec latency 33768.779 ms 1 600 0.00 MB/sec execute 27 sec latency 34769.651 ms 1 600 0.00 MB/sec execute 28 sec latency 35771.950 ms 1 600 0.00 MB/sec execute 29 sec latency 36772.278 ms 1 600 0.00 MB/sec execute 30 sec latency 37774.505 ms 1 600 0.00 MB/sec execute 31 sec latency 38776.266 ms 1 600 0.00 MB/sec execute 32 sec latency 39777.032 ms 1 639 0.00 MB/sec execute 33 sec latency 40208.719 ms 1 673 0.01 MB/sec execute 34 sec latency 194.331 ms 1 711 0.01 MB/sec execute 35 sec latency 98.656 ms 1 730 0.01 MB/sec execute 36 sec latency 271.335 ms 1 765 0.01 MB/sec execute 37 sec latency 106.877 ms oleg351-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 791 0.01 MB/sec execute 38 sec latency 154.718 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 810 0.01 MB/sec execute 39 sec latency 137.478 ms 1 873 0.02 MB/sec execute 40 sec latency 87.646 ms 1 900 0.02 MB/sec execute 41 sec latency 260.641 ms 1 921 0.02 MB/sec execute 42 sec latency 226.915 ms 1 969 0.02 MB/sec execute 43 sec latency 109.031 ms 1 995 0.02 MB/sec execute 44 sec latency 211.362 ms 1 1050 0.04 MB/sec execute 45 sec latency 164.231 ms 1 1113 0.04 MB/sec execute 46 sec latency 80.242 ms 1 1155 0.04 MB/sec execute 47 sec latency 99.070 ms 1 1211 0.04 MB/sec execute 48 sec latency 66.555 ms 1 1259 0.04 MB/sec execute 49 sec latency 131.689 ms 1 1403 0.10 MB/sec execute 50 sec latency 59.308 ms 1 1468 0.10 MB/sec execute 51 sec latency 62.667 ms 1 1512 0.10 MB/sec execute 52 sec latency 203.269 ms 1 1578 0.10 MB/sec execute 53 sec latency 49.439 ms 1 1632 0.10 MB/sec execute 54 sec latency 196.605 ms 1 1680 0.10 MB/sec execute 55 sec latency 244.253 ms 1 1754 0.09 MB/sec execute 56 sec latency 82.173 ms 1 1823 0.09 MB/sec execute 57 sec latency 80.353 ms 1 1884 0.09 MB/sec execute 58 sec latency 83.938 ms 1 1948 0.09 MB/sec execute 59 sec latency 242.465 ms 1 2014 0.09 MB/sec execute 60 sec latency 74.623 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Sep 21 09:55:50 EDT 2026 with return code 0 1 2087 0.09 MB/sec execute 61 sec latency 83.672 ms 48243 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48243 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished