== replay-dual test 26: dbench and tar with mds failover ========================================================== 07:47:27 (1749124047) Starting client oleg215-client.virtnet: -o user_xattr,flock 192.168.202.115@tcp:/lustre /mnt/lustre Started clients oleg215-client.virtnet: 192.168.202.115@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 5133 Started dbench loop with 5134 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar 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 Jun 5 07:47:28 EDT 2025 waiting for dbench pid 5175 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2280 1285408 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2028 1285660 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 26120 3555924 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27656 7161408 1% /mnt/lustre 1 222 8.62 MB/sec warmup 1 sec latency 25.674 ms 1 449 7.86 MB/sec warmup 2 sec latency 23.065 ms 1 664 7.05 MB/sec warmup 3 sec latency 238.883 ms 1 896 5.42 MB/sec warmup 4 sec latency 19.854 ms test_26 fail mds1 1 times 1 1177 4.60 MB/sec warmup 5 sec latency 18.728 ms Failing mds1 on oleg215-server Stopping /mnt/lustre-mds1 (opts:) on oleg215-server 1 1436 4.34 MB/sec warmup 6 sec latency 363.485 ms 07:47:35 (1749124055) shut down facet: mds1 facet_host: oleg215-server facet_failover_host: oleg215-server 1 1436 3.72 MB/sec warmup 7 sec latency 1363.636 ms 1 1436 3.25 MB/sec warmup 8 sec latency 2363.789 ms 1 1436 2.89 MB/sec warmup 9 sec latency 3363.931 ms 1 1436 2.60 MB/sec warmup 10 sec latency 4364.112 ms 1 1436 2.37 MB/sec warmup 11 sec latency 5364.267 ms 1 1436 2.17 MB/sec warmup 12 sec latency 6364.420 ms 1 1436 2.00 MB/sec warmup 13 sec latency 7364.570 ms 1 1436 1.86 MB/sec warmup 14 sec latency 8364.718 ms 1 1436 1.73 MB/sec warmup 15 sec latency 9364.868 ms 1 1436 1.63 MB/sec warmup 16 sec latency 10365.046 ms Failover mds1 to oleg215-server mount facets: mds1 1 1436 1.53 MB/sec warmup 17 sec latency 11365.154 ms 1 1436 1.45 MB/sec warmup 18 sec latency 12365.296 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1436 1.37 MB/sec warmup 19 sec latency 13365.459 ms oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 Started lustre-MDT0000 07:47:48 (1749124068) targets are mounted 07:47:48 (1749124068) facet_failover done 1 1436 0.00 MB/sec execute 1 sec latency 15365.758 ms 1 1436 0.00 MB/sec execute 2 sec latency 16365.985 ms 1 1436 0.00 MB/sec execute 3 sec latency 17366.145 ms 1 1436 0.00 MB/sec execute 4 sec latency 18366.280 ms oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1619 0.03 MB/sec execute 5 sec latency 18596.139 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1967 0.07 MB/sec execute 6 sec latency 18.407 ms 1 2325 0.26 MB/sec execute 7 sec latency 14.811 ms 1 2719 0.74 MB/sec execute 8 sec latency 16.723 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2892 1284796 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2676 1285012 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 31424 3567692 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 6508 3594072 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 37932 7161764 1% /mnt/lustre 1 3297 1.04 MB/sec execute 9 sec latency 18.036 ms 1 3729 1.29 MB/sec execute 10 sec latency 13.364 ms 1 3975 1.28 MB/sec execute 11 sec latency 18.271 ms 1 4245 1.19 MB/sec execute 12 sec latency 15.085 ms test_26 fail mds2 2 times 1 4493 1.14 MB/sec execute 13 sec latency 20.432 ms Failing mds2 on oleg215-server Stopping /mnt/lustre-mds2 (opts:) on oleg215-server 1 4767 1.15 MB/sec execute 14 sec latency 25.573 ms 07:48:03 (1749124083) shut down facet: mds2 facet_host: oleg215-server facet_failover_host: oleg215-server 1 4851 1.08 MB/sec execute 15 sec latency 660.653 ms 1 4851 1.02 MB/sec execute 16 sec latency 1660.811 ms 1 4851 0.96 MB/sec execute 17 sec latency 2660.970 ms 1 4851 0.90 MB/sec execute 18 sec latency 3661.138 ms 1 4851 0.85 MB/sec execute 19 sec latency 4661.280 ms 1 4851 0.81 MB/sec execute 20 sec latency 5661.420 ms 1 4851 0.77 MB/sec execute 21 sec latency 6661.592 ms 1 4851 0.74 MB/sec execute 22 sec latency 7661.773 ms 1 4851 0.71 MB/sec execute 23 sec latency 8661.913 ms 1 4851 0.68 MB/sec execute 24 sec latency 9662.083 ms Failover mds2 to oleg215-server mount facets: mds2 1 4851 0.65 MB/sec execute 25 sec latency 10662.210 ms 1 4851 0.62 MB/sec execute 26 sec latency 11662.381 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4851 0.60 MB/sec execute 27 sec latency 12662.555 ms oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 Started lustre-MDT0001 07:48:17 (1749124097) targets are mounted 07:48:17 (1749124097) facet_failover done 1 4851 0.58 MB/sec execute 28 sec latency 13662.661 ms 1 4851 0.56 MB/sec execute 29 sec latency 14662.791 ms 1 4851 0.54 MB/sec execute 30 sec latency 15662.983 ms 1 4851 0.52 MB/sec execute 31 sec latency 16663.422 ms 1 4851 0.51 MB/sec execute 32 sec latency 17663.554 ms 1 4851 0.49 MB/sec execute 33 sec latency 18663.655 ms 1 4851 0.48 MB/sec execute 34 sec latency 19663.774 ms oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 5127 0.55 MB/sec execute 35 sec latency 19793.687 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5348 0.54 MB/sec execute 36 sec latency 19.771 ms 1 5596 0.53 MB/sec execute 37 sec latency 36.138 ms 1 5916 0.55 MB/sec execute 38 sec latency 40.405 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2720 1284968 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3152 1284536 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39508 3557560 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 11416 3587460 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 50924 7145020 1% /mnt/lustre 1 6175 0.57 MB/sec execute 39 sec latency 18.964 ms 1 6752 0.68 MB/sec execute 40 sec latency 19.384 ms 1 7138 0.77 MB/sec execute 41 sec latency 18.661 ms 1 7388 0.78 MB/sec execute 42 sec latency 19.180 ms test_26 fail mds1 3 times 1 7596 0.77 MB/sec execute 43 sec latency 16.514 ms Failing mds1 on oleg215-server Stopping /mnt/lustre-mds1 (opts:) on oleg215-server 1 7799 0.76 MB/sec execute 44 sec latency 273.225 ms 07:48:33 (1749124113) shut down facet: mds1 facet_host: oleg215-server facet_failover_host: oleg215-server 1 7799 0.74 MB/sec execute 45 sec latency 1273.329 ms 1 7799 0.73 MB/sec execute 46 sec latency 2273.542 ms 1 7799 0.71 MB/sec execute 47 sec latency 3274.018 ms 1 7799 0.70 MB/sec execute 48 sec latency 4274.123 ms 1 7799 0.68 MB/sec execute 49 sec latency 5274.228 ms 1 7799 0.67 MB/sec execute 50 sec latency 6274.329 ms 1 7799 0.65 MB/sec execute 51 sec latency 7274.452 ms 1 7799 0.64 MB/sec execute 52 sec latency 8274.581 ms 1 7799 0.63 MB/sec execute 53 sec latency 9274.704 ms 1 7799 0.62 MB/sec execute 54 sec latency 10274.805 ms Failover mds1 to oleg215-server mount facets: mds1 1 7799 0.61 MB/sec execute 55 sec latency 11274.892 ms 1 7799 0.60 MB/sec execute 56 sec latency 12275.031 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7799 0.59 MB/sec execute 57 sec latency 13275.159 ms oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 1 7799 0.58 MB/sec execute 58 sec latency 14275.308 ms Started lustre-MDT0000 07:48:47 (1749124127) targets are mounted 07:48:47 (1749124127) facet_failover done 1 7799 0.57 MB/sec execute 59 sec latency 15275.479 ms 1 7799 0.56 MB/sec execute 60 sec latency 16275.629 ms 1 7799 0.55 MB/sec execute 61 sec latency 17275.753 ms 1 7807 0.54 MB/sec execute 62 sec latency 18216.826 ms oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8051 0.54 MB/sec execute 63 sec latency 19.680 ms 1 8343 0.55 MB/sec execute 64 sec latency 17.825 ms 1 8686 0.59 MB/sec execute 65 sec latency 21.628 ms 1 8938 0.58 MB/sec execute 66 sec latency 19.065 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2984 1284704 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 4612 1283076 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 44296 3548008 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 22744 3564332 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 67040 7112340 1% /mnt/lustre 1 9262 0.58 MB/sec execute 67 sec latency 19.772 ms 1 9509 0.59 MB/sec execute 68 sec latency 209.776 ms 1 9856 0.64 MB/sec execute 69 sec latency 423.428 ms 1 10397 0.68 MB/sec execute 70 sec latency 17.292 ms test_26 fail mds2 4 times Failing mds2 on oleg215-server 1 10785 0.72 MB/sec execute 71 sec latency 18.481 ms Stopping /mnt/lustre-mds2 (opts:) on oleg215-server 1 10887 0.72 MB/sec execute 72 sec latency 646.498 ms 07:49:01 (1749124141) shut down facet: mds2 facet_host: oleg215-server facet_failover_host: oleg215-server 1 10887 0.71 MB/sec execute 73 sec latency 1646.655 ms 1 10887 0.70 MB/sec execute 74 sec latency 2646.803 ms 1 10887 0.69 MB/sec execute 75 sec latency 3646.953 ms 1 10887 0.68 MB/sec execute 76 sec latency 4647.123 ms 1 10887 0.68 MB/sec execute 77 sec latency 5647.303 ms 1 10887 0.67 MB/sec execute 78 sec latency 6647.483 ms 1 10887 0.66 MB/sec execute 79 sec latency 7647.647 ms 1 10887 0.65 MB/sec execute 80 sec latency 8647.765 ms 1 10887 0.64 MB/sec execute 81 sec latency 9647.918 ms 1 10887 0.63 MB/sec execute 82 sec latency 10648.032 ms Failover mds2 to oleg215-server mount facets: mds2 1 10887 0.63 MB/sec execute 83 sec latency 11648.139 ms 1 10887 0.62 MB/sec execute 84 sec latency 12648.301 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 10887 0.61 MB/sec execute 85 sec latency 13648.395 ms oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 Started lustre-MDT0001 07:49:14 (1749124154) targets are mounted 07:49:14 (1749124154) facet_failover done 1 10887 0.60 MB/sec execute 86 sec latency 14648.575 ms 1 10887 0.60 MB/sec execute 87 sec latency 15648.722 ms 1 10887 0.59 MB/sec execute 88 sec latency 16648.897 ms 1 10887 0.58 MB/sec execute 89 sec latency 17649.085 ms 1 10887 0.58 MB/sec execute 90 sec latency 18649.215 ms 1 10970 0.57 MB/sec execute 91 sec latency 19209.083 ms oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 11166 0.57 MB/sec execute 92 sec latency 22.035 ms 1 11400 0.57 MB/sec execute 93 sec latency 22.153 ms 1 11641 0.57 MB/sec execute 94 sec latency 21.057 ms 1 11932 0.57 MB/sec execute 95 sec latency 17.046 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3724 1283964 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 5236 1282452 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 48700 3553744 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 28604 3570492 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 77304 7124236 2% /mnt/lustre 1 12264 0.60 MB/sec execute 96 sec latency 21.289 ms 1 12497 0.59 MB/sec execute 97 sec latency 21.230 ms 1 12813 0.59 MB/sec execute 98 sec latency 26.875 ms 1 13103 0.60 MB/sec execute 99 sec latency 17.191 ms test_26 fail mds1 5 times Failing mds1 on oleg215-server Stopping /mnt/lustre-mds1 (opts:) on oleg215-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 07:49:35 (1749124175) shut down facet: mds1 facet_host: oleg215-server facet_failover_host: oleg215-server 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 1 cleanup 114 sec 1 cleanup 115 sec 1 cleanup 116 sec Failover mds1 to oleg215-server mount facets: mds1 1 cleanup 117 sec 1 cleanup 118 sec Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 cleanup 119 sec oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 1 cleanup 120 sec Started lustre-MDT0000 07:49:49 (1749124189) targets are mounted 07:49:49 (1749124189) facet_failover done 1 cleanup 121 sec 1 cleanup 122 sec 1 cleanup 123 sec 1 cleanup 124 sec 0 cleanup 125 sec 0 cleanup 125 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 2099 36.689 19793.675 Close 1563 13.836 18596.126 Rename 87 14.653 20.408 Unlink 399 4.725 22.878 Qpathinfo 1947 2.654 22.129 Qfileinfo 349 0.464 3.045 Qfsinfo 328 0.911 5.323 Sfileinfo 166 8.690 14.153 Find 725 2.303 11.254 WriteX 1052 2.108 13.500 ReadX 3277 0.099 9.049 LockX 8 1.461 1.719 UnlockX 8 1.484 1.727 Flush 141 8.261 40.392 Throughput 0.600513 MB/sec 1 clients 1 procs max_latency=19793.687 ms stopping dbench on /mnt/lustre at Thu Jun 5 07:49:54 EDT 2025 with return code 0 oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench 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 Jun 5 07:49:55 EDT 2025 waiting for dbench pid 10787 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 1 200 7.84 MB/sec warmup 1 sec latency 28.295 ms 1 441 7.73 MB/sec warmup 2 sec latency 20.053 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3328 1284360 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 4680 1283008 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 58992 3544616 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 14444 3592096 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 73436 7136712 2% /mnt/lustre 1 718 7.10 MB/sec warmup 3 sec latency 37.487 ms 1 969 5.45 MB/sec warmup 4 sec latency 17.924 ms 1 1250 4.62 MB/sec warmup 5 sec latency 16.884 ms 1 1634 4.36 MB/sec warmup 6 sec latency 13.511 ms test_26 fail mds2 6 times Failing mds2 on oleg215-server 1 1932 3.78 MB/sec warmup 7 sec latency 18.750 ms Stopping /mnt/lustre-mds2 (opts:) on oleg215-server 07:50:03 (1749124203) shut down facet: mds2 facet_host: oleg215-server facet_failover_host: oleg215-server 1 2034 3.32 MB/sec warmup 8 sec latency 619.387 ms 1 2034 2.95 MB/sec warmup 9 sec latency 1619.575 ms 1 2034 2.66 MB/sec warmup 10 sec latency 2619.727 ms 1 2034 2.42 MB/sec warmup 11 sec latency 3619.883 ms 1 2034 2.21 MB/sec warmup 12 sec latency 4620.055 ms 1 2034 2.04 MB/sec warmup 13 sec latency 5620.201 ms 1 2034 1.90 MB/sec warmup 14 sec latency 6620.355 ms 1 2034 1.77 MB/sec warmup 15 sec latency 7620.542 ms 1 2034 1.66 MB/sec warmup 16 sec latency 8620.704 ms 1 2034 1.56 MB/sec warmup 17 sec latency 9620.881 ms Failover mds2 to oleg215-server mount facets: mds2 1 2034 1.48 MB/sec warmup 18 sec latency 10620.976 ms 1 2034 1.40 MB/sec warmup 19 sec latency 11621.094 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2034 0.00 MB/sec execute 1 sec latency 13621.365 ms oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 Started lustre-MDT0001 07:50:17 (1749124217) targets are mounted 07:50:17 (1749124217) facet_failover done 1 2034 0.00 MB/sec execute 2 sec latency 14621.564 ms 1 2034 0.00 MB/sec execute 3 sec latency 15621.717 ms 1 2034 0.00 MB/sec execute 4 sec latency 16621.870 ms 1 2034 0.00 MB/sec execute 5 sec latency 17622.095 ms 1 2034 0.00 MB/sec execute 6 sec latency 18623.170 ms 1 2034 0.00 MB/sec execute 7 sec latency 19623.370 ms 1 2034 0.00 MB/sec execute 8 sec latency 20624.234 ms oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 2168 0.02 MB/sec execute 9 sec latency 20909.940 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2426 0.15 MB/sec execute 10 sec latency 35.057 ms 1 2881 0.51 MB/sec execute 11 sec latency 20.804 ms 1 3198 0.64 MB/sec execute 12 sec latency 46.856 ms 1 3524 0.91 MB/sec execute 13 sec latency 29.870 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3180 1284508 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3392 1284296 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 31264 3564836 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 13128 3580624 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 44392 7145460 1% /mnt/lustre 1 3695 0.87 MB/sec execute 14 sec latency 54.418 ms 1 3836 0.88 MB/sec execute 15 sec latency 35.933 ms 1 3932 0.84 MB/sec execute 16 sec latency 40.487 ms 1 4021 0.79 MB/sec execute 17 sec latency 38.169 ms 1 4152 0.75 MB/sec execute 18 sec latency 32.133 ms test_26 fail mds1 7 times Failing mds1 on oleg215-server 1 4301 0.73 MB/sec execute 19 sec latency 49.261 ms Stopping /mnt/lustre-mds1 (opts:) on oleg215-server 1 4349 0.70 MB/sec execute 20 sec latency 666.907 ms 07:50:36 (1749124236) shut down facet: mds1 facet_host: oleg215-server facet_failover_host: oleg215-server 1 4349 0.66 MB/sec execute 21 sec latency 1667.096 ms 1 4349 0.63 MB/sec execute 22 sec latency 2668.189 ms 1 4349 0.60 MB/sec execute 23 sec latency 3668.354 ms 1 4349 0.58 MB/sec execute 24 sec latency 4668.532 ms 1 4349 0.56 MB/sec execute 25 sec latency 5668.719 ms 1 4349 0.53 MB/sec execute 26 sec latency 6668.887 ms 1 4349 0.51 MB/sec execute 27 sec latency 7669.050 ms 1 4349 0.50 MB/sec execute 28 sec latency 8669.218 ms 1 4349 0.48 MB/sec execute 29 sec latency 9669.391 ms 1 4349 0.46 MB/sec execute 30 sec latency 10669.554 ms Failover mds1 to oleg215-server mount facets: mds1 1 4349 0.45 MB/sec execute 31 sec latency 11669.747 ms 1 4349 0.43 MB/sec execute 32 sec latency 12670.249 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 4349 0.42 MB/sec execute 33 sec latency 13670.393 ms 1 4349 0.41 MB/sec execute 34 sec latency 14670.585 ms oleg215-server: oleg215-server.virtnet: executing set_default_debug -1 all pdsh@oleg215-client: oleg215-server: ssh exited with exit code 1 Started lustre-MDT0000 07:50:50 (1749124250) targets are mounted 07:50:50 (1749124250) facet_failover done 1 4349 0.40 MB/sec execute 35 sec latency 15670.766 ms 1 4349 0.39 MB/sec execute 36 sec latency 16670.935 ms 1 4349 0.38 MB/sec execute 37 sec latency 17671.098 ms 1 4349 0.37 MB/sec execute 38 sec latency 18671.257 ms oleg215-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 4488 0.37 MB/sec execute 39 sec latency 19068.851 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4760 0.39 MB/sec execute 40 sec latency 20.197 ms 1 5098 0.45 MB/sec execute 41 sec latency 27.412 ms 1 5358 0.45 MB/sec execute 42 sec latency 17.373 ms 1 5685 0.45 MB/sec execute 43 sec latency 23.781 ms 1 5997 0.47 MB/sec execute 44 sec latency 31.758 ms 1 6487 0.58 MB/sec execute 45 sec latency 18.690 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Jun 5 07:51:01 EDT 2025 with return code 0 10787 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 10787 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished