== replay-dual test 26: dbench and tar with mds failover ========================================================== 11:56:08 (1761321368) Starting client oleg150-client.virtnet: -o user_xattr,flock oleg150-server@tcp:/lustre /mnt/lustre Started clients oleg150-client.virtnet: 192.168.201.150@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,encrypt) Started tar loop with pid 45157 Started dbench loop with 45158 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 Fri Oct 24 11:56:10 EDT 2025 waiting for dbench pid 45194 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 2210688 3328 2205312 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 7168 3708928 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3730432 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 10240 7439360 1% /mnt/lustre 1 130 5.76 MB/sec warmup 1 sec latency 51.115 ms 1 247 4.70 MB/sec warmup 2 sec latency 53.912 ms 1 349 4.17 MB/sec warmup 3 sec latency 44.382 ms test_26 fail mds1 1 times 1 454 3.98 MB/sec warmup 4 sec latency 61.531 ms Failing mds1 on oleg150-server Stopping /mnt/lustre-mds1 (opts:) on oleg150-server 1 603 4.19 MB/sec warmup 5 sec latency 58.321 ms 1 660 3.52 MB/sec warmup 6 sec latency 657.059 ms reboot facets: mds1 1 660 3.02 MB/sec warmup 7 sec latency 1657.377 ms 1 660 2.64 MB/sec warmup 8 sec latency 2657.668 ms 1 660 2.35 MB/sec warmup 9 sec latency 3657.950 ms 1 660 2.11 MB/sec warmup 10 sec latency 4658.212 ms 1 660 1.92 MB/sec warmup 11 sec latency 5658.429 ms 1 660 1.76 MB/sec warmup 12 sec latency 6658.695 ms 1 660 1.63 MB/sec warmup 13 sec latency 7658.908 ms 1 660 1.51 MB/sec warmup 14 sec latency 8659.147 ms 1 660 1.41 MB/sec warmup 15 sec latency 9659.353 ms 1 660 1.32 MB/sec warmup 16 sec latency 10659.668 ms Failover mds1 to oleg150-server 1 660 1.24 MB/sec warmup 17 sec latency 11660.070 ms mount facets: mds1 1 660 1.17 MB/sec warmup 18 sec latency 12660.241 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 660 1.11 MB/sec warmup 19 sec latency 13660.452 ms 1 660 0.00 MB/sec execute 1 sec latency 15660.843 ms 1 660 0.00 MB/sec execute 2 sec latency 16661.161 ms oleg150-server: oleg150-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg150-client: oleg150-server: ssh exited with exit code 1 1 660 0.00 MB/sec execute 3 sec latency 17661.359 ms Started lustre-MDT0000 1 660 0.00 MB/sec execute 4 sec latency 18661.556 ms 1 660 0.00 MB/sec execute 5 sec latency 19662.567 ms 1 660 0.00 MB/sec execute 6 sec latency 20662.806 ms 1 660 0.00 MB/sec execute 7 sec latency 21664.975 ms 1 660 0.00 MB/sec execute 8 sec latency 22665.181 ms 1 660 0.00 MB/sec execute 9 sec latency 23665.354 ms 1 660 0.00 MB/sec execute 10 sec latency 24665.536 ms 1 660 0.00 MB/sec execute 11 sec latency 25665.785 ms 1 660 0.00 MB/sec execute 12 sec latency 26665.929 ms 1 660 0.00 MB/sec execute 13 sec latency 27666.427 ms 1 660 0.00 MB/sec execute 14 sec latency 28666.670 ms 1 660 0.00 MB/sec execute 15 sec latency 29666.951 ms 1 660 0.00 MB/sec execute 16 sec latency 30667.516 ms 1 662 0.00 MB/sec execute 17 sec latency 31582.394 ms 1 759 0.01 MB/sec execute 18 sec latency 73.590 ms oleg150-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 876 0.03 MB/sec execute 19 sec latency 73.999 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 990 0.04 MB/sec execute 20 sec latency 69.673 ms 1 1156 0.09 MB/sec execute 21 sec latency 49.559 ms 1 1403 0.22 MB/sec execute 22 sec latency 28.184 ms 1 1564 0.22 MB/sec execute 23 sec latency 76.742 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4096 2204416 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 41984 3663872 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 22528 3720192 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 64512 7384064 1% /mnt/lustre 1 1684 0.21 MB/sec execute 24 sec latency 60.698 ms 1 1868 0.21 MB/sec execute 25 sec latency 36.109 ms 1 2060 0.21 MB/sec execute 26 sec latency 33.975 ms 1 2297 0.24 MB/sec execute 27 sec latency 22.727 ms test_26 fail mds1 2 times Failing mds1 on oleg150-server 1 2429 0.25 MB/sec execute 28 sec latency 70.385 ms Stopping /mnt/lustre-mds1 (opts:) on oleg150-server 1 2571 0.27 MB/sec execute 29 sec latency 308.423 ms reboot facets: mds1 1 2571 0.26 MB/sec execute 30 sec latency 1308.676 ms 1 2571 0.25 MB/sec execute 31 sec latency 2308.950 ms 1 2571 0.24 MB/sec execute 32 sec latency 3309.502 ms 1 2571 0.24 MB/sec execute 33 sec latency 4309.717 ms 1 2571 0.23 MB/sec execute 34 sec latency 5309.947 ms 1 2571 0.22 MB/sec execute 35 sec latency 6310.150 ms 1 2571 0.22 MB/sec execute 36 sec latency 7310.360 ms 1 2571 0.21 MB/sec execute 37 sec latency 8310.675 ms 1 2571 0.21 MB/sec execute 38 sec latency 9312.109 ms 1 2571 0.20 MB/sec execute 39 sec latency 10312.407 ms 1 2571 0.19 MB/sec execute 40 sec latency 11312.557 ms Failover mds1 to oleg150-server mount facets: mds1 1 2571 0.19 MB/sec execute 41 sec latency 12312.724 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2571 0.19 MB/sec execute 42 sec latency 13313.029 ms 1 2571 0.18 MB/sec execute 43 sec latency 14313.501 ms 1 2571 0.18 MB/sec execute 44 sec latency 15313.762 ms 1 2571 0.17 MB/sec execute 45 sec latency 16314.083 ms 1 2571 0.17 MB/sec execute 46 sec latency 17314.308 ms oleg150-server: oleg150-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg150-client: oleg150-server: ssh exited with exit code 1 Started lustre-MDT0000 1 2571 0.17 MB/sec execute 47 sec latency 18314.504 ms 1 2571 0.16 MB/sec execute 48 sec latency 19314.694 ms 1 2571 0.16 MB/sec execute 49 sec latency 20314.897 ms 1 2571 0.16 MB/sec execute 50 sec latency 21315.182 ms 1 2571 0.15 MB/sec execute 51 sec latency 22315.359 ms 1 2571 0.15 MB/sec execute 52 sec latency 23315.567 ms 1 2571 0.15 MB/sec execute 53 sec latency 24316.269 ms 1 2571 0.14 MB/sec execute 54 sec latency 25316.456 ms 1 2571 0.14 MB/sec execute 55 sec latency 26316.637 ms 1 2571 0.14 MB/sec execute 56 sec latency 27316.833 ms 1 2571 0.14 MB/sec execute 57 sec latency 28317.149 ms 1 2571 0.13 MB/sec execute 58 sec latency 29317.405 ms 1 2571 0.13 MB/sec execute 59 sec latency 30317.959 ms 1 2763 0.18 MB/sec execute 60 sec latency 30664.074 ms 1 2957 0.20 MB/sec execute 61 sec latency 93.678 ms oleg150-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 3197 0.21 MB/sec execute 62 sec latency 99.339 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3360 0.23 MB/sec execute 63 sec latency 116.966 ms 1 3564 0.27 MB/sec execute 64 sec latency 35.968 ms 1 3696 0.27 MB/sec execute 65 sec latency 35.967 ms 1 3821 0.28 MB/sec execute 66 sec latency 47.440 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 4608 2203904 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 53248 3689472 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 25600 3715072 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 78848 7404544 2% /mnt/lustre 1 3944 0.28 MB/sec execute 67 sec latency 41.300 ms 1 4059 0.28 MB/sec execute 68 sec latency 38.878 ms 1 4218 0.28 MB/sec execute 69 sec latency 25.451 ms 1 4301 0.28 MB/sec execute 70 sec latency 119.652 ms test_26 fail mds1 3 times 1 4421 0.28 MB/sec execute 71 sec latency 59.343 ms Failing mds1 on oleg150-server Stopping /mnt/lustre-mds1 (opts:) on oleg150-server 1 4521 0.27 MB/sec execute 72 sec latency 77.877 ms 1 4521 0.27 MB/sec execute 73 sec latency 1054.593 ms 1 4521 0.27 MB/sec execute 74 sec latency 2054.846 ms 1 4521 0.26 MB/sec execute 75 sec latency 3055.088 ms 1 4521 0.26 MB/sec execute 76 sec latency 4055.433 ms 1 4521 0.26 MB/sec execute 77 sec latency 5055.745 ms 1 4521 0.25 MB/sec execute 78 sec latency 6055.974 ms 1 4521 0.25 MB/sec execute 79 sec latency 7056.760 ms reboot facets: mds1 1 4521 0.25 MB/sec execute 80 sec latency 8057.096 ms 1 4521 0.24 MB/sec execute 81 sec latency 9057.361 ms 1 4521 0.24 MB/sec execute 82 sec latency 10057.656 ms 1 4521 0.24 MB/sec execute 83 sec latency 11057.936 ms 1 4521 0.24 MB/sec execute 84 sec latency 12058.690 ms 1 4521 0.23 MB/sec execute 85 sec latency 13058.897 ms 1 4521 0.23 MB/sec execute 86 sec latency 14059.171 ms 1 4521 0.23 MB/sec execute 87 sec latency 15059.405 ms 1 4521 0.22 MB/sec execute 88 sec latency 16059.817 ms 1 4521 0.22 MB/sec execute 89 sec latency 17060.030 ms Failover mds1 to oleg150-server 1 4521 0.22 MB/sec execute 90 sec latency 18060.337 ms mount facets: mds1 1 4521 0.22 MB/sec execute 91 sec latency 19060.485 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 4521 0.21 MB/sec execute 92 sec latency 20060.776 ms 1 4521 0.21 MB/sec execute 93 sec latency 21061.011 ms 1 4521 0.21 MB/sec execute 94 sec latency 22061.312 ms 1 4521 0.21 MB/sec execute 95 sec latency 23061.539 ms oleg150-server: oleg150-server.virtnet: executing set_default_debug -1 all 8 1 4521 0.21 MB/sec execute 96 sec latency 24061.844 ms pdsh@oleg150-client: oleg150-server: ssh exited with exit code 1 Started lustre-MDT0000 1 4521 0.20 MB/sec execute 97 sec latency 25062.057 ms 1 4521 0.20 MB/sec execute 98 sec latency 26062.575 ms 1 4521 0.20 MB/sec execute 99 sec latency 27062.865 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 665 61.115 29418.440 Close 496 67.348 31582.376 Rename 29 23.547 41.192 Unlink 131 9.057 22.426 Qpathinfo 601 55.854 30664.054 Qfileinfo 104 0.752 3.637 Qfsinfo 113 0.696 11.425 Sfileinfo 63 11.556 25.957 Find 232 2.583 20.795 WriteX 341 3.643 17.034 ReadX 1018 0.781 49.541 LockX 2 4.136 4.471 UnlockX 2 5.129 5.714 Flush 65 45.654 119.636 Throughput 0.199663 MB/sec 1 clients 1 procs max_latency=31582.394 ms stopping dbench on /mnt/lustre at Fri Oct 24 11:58:13 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg150-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 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 24 11:58:16 EDT 2025 waiting for dbench pid 48305 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 1 129 5.76 MB/sec warmup 1 sec latency 51.711 ms 1 215 4.18 MB/sec warmup 2 sec latency 150.608 ms 1 326 3.91 MB/sec warmup 3 sec latency 49.095 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 5760 2202752 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 54272 3654656 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 35840 3648512 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 90112 7303168 2% /mnt/lustre 1 429 3.78 MB/sec warmup 4 sec latency 52.765 ms 1 535 3.74 MB/sec warmup 5 sec latency 71.340 ms 1 695 3.53 MB/sec warmup 6 sec latency 105.016 ms 1 796 3.07 MB/sec warmup 7 sec latency 63.886 ms test_26 fail mds1 4 times Failing mds1 on oleg150-server 1 910 2.72 MB/sec warmup 8 sec latency 64.225 ms Stopping /mnt/lustre-mds1 (opts:) on oleg150-server 1 980 2.43 MB/sec warmup 9 sec latency 319.237 ms 1 980 2.19 MB/sec warmup 10 sec latency 1319.718 ms reboot facets: mds1 1 980 1.99 MB/sec warmup 11 sec latency 2320.075 ms 1 980 1.82 MB/sec warmup 12 sec latency 3320.891 ms 1 980 1.68 MB/sec warmup 13 sec latency 4321.096 ms 1 980 1.56 MB/sec warmup 14 sec latency 5321.727 ms 1 980 1.46 MB/sec warmup 15 sec latency 6321.918 ms 1 980 1.37 MB/sec warmup 16 sec latency 7322.126 ms 1 980 1.29 MB/sec warmup 17 sec latency 8322.568 ms 1 980 1.22 MB/sec warmup 18 sec latency 9322.836 ms 1 980 1.15 MB/sec warmup 19 sec latency 10323.067 ms Failover mds1 to oleg150-server 1 980 0.00 MB/sec execute 1 sec latency 12325.512 ms mount facets: mds1 1 980 0.00 MB/sec execute 2 sec latency 13325.791 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 980 0.00 MB/sec execute 3 sec latency 14326.027 ms 1 980 0.00 MB/sec execute 4 sec latency 15326.230 ms 1 980 0.00 MB/sec execute 5 sec latency 16326.713 ms 1 980 0.00 MB/sec execute 6 sec latency 17326.881 ms oleg150-server: oleg150-server.virtnet: executing set_default_debug -1 all 8 1 980 0.00 MB/sec execute 7 sec latency 18327.502 ms pdsh@oleg150-client: oleg150-server: ssh exited with exit code 1 Started lustre-MDT0000 1 1009 0.05 MB/sec execute 8 sec latency 18872.340 ms 1 1163 0.12 MB/sec execute 9 sec latency 52.633 ms 1 1378 0.41 MB/sec execute 10 sec latency 40.681 ms oleg150-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1487 0.38 MB/sec execute 11 sec latency 91.558 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1634 0.36 MB/sec execute 12 sec latency 85.209 ms 1 1825 0.34 MB/sec execute 13 sec latency 39.559 ms 1 2002 0.33 MB/sec execute 14 sec latency 82.849 ms 1 2183 0.32 MB/sec execute 15 sec latency 34.042 ms 1 2376 0.38 MB/sec execute 16 sec latency 101.410 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 6272 2202240 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 29696 3699712 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 53248 3679232 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 82944 7378944 2% /mnt/lustre 1 2467 0.40 MB/sec execute 17 sec latency 98.688 ms 1 2612 0.39 MB/sec execute 18 sec latency 75.359 ms 1 2934 0.61 MB/sec execute 19 sec latency 109.136 ms test_26 fail mds1 5 times 1 3210 0.62 MB/sec execute 20 sec latency 84.261 ms Failing mds1 on oleg150-server Stopping /mnt/lustre-mds1 (opts:) on oleg150-server 1 3387 0.65 MB/sec execute 21 sec latency 42.550 ms 1 3506 0.75 MB/sec execute 22 sec latency 832.781 ms reboot facets: mds1 1 3506 0.71 MB/sec execute 23 sec latency 1833.056 ms 1 3506 0.69 MB/sec execute 24 sec latency 2833.706 ms 1 3506 0.66 MB/sec execute 25 sec latency 3833.946 ms 1 3506 0.63 MB/sec execute 26 sec latency 4834.495 ms 1 3506 0.61 MB/sec execute 27 sec latency 5834.700 ms 1 3506 0.59 MB/sec execute 28 sec latency 6834.933 ms 1 3506 0.57 MB/sec execute 29 sec latency 7835.752 ms 1 3506 0.55 MB/sec execute 30 sec latency 8836.011 ms 1 3506 0.53 MB/sec execute 31 sec latency 9836.178 ms 1 3506 0.51 MB/sec execute 32 sec latency 10836.491 ms Failover mds1 to oleg150-server 1 3506 0.50 MB/sec execute 33 sec latency 11836.765 ms mount facets: mds1 1 3506 0.48 MB/sec execute 34 sec latency 12836.892 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 3506 0.47 MB/sec execute 35 sec latency 13837.149 ms 1 3506 0.46 MB/sec execute 36 sec latency 14839.300 ms 1 3506 0.44 MB/sec execute 37 sec latency 15839.819 ms 1 3506 0.43 MB/sec execute 38 sec latency 16840.054 ms 1 3506 0.42 MB/sec execute 39 sec latency 17841.362 ms 1 3506 0.41 MB/sec execute 40 sec latency 18841.685 ms oleg150-server: oleg150-server.virtnet: executing set_default_debug -1 all 8 1 3506 0.40 MB/sec execute 41 sec latency 19841.963 ms pdsh@oleg150-client: oleg150-server: ssh exited with exit code 1 Started lustre-MDT0000 1 3506 0.39 MB/sec execute 42 sec latency 20842.204 ms 1 3506 0.38 MB/sec execute 43 sec latency 21842.398 ms 1 3506 0.37 MB/sec execute 44 sec latency 22842.641 ms 1 3506 0.37 MB/sec execute 45 sec latency 23842.858 ms 1 3506 0.36 MB/sec execute 46 sec latency 24843.138 ms 1 3506 0.35 MB/sec execute 47 sec latency 25843.340 ms 1 3506 0.34 MB/sec execute 48 sec latency 26843.553 ms 1 3506 0.34 MB/sec execute 49 sec latency 27843.771 ms 1 3506 0.33 MB/sec execute 50 sec latency 28843.923 ms 1 3555 0.32 MB/sec execute 51 sec latency 29384.858 ms 1 3724 0.32 MB/sec execute 52 sec latency 29.208 ms oleg150-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 3868 0.34 MB/sec execute 53 sec latency 36.482 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 4009 0.34 MB/sec execute 54 sec latency 33.669 ms 1 4168 0.33 MB/sec execute 55 sec latency 26.811 ms 1 4283 0.33 MB/sec execute 56 sec latency 263.404 ms 1 4421 0.33 MB/sec execute 57 sec latency 80.922 ms 1 4549 0.33 MB/sec execute 58 sec latency 68.598 ms 1 4730 0.34 MB/sec execute 59 sec latency 93.716 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Fri Oct 24 11:59:36 EDT 2025 with return code 0 48305 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 48305 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished