== replay-dual test 26: dbench and tar with mds failover ========================================================== 10:25:06 (1781619906) Starting client oleg241-client.virtnet: -o user_xattr,flock 192.168.202.141@tcp:/lustre /mnt/lustre Started clients oleg241-client.virtnet: 192.168.202.141@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 65579 Started dbench loop with 65580 striped dir -i0 -c2 -H all_char /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' UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1964 1269340 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17928 3580768 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7186224 1% /mnt/lustre running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Tue Jun 16 10:25:10 EDT 2026 waiting for dbench pid 65637 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 30 1.05 MB/sec warmup 1 sec latency 22.600 ms 1 111 2.62 MB/sec warmup 2 sec latency 69.390 ms 1 155 2.18 MB/sec warmup 3 sec latency 123.661 ms 1 188 1.89 MB/sec warmup 4 sec latency 418.217 ms 1 232 1.78 MB/sec warmup 5 sec latency 99.862 ms 1 283 1.75 MB/sec warmup 6 sec latency 104.641 ms 1 332 1.71 MB/sec warmup 7 sec latency 84.582 ms test_26 fail mds1 1 times 1 377 1.67 MB/sec warmup 8 sec latency 108.985 ms 1 421 1.65 MB/sec warmup 9 sec latency 108.742 ms Failing mds1 on oleg241-server 1 470 1.64 MB/sec warmup 10 sec latency 99.073 ms Stopping /mnt/lustre-mds1 (opts:) on oleg241-server 1 521 1.64 MB/sec warmup 11 sec latency 122.071 ms 1 521 1.50 MB/sec warmup 12 sec latency 1027.604 ms 10:25:23 (1781619923) shut down facet: mds1 facet_host: oleg241-server facet_failover_host: oleg241-server 1 521 1.39 MB/sec warmup 13 sec latency 2028.700 ms 1 521 1.29 MB/sec warmup 14 sec latency 3030.343 ms 1 521 1.20 MB/sec warmup 15 sec latency 4031.737 ms 1 521 1.13 MB/sec warmup 16 sec latency 5032.105 ms 1 521 1.06 MB/sec warmup 17 sec latency 6033.020 ms 1 521 1.00 MB/sec warmup 18 sec latency 7033.878 ms 1 521 0.95 MB/sec warmup 19 sec latency 8034.094 ms 1 521 0.00 MB/sec execute 1 sec latency 10034.532 ms 1 521 0.00 MB/sec execute 2 sec latency 11041.394 ms 1 521 0.00 MB/sec execute 3 sec latency 12041.575 ms Failover mds1 to oleg241-server mount facets: mds1 1 521 0.00 MB/sec execute 4 sec latency 13041.835 ms 1 521 0.00 MB/sec execute 5 sec latency 14042.228 ms 1 521 0.00 MB/sec execute 6 sec latency 15042.463 ms 1 521 0.00 MB/sec execute 7 sec latency 16042.862 ms 1 521 0.00 MB/sec execute 8 sec latency 17045.860 ms 1 521 0.00 MB/sec execute 9 sec latency 18046.031 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 521 0.00 MB/sec execute 10 sec latency 19046.207 ms 1 521 0.00 MB/sec execute 11 sec latency 20046.401 ms 1 521 0.00 MB/sec execute 12 sec latency 21048.788 ms 1 521 0.00 MB/sec execute 13 sec latency 22049.754 ms oleg241-server: oleg241-server.virtnet: executing set_default_debug -1 all 1 521 0.00 MB/sec execute 14 sec latency 23049.906 ms pdsh@oleg241-client: oleg241-server: ssh exited with exit code 1 1 521 0.00 MB/sec execute 15 sec latency 24050.101 ms Started lustre-MDT0000 10:25:46 (1781619946) targets are mounted 10:25:46 (1781619946) facet_failover done 1 521 0.00 MB/sec execute 16 sec latency 25050.388 ms 1 521 0.00 MB/sec execute 17 sec latency 26051.038 ms 1 521 0.00 MB/sec execute 18 sec latency 27054.117 ms 1 603 0.15 MB/sec execute 19 sec latency 27174.446 ms 1 677 0.16 MB/sec execute 20 sec latency 74.608 ms 1 721 0.15 MB/sec execute 21 sec latency 90.830 ms oleg241-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 767 0.15 MB/sec execute 22 sec latency 101.184 ms 1 803 0.15 MB/sec execute 23 sec latency 127.375 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 865 0.15 MB/sec execute 24 sec latency 101.872 ms 1 884 0.14 MB/sec execute 25 sec latency 427.381 ms 1 903 0.14 MB/sec execute 26 sec latency 854.028 ms 1 952 0.14 MB/sec execute 27 sec latency 103.422 ms 1 1036 0.17 MB/sec execute 28 sec latency 63.302 ms 1 1131 0.17 MB/sec execute 29 sec latency 46.869 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2204 1269100 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2000 1269304 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 19200 3579288 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 37000 3569572 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 56200 7148860 1% /mnt/lustre 1 1190 0.17 MB/sec execute 30 sec latency 110.528 ms 1 1231 0.16 MB/sec execute 31 sec latency 88.975 ms 1 1277 0.16 MB/sec execute 32 sec latency 125.036 ms 1 1421 0.24 MB/sec execute 33 sec latency 75.917 ms 1 1467 0.23 MB/sec execute 34 sec latency 305.645 ms 1 1489 0.23 MB/sec execute 35 sec latency 523.429 ms 1 1538 0.22 MB/sec execute 36 sec latency 88.765 ms 1 1625 0.22 MB/sec execute 37 sec latency 65.226 ms test_26 fail mds2 2 times 1 1691 0.21 MB/sec execute 38 sec latency 76.279 ms 1 1770 0.21 MB/sec execute 39 sec latency 83.852 ms Failing mds2 on oleg241-server Stopping /mnt/lustre-mds2 (opts:) on oleg241-server 1 1830 0.21 MB/sec execute 40 sec latency 98.648 ms 1 1886 0.20 MB/sec execute 41 sec latency 161.999 ms 1 1886 0.20 MB/sec execute 42 sec latency 1162.854 ms 1 1886 0.19 MB/sec execute 43 sec latency 2164.143 ms 1 1886 0.19 MB/sec execute 44 sec latency 3164.338 ms 1 1886 0.18 MB/sec execute 45 sec latency 4164.611 ms 1 1886 0.18 MB/sec execute 46 sec latency 5164.965 ms 1 1886 0.18 MB/sec execute 47 sec latency 6166.452 ms 1 1886 0.17 MB/sec execute 48 sec latency 7168.242 ms 10:26:19 (1781619979) shut down facet: mds2 facet_host: oleg241-server facet_failover_host: oleg241-server 1 1886 0.17 MB/sec execute 49 sec latency 8168.449 ms 1 1886 0.17 MB/sec execute 50 sec latency 9174.641 ms 1 1886 0.16 MB/sec execute 51 sec latency 10174.910 ms 1 1886 0.16 MB/sec execute 52 sec latency 11176.056 ms 1 1886 0.16 MB/sec execute 53 sec latency 12176.273 ms 1 1886 0.15 MB/sec execute 54 sec latency 13176.472 ms 1 1886 0.15 MB/sec execute 55 sec latency 14176.776 ms 1 1886 0.15 MB/sec execute 56 sec latency 15176.998 ms 1 1886 0.15 MB/sec execute 57 sec latency 16177.273 ms 1 1886 0.14 MB/sec execute 58 sec latency 17177.488 ms Failover mds2 to oleg241-server mount facets: mds2 1 1886 0.14 MB/sec execute 59 sec latency 18177.841 ms 1 1886 0.14 MB/sec execute 60 sec latency 19178.147 ms 1 1886 0.14 MB/sec execute 61 sec latency 20178.620 ms 1 1886 0.13 MB/sec execute 62 sec latency 21178.992 ms 1 1886 0.13 MB/sec execute 63 sec latency 22179.205 ms 1 1886 0.13 MB/sec execute 64 sec latency 23181.406 ms 1 1886 0.13 MB/sec execute 65 sec latency 24181.851 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 1886 0.13 MB/sec execute 66 sec latency 25182.063 ms 1 1886 0.12 MB/sec execute 67 sec latency 26182.286 ms 1 1886 0.12 MB/sec execute 68 sec latency 27183.533 ms 1 1886 0.12 MB/sec execute 69 sec latency 28184.683 ms 1 1886 0.12 MB/sec execute 70 sec latency 29185.720 ms oleg241-server: oleg241-server.virtnet: executing set_default_debug -1 all 1 1886 0.12 MB/sec execute 71 sec latency 30186.465 ms pdsh@oleg241-client: oleg241-server: ssh exited with exit code 1 Started lustre-MDT0001 10:26:43 (1781620003) targets are mounted 1 1886 0.12 MB/sec execute 72 sec latency 31187.863 ms 10:26:43 (1781620003) facet_failover done 1 1886 0.11 MB/sec execute 73 sec latency 32188.076 ms 1 1942 0.11 MB/sec execute 74 sec latency 32556.829 ms 1 2004 0.11 MB/sec execute 75 sec latency 125.500 ms 1 2046 0.11 MB/sec execute 76 sec latency 105.090 ms 1 2103 0.11 MB/sec execute 77 sec latency 95.903 ms oleg241-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 2160 0.11 MB/sec execute 78 sec latency 100.377 ms 1 2200 0.11 MB/sec execute 79 sec latency 167.850 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2291 0.12 MB/sec execute 80 sec latency 94.287 ms 1 2359 0.12 MB/sec execute 81 sec latency 83.608 ms 1 2401 0.12 MB/sec execute 82 sec latency 108.391 ms 1 2445 0.12 MB/sec execute 83 sec latency 83.831 ms 1 2503 0.13 MB/sec execute 84 sec latency 76.871 ms 1 2584 0.13 MB/sec execute 85 sec latency 87.477 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2452 1268852 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2296 1269008 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 23280 3582808 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46252 3560396 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 69532 7143204 1% /mnt/lustre 1 2716 0.16 MB/sec execute 86 sec latency 108.833 ms 1 2784 0.16 MB/sec execute 87 sec latency 92.386 ms 1 2932 0.18 MB/sec execute 88 sec latency 68.995 ms 1 3000 0.17 MB/sec execute 89 sec latency 197.192 ms 1 3000 0.17 MB/sec execute 90 sec latency 1197.472 ms 1 3169 0.18 MB/sec execute 91 sec latency 1509.463 ms 1 3273 0.19 MB/sec execute 92 sec latency 79.395 ms 1 3359 0.19 MB/sec execute 93 sec latency 53.326 ms test_26 fail mds1 3 times 1 3491 0.22 MB/sec execute 94 sec latency 106.672 ms Failing mds1 on oleg241-server 1 3541 0.21 MB/sec execute 95 sec latency 94.613 ms Stopping /mnt/lustre-mds1 (opts:) on oleg241-server 1 3591 0.21 MB/sec execute 96 sec latency 77.518 ms 1 3637 0.21 MB/sec execute 97 sec latency 366.329 ms 1 3637 0.21 MB/sec execute 98 sec latency 1366.572 ms 10:27:09 (1781620029) shut down facet: mds1 facet_host: oleg241-server facet_failover_host: oleg241-server 1 3637 0.21 MB/sec execute 99 sec latency 2366.910 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 Failover mds1 to oleg241-server mount facets: mds1 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 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 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 oleg241-server: oleg241-server.virtnet: executing set_default_debug -1 all 1 cleanup 128 sec pdsh@oleg241-client: oleg241-server: ssh exited with exit code 1 1 cleanup 129 sec Started lustre-MDT0000 10:27:40 (1781620060) targets are mounted 10:27:40 (1781620060) facet_failover done 1 cleanup 130 sec 1 cleanup 131 sec 1 cleanup 132 sec 1 cleanup 133 sec 0 cleanup 134 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 458 42.036 264.232 Close 384 167.513 33416.146 Rename 23 67.838 125.012 Unlink 57 21.279 53.819 Qpathinfo 451 14.071 110.364 Qfileinfo 109 1.974 15.706 Qfsinfo 88 2.809 30.362 Sfileinfo 50 46.236 101.168 Find 189 8.859 34.200 WriteX 333 10.819 134.961 ReadX 928 0.771 62.388 LockX 2 13.830 22.034 UnlockX 2 7.731 8.067 Flush 43 846.965 32556.813 Throughput 0.207577 MB/sec 1 clients 1 procs max_latency=32556.829 ms stopping dbench on /mnt/lustre at Tue Jun 16 10:27:44 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg241-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench 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 Tue Jun 16 10:27:51 EDT 2026 waiting for dbench pid 68834 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 2.09 MB/sec warmup 1 sec latency 66.305 ms 1 137 3.01 MB/sec warmup 2 sec latency 98.937 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2916 1268388 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2732 1268572 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39324 3564096 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 12684 3593212 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 52008 7157308 1% /mnt/lustre 1 184 2.46 MB/sec warmup 3 sec latency 91.804 ms 1 231 2.22 MB/sec warmup 4 sec latency 261.591 ms 1 288 2.14 MB/sec warmup 5 sec latency 90.778 ms 1 331 2.00 MB/sec warmup 6 sec latency 125.397 ms 1 390 1.97 MB/sec warmup 7 sec latency 89.167 ms 1 437 1.92 MB/sec warmup 8 sec latency 121.864 ms 1 490 1.89 MB/sec warmup 9 sec latency 103.395 ms 1 595 2.06 MB/sec warmup 10 sec latency 61.441 ms test_26 fail mds2 4 times 1 664 1.92 MB/sec warmup 11 sec latency 85.473 ms Failing mds2 on oleg241-server 1 708 1.76 MB/sec warmup 12 sec latency 98.804 ms Stopping /mnt/lustre-mds2 (opts:) on oleg241-server 1 759 1.64 MB/sec warmup 13 sec latency 100.792 ms 1 808 1.53 MB/sec warmup 14 sec latency 106.318 ms 1 882 1.44 MB/sec warmup 15 sec latency 78.910 ms 10:28:06 (1781620086) shut down facet: mds2 facet_host: oleg241-server facet_failover_host: oleg241-server 1 902 1.35 MB/sec warmup 16 sec latency 558.050 ms 1 977 1.29 MB/sec warmup 17 sec latency 62.151 ms 1 995 1.22 MB/sec warmup 18 sec latency 700.172 ms 1 995 1.15 MB/sec warmup 19 sec latency 1700.809 ms 1 995 0.00 MB/sec execute 1 sec latency 3701.405 ms 1 995 0.00 MB/sec execute 2 sec latency 4701.822 ms 1 995 0.00 MB/sec execute 3 sec latency 5702.181 ms 1 995 0.00 MB/sec execute 4 sec latency 6703.621 ms 1 995 0.00 MB/sec execute 5 sec latency 7705.212 ms Failover mds2 to oleg241-server mount facets: mds2 1 995 0.00 MB/sec execute 6 sec latency 8706.168 ms 1 995 0.00 MB/sec execute 7 sec latency 9706.441 ms 1 995 0.00 MB/sec execute 8 sec latency 10706.652 ms 1 995 0.00 MB/sec execute 9 sec latency 11709.432 ms 1 995 0.00 MB/sec execute 10 sec latency 12709.638 ms 1 995 0.00 MB/sec execute 11 sec latency 13710.857 ms 1 995 0.00 MB/sec execute 12 sec latency 14711.084 ms 1 995 0.00 MB/sec execute 13 sec latency 15713.305 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 995 0.00 MB/sec execute 14 sec latency 16714.624 ms 1 995 0.00 MB/sec execute 15 sec latency 17714.828 ms 1 995 0.00 MB/sec execute 16 sec latency 18715.177 ms 1 995 0.00 MB/sec execute 17 sec latency 19715.516 ms oleg241-server: oleg241-server.virtnet: executing set_default_debug -1 all 1 995 0.00 MB/sec execute 18 sec latency 20715.779 ms pdsh@oleg241-client: oleg241-server: ssh exited with exit code 1 1 995 0.00 MB/sec execute 19 sec latency 21715.961 ms Started lustre-MDT0001 10:28:30 (1781620110) targets are mounted 10:28:30 (1781620110) facet_failover done 1 995 0.00 MB/sec execute 20 sec latency 22716.169 ms 1 1011 0.02 MB/sec execute 21 sec latency 23321.612 ms 1 1099 0.05 MB/sec execute 22 sec latency 136.768 ms 1 1172 0.05 MB/sec execute 23 sec latency 72.379 ms oleg241-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 1233 0.05 MB/sec execute 24 sec latency 61.896 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1285 0.05 MB/sec execute 25 sec latency 87.510 ms 1 1426 0.16 MB/sec execute 26 sec latency 80.790 ms 1 1492 0.15 MB/sec execute 27 sec latency 217.422 ms 1 1564 0.15 MB/sec execute 28 sec latency 67.048 ms 1 1637 0.15 MB/sec execute 29 sec latency 76.780 ms 1 1692 0.14 MB/sec execute 30 sec latency 139.935 ms 1 1785 0.14 MB/sec execute 31 sec latency 69.520 ms 1 1861 0.14 MB/sec execute 32 sec latency 64.560 ms 1 1965 0.14 MB/sec execute 33 sec latency 63.701 ms 1 2020 0.14 MB/sec execute 34 sec latency 77.459 ms 1 2108 0.14 MB/sec execute 35 sec latency 64.512 ms 1 2173 0.13 MB/sec execute 36 sec latency 80.310 ms 1 2251 0.13 MB/sec execute 37 sec latency 98.222 ms 1 2348 0.16 MB/sec execute 38 sec latency 67.716 ms 1 2410 0.16 MB/sec execute 39 sec latency 62.828 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Tue Jun 16 10:28:51 EDT 2026 with return code 0 68834 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 68834 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished