== replay-dual test 26: dbench and tar with mds failover ========================================================== 10:11:36 (1784124696) Starting client oleg135-client.virtnet: -o user_xattr,flock 192.168.201.135@tcp:/lustre /mnt/lustre Started clients oleg135-client.virtnet: 192.168.201.135@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 65458 Started dbench loop with 65459 striped dir -i0 -c2 -H crush2 /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 Wed Jul 15 10:11:39 EDT 2026 waiting for dbench pid 65501 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 1 of 1 processes prepared for launch 0 sec releasing clients UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1996 1269308 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1784 1269520 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1592 3605400 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 5644 3579640 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 7236 7185040 1% /mnt/lustre 1 68 3.01 MB/sec warmup 1 sec latency 65.956 ms 1 151 3.17 MB/sec warmup 2 sec latency 94.292 ms 1 207 2.70 MB/sec warmup 3 sec latency 183.501 ms 1 287 2.68 MB/sec warmup 4 sec latency 73.124 ms 1 357 2.56 MB/sec warmup 5 sec latency 74.746 ms 1 437 2.56 MB/sec warmup 6 sec latency 90.119 ms test_26 fail mds1 1 times 1 511 2.53 MB/sec warmup 7 sec latency 88.181 ms Failing mds1 on oleg135-server 1 642 2.63 MB/sec warmup 8 sec latency 78.647 ms Stopping /mnt/lustre-mds1 (opts:) on oleg135-server 1 700 2.35 MB/sec warmup 9 sec latency 273.661 ms 10:11:49 (1784124709) shut down 1 700 2.12 MB/sec warmup 10 sec latency 1274.402 ms facet: mds1 facet_host: oleg135-server facet_failover_host: oleg135-server 1 700 1.93 MB/sec warmup 11 sec latency 2274.535 ms 1 700 1.77 MB/sec warmup 12 sec latency 3274.958 ms 1 700 1.63 MB/sec warmup 13 sec latency 4275.464 ms 1 700 1.51 MB/sec warmup 14 sec latency 5276.996 ms 1 700 1.41 MB/sec warmup 15 sec latency 6277.748 ms 1 700 1.32 MB/sec warmup 16 sec latency 7277.959 ms 1 700 1.25 MB/sec warmup 17 sec latency 8281.439 ms 1 700 1.18 MB/sec warmup 18 sec latency 9282.705 ms 1 700 1.12 MB/sec warmup 19 sec latency 10282.892 ms Failover mds1 to oleg135-server mount facets: mds1 1 700 0.00 MB/sec execute 1 sec latency 12283.328 ms 1 700 0.00 MB/sec execute 2 sec latency 13283.537 ms 1 700 0.00 MB/sec execute 3 sec latency 14283.679 ms 1 700 0.00 MB/sec execute 4 sec latency 15285.169 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 700 0.00 MB/sec execute 5 sec latency 16285.346 ms 1 700 0.00 MB/sec execute 6 sec latency 17285.557 ms 1 700 0.00 MB/sec execute 7 sec latency 18285.734 ms oleg135-server: oleg135-server.virtnet: executing set_default_debug -1 all pdsh@oleg135-client: oleg135-server: ssh exited with exit code 1 1 700 0.00 MB/sec execute 8 sec latency 19285.941 ms Started lustre-MDT0000 10:12:07 (1784124727) targets are mounted 10:12:07 (1784124727) facet_failover done 1 700 0.00 MB/sec execute 9 sec latency 20286.172 ms 1 700 0.00 MB/sec execute 10 sec latency 21286.329 ms 1 700 0.00 MB/sec execute 11 sec latency 22286.624 ms 1 733 0.01 MB/sec execute 12 sec latency 22749.328 ms 1 781 0.01 MB/sec execute 13 sec latency 92.531 ms 1 848 0.03 MB/sec execute 14 sec latency 99.974 ms oleg135-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 884 0.03 MB/sec execute 15 sec latency 99.137 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 884 0.03 MB/sec execute 16 sec latency 1100.160 ms 1 918 0.03 MB/sec execute 17 sec latency 1132.822 ms 1 969 0.03 MB/sec execute 18 sec latency 84.718 ms 1 1023 0.08 MB/sec execute 19 sec latency 102.028 ms 1 1099 0.09 MB/sec execute 20 sec latency 146.237 ms 1 1132 0.08 MB/sec execute 21 sec latency 359.332 ms 1 1172 0.08 MB/sec execute 22 sec latency 130.850 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2208 1269096 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2012 1269292 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20144 3586428 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 38808 3568072 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 58952 7154500 1% /mnt/lustre 1 1192 0.08 MB/sec execute 23 sec latency 188.392 ms 1 1221 0.08 MB/sec execute 24 sec latency 462.206 ms 1 1251 0.08 MB/sec execute 25 sec latency 134.958 ms 1 1378 0.18 MB/sec execute 26 sec latency 98.784 ms 1 1404 0.18 MB/sec execute 27 sec latency 108.015 ms 1 1425 0.17 MB/sec execute 28 sec latency 168.444 ms 1 1453 0.17 MB/sec execute 29 sec latency 158.329 ms 1 1470 0.16 MB/sec execute 30 sec latency 469.308 ms 1 1505 0.16 MB/sec execute 31 sec latency 161.823 ms 1 1565 0.15 MB/sec execute 32 sec latency 77.992 ms 1 1634 0.15 MB/sec execute 33 sec latency 58.289 ms test_26 fail mds2 2 times 1 1662 0.15 MB/sec execute 34 sec latency 147.407 ms Failing mds2 on oleg135-server 1 1692 0.14 MB/sec execute 35 sec latency 144.284 ms Stopping /mnt/lustre-mds2 (opts:) on oleg135-server 1 1752 0.14 MB/sec execute 36 sec latency 141.977 ms 1 1789 0.14 MB/sec execute 37 sec latency 184.632 ms 1 1814 0.13 MB/sec execute 38 sec latency 373.192 ms 1 1849 0.13 MB/sec execute 39 sec latency 390.721 ms 1 1901 0.13 MB/sec execute 40 sec latency 257.363 ms 1 1965 0.13 MB/sec execute 41 sec latency 101.034 ms 1 2000 0.13 MB/sec execute 42 sec latency 224.315 ms 1 2020 0.12 MB/sec execute 43 sec latency 152.186 ms 1 2055 0.12 MB/sec execute 44 sec latency 206.280 ms 1 2102 0.12 MB/sec execute 45 sec latency 231.675 ms 10:12:45 (1784124765) shut down facet: mds2 facet_host: oleg135-server facet_failover_host: oleg135-server 1 2150 0.12 MB/sec execute 46 sec latency 109.087 ms 1 2210 0.12 MB/sec execute 47 sec latency 72.491 ms 1 2259 0.12 MB/sec execute 48 sec latency 700.056 ms 1 2259 0.11 MB/sec execute 49 sec latency 1700.441 ms 1 2259 0.11 MB/sec execute 50 sec latency 2700.706 ms 1 2259 0.11 MB/sec execute 51 sec latency 3713.319 ms 1 2259 0.11 MB/sec execute 52 sec latency 4713.531 ms 1 2259 0.10 MB/sec execute 53 sec latency 5713.735 ms 1 2259 0.10 MB/sec execute 54 sec latency 6714.608 ms 1 2259 0.10 MB/sec execute 55 sec latency 7715.149 ms Failover mds2 to oleg135-server 1 2259 0.10 MB/sec execute 56 sec latency 8716.748 ms mount facets: mds2 1 2259 0.10 MB/sec execute 57 sec latency 9717.121 ms 1 2259 0.10 MB/sec execute 58 sec latency 10718.457 ms 1 2259 0.09 MB/sec execute 59 sec latency 11718.954 ms 1 2259 0.09 MB/sec execute 60 sec latency 12719.184 ms 1 2259 0.09 MB/sec execute 61 sec latency 13719.404 ms 1 2259 0.09 MB/sec execute 62 sec latency 14719.547 ms 1 2259 0.09 MB/sec execute 63 sec latency 15726.816 ms 1 2259 0.09 MB/sec execute 64 sec latency 16728.073 ms 1 2259 0.09 MB/sec execute 65 sec latency 17728.726 ms 1 2259 0.08 MB/sec execute 66 sec latency 18732.119 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.08 MB/sec execute 67 sec latency 19732.278 ms 1 2259 0.08 MB/sec execute 68 sec latency 20733.482 ms 1 2259 0.08 MB/sec execute 69 sec latency 21738.388 ms 1 2259 0.08 MB/sec execute 70 sec latency 22742.339 ms 1 2259 0.08 MB/sec execute 71 sec latency 23742.741 ms 1 2259 0.08 MB/sec execute 72 sec latency 24742.947 ms 1 2259 0.08 MB/sec execute 73 sec latency 25743.848 ms oleg135-server: oleg135-server.virtnet: executing set_default_debug -1 all 1 2259 0.08 MB/sec execute 74 sec latency 26744.082 ms pdsh@oleg135-client: oleg135-server: ssh exited with exit code 1 1 2259 0.07 MB/sec execute 75 sec latency 27745.685 ms Started lustre-MDT0001 10:13:15 (1784124795) targets are mounted 10:13:15 (1784124795) facet_failover done 1 2356 0.09 MB/sec execute 76 sec latency 27833.659 ms 1 2416 0.09 MB/sec execute 77 sec latency 86.503 ms 1 2473 0.09 MB/sec execute 78 sec latency 93.626 ms 1 2566 0.10 MB/sec execute 79 sec latency 94.285 ms 1 2602 0.10 MB/sec execute 80 sec latency 111.544 ms oleg135-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 2768 0.13 MB/sec execute 81 sec latency 118.581 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2903 0.14 MB/sec execute 82 sec latency 63.892 ms 1 2987 0.15 MB/sec execute 83 sec latency 78.924 ms 1 3197 0.16 MB/sec execute 84 sec latency 55.988 ms 1 3324 0.17 MB/sec execute 85 sec latency 68.253 ms 1 3410 0.17 MB/sec execute 86 sec latency 68.736 ms 1 3566 0.20 MB/sec execute 87 sec latency 74.396 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2492 1268812 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2392 1268912 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 31004 3573448 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 39484 3565912 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 70488 7139360 1% /mnt/lustre 1 3641 0.20 MB/sec execute 88 sec latency 92.824 ms 1 3708 0.20 MB/sec execute 89 sec latency 59.101 ms 1 3792 0.21 MB/sec execute 90 sec latency 76.078 ms 1 3856 0.20 MB/sec execute 91 sec latency 69.072 ms 1 3915 0.20 MB/sec execute 92 sec latency 89.927 ms 1 3967 0.20 MB/sec execute 93 sec latency 92.327 ms 1 4055 0.20 MB/sec execute 94 sec latency 50.189 ms test_26 fail mds1 3 times 1 4129 0.20 MB/sec execute 95 sec latency 55.460 ms Failing mds1 on oleg135-server Stopping /mnt/lustre-mds1 (opts:) on oleg135-server 1 4220 0.20 MB/sec execute 96 sec latency 59.856 ms 1 4246 0.20 MB/sec execute 97 sec latency 646.903 ms 1 4246 0.19 MB/sec execute 98 sec latency 1647.127 ms 1 4246 0.19 MB/sec execute 99 sec latency 2647.331 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 10:13:42 (1784124822) shut down facet: mds1 facet_host: oleg135-server facet_failover_host: oleg135-server 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 oleg135-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 /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 cleanup 118 sec 1 cleanup 119 sec 1 cleanup 120 sec oleg135-server: oleg135-server.virtnet: executing set_default_debug -1 all pdsh@oleg135-client: oleg135-server: ssh exited with exit code 1 1 cleanup 121 sec Started lustre-MDT0000 10:14:01 (1784124841) targets are mounted 10:14:01 (1784124841) facet_failover done 1 cleanup 122 sec 1 cleanup 123 sec 1 cleanup 124 sec 1 cleanup 125 sec 1 cleanup 126 sec 0 cleanup 127 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 607 91.115 27833.646 Close 446 62.422 22749.305 Rename 26 68.451 144.266 Unlink 124 18.972 59.831 Qpathinfo 582 14.195 359.312 Qfileinfo 97 1.957 9.550 Qfsinfo 99 1.647 16.017 Sfileinfo 49 634.679 28629.303 Find 213 8.536 47.633 WriteX 301 11.498 161.809 ReadX 957 1.139 88.255 LockX 2 7.241 8.645 UnlockX 2 7.878 9.774 Flush 42 37.821 79.378 Throughput 0.19233 MB/sec 1 clients 1 procs max_latency=27833.659 ms stopping dbench on /mnt/lustre at Wed Jul 15 10:14:06 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg135-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 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 Wed Jul 15 10:14:11 EDT 2026 waiting for dbench pid 68715 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 71 3.15 MB/sec warmup 1 sec latency 54.349 ms 1 140 3.01 MB/sec warmup 2 sec latency 104.220 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2928 1268376 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2740 1268564 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 21972 3582916 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 27508 3577848 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 49480 7160764 1% /mnt/lustre 1 189 2.53 MB/sec warmup 3 sec latency 203.672 ms 1 263 2.48 MB/sec warmup 4 sec latency 76.841 ms 1 312 2.30 MB/sec warmup 5 sec latency 286.271 ms 1 332 2.00 MB/sec warmup 6 sec latency 888.535 ms 1 412 2.09 MB/sec warmup 7 sec latency 67.862 ms 1 485 2.12 MB/sec warmup 8 sec latency 88.966 ms test_26 fail mds2 4 times 1 576 2.16 MB/sec warmup 9 sec latency 73.192 ms Failing mds2 on oleg135-server Stopping /mnt/lustre-mds2 (opts:) on oleg135-server 1 666 2.11 MB/sec warmup 10 sec latency 119.458 ms 1 733 1.94 MB/sec warmup 11 sec latency 118.497 ms 1 804 1.79 MB/sec warmup 12 sec latency 54.579 ms 1 882 1.67 MB/sec warmup 13 sec latency 61.855 ms 1 913 1.55 MB/sec warmup 14 sec latency 442.352 ms 1 985 1.46 MB/sec warmup 15 sec latency 55.613 ms 1 995 1.37 MB/sec warmup 16 sec latency 828.504 ms 1 995 1.29 MB/sec warmup 17 sec latency 1828.708 ms 10:14:28 (1784124868) shut down facet: mds2 facet_host: oleg135-server facet_failover_host: oleg135-server 1 995 1.22 MB/sec warmup 18 sec latency 2828.882 ms 1 995 1.15 MB/sec warmup 19 sec latency 3829.079 ms 1 995 0.00 MB/sec execute 1 sec latency 5829.991 ms 1 995 0.00 MB/sec execute 2 sec latency 6830.512 ms 1 995 0.00 MB/sec execute 3 sec latency 7832.147 ms 1 995 0.00 MB/sec execute 4 sec latency 8833.535 ms 1 995 0.00 MB/sec execute 5 sec latency 9833.754 ms 1 995 0.00 MB/sec execute 6 sec latency 10833.963 ms 1 995 0.00 MB/sec execute 7 sec latency 11834.535 ms Failover mds2 to oleg135-server mount facets: mds2 1 995 0.00 MB/sec execute 8 sec latency 12834.975 ms 1 995 0.00 MB/sec execute 9 sec latency 13835.249 ms 1 995 0.00 MB/sec execute 10 sec latency 14836.069 ms 1 995 0.00 MB/sec execute 11 sec latency 15836.307 ms 1 995 0.00 MB/sec execute 12 sec latency 16836.608 ms 1 995 0.00 MB/sec execute 13 sec latency 17836.879 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 18837.155 ms 1 995 0.00 MB/sec execute 15 sec latency 19837.420 ms 1 995 0.00 MB/sec execute 16 sec latency 20837.716 ms 1 995 0.00 MB/sec execute 17 sec latency 21840.480 ms oleg135-server: oleg135-server.virtnet: executing set_default_debug -1 all 1 995 0.00 MB/sec execute 18 sec latency 22840.706 ms pdsh@oleg135-client: oleg135-server: ssh exited with exit code 1 Started lustre-MDT0001 10:14:50 (1784124890) targets are mounted 10:14:50 (1784124890) facet_failover done 1 995 0.00 MB/sec execute 19 sec latency 23843.538 ms 1 995 0.00 MB/sec execute 20 sec latency 24843.844 ms 1 1002 0.01 MB/sec execute 21 sec latency 25532.902 ms 1 1064 0.04 MB/sec execute 22 sec latency 165.108 ms 1 1147 0.05 MB/sec execute 23 sec latency 59.618 ms oleg135-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 1 1211 0.05 MB/sec execute 24 sec latency 69.202 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1262 0.05 MB/sec execute 25 sec latency 93.982 ms 1 1403 0.16 MB/sec execute 26 sec latency 117.411 ms 1 1468 0.15 MB/sec execute 27 sec latency 197.686 ms 1 1532 0.15 MB/sec execute 28 sec latency 68.967 ms 1 1616 0.15 MB/sec execute 29 sec latency 76.849 ms 1 1721 0.14 MB/sec execute 30 sec latency 55.083 ms 1 1816 0.14 MB/sec execute 31 sec latency 69.028 ms 1 1888 0.14 MB/sec execute 32 sec latency 70.571 ms 1 1984 0.14 MB/sec execute 33 sec latency 62.481 ms 1 2069 0.14 MB/sec execute 34 sec latency 81.339 ms 1 2156 0.14 MB/sec execute 35 sec latency 87.403 ms 1 2247 0.14 MB/sec execute 36 sec latency 72.396 ms 1 2350 0.16 MB/sec execute 37 sec latency 103.425 ms 1 2406 0.16 MB/sec execute 38 sec latency 74.736 ms 1 2477 0.17 MB/sec execute 39 sec latency 79.588 ms 1 2576 0.18 MB/sec execute 40 sec latency 69.566 ms 1 2764 0.24 MB/sec execute 41 sec latency 79.118 ms 1 2922 0.28 MB/sec execute 42 sec latency 108.540 ms 1 2996 0.27 MB/sec execute 43 sec latency 75.994 ms 1 3201 0.28 MB/sec execute 44 sec latency 93.587 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Jul 15 10:15:16 EDT 2026 with return code 0 1 3342 0.30 MB/sec execute 45 sec latency 74.525 ms 68715 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 68715 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished