== replay-dual test 26: dbench and tar with mds failover ========================================================== 14:21:22 (1779128482) Starting client oleg458-client.virtnet: -o user_xattr,flock 192.168.204.158@tcp:/lustre /mnt/lustre Started clients oleg458-client.virtnet: 192.168.204.158@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 64795 Started dbench loop with 64796 striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1968 1269336 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1768 1269536 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 17948 3589016 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7194492 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 May 18 14:21:28 EDT 2026 waiting for dbench pid 64874 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 0 8 0.00 MB/sec warmup 1 sec latency 127.615 ms 1 66 1.44 MB/sec warmup 2 sec latency 122.736 ms 1 101 1.55 MB/sec warmup 3 sec latency 182.915 ms 1 121 1.37 MB/sec warmup 4 sec latency 238.343 ms 1 147 1.25 MB/sec warmup 5 sec latency 231.535 ms 1 167 1.13 MB/sec warmup 6 sec latency 292.146 ms 1 184 1.05 MB/sec warmup 7 sec latency 391.832 ms 1 199 0.98 MB/sec warmup 8 sec latency 735.008 ms 1 215 0.93 MB/sec warmup 9 sec latency 319.103 ms 1 240 0.91 MB/sec warmup 10 sec latency 335.361 ms test_26 fail mds1 1 times 1 267 0.91 MB/sec warmup 11 sec latency 172.830 ms 1 287 0.89 MB/sec warmup 12 sec latency 395.228 ms 1 307 0.86 MB/sec warmup 13 sec latency 190.657 ms Failing mds1 on oleg458-server 1 324 0.84 MB/sec warmup 14 sec latency 258.531 ms 1 356 0.85 MB/sec warmup 15 sec latency 161.334 ms Stopping /mnt/lustre-mds1 (opts:) on oleg458-server 1 382 0.85 MB/sec warmup 16 sec latency 187.368 ms 1 404 0.84 MB/sec warmup 17 sec latency 517.800 ms 1 404 0.80 MB/sec warmup 18 sec latency 1521.258 ms 14:21:47 (1779128507) shut down 1 404 0.75 MB/sec warmup 19 sec latency 2527.080 ms facet: mds1 facet_host: oleg458-server facet_failover_host: oleg458-server 1 404 0.00 MB/sec execute 1 sec latency 4529.716 ms 1 404 0.00 MB/sec execute 2 sec latency 5530.193 ms 1 404 0.00 MB/sec execute 3 sec latency 6533.166 ms 1 404 0.00 MB/sec execute 4 sec latency 7533.446 ms 1 404 0.00 MB/sec execute 5 sec latency 8533.859 ms 1 404 0.00 MB/sec execute 6 sec latency 9534.044 ms 1 404 0.00 MB/sec execute 7 sec latency 10537.387 ms 1 404 0.00 MB/sec execute 8 sec latency 11538.845 ms 1 404 0.00 MB/sec execute 9 sec latency 12539.905 ms Failover mds1 to oleg458-server mount facets: mds1 1 404 0.00 MB/sec execute 10 sec latency 13543.642 ms 1 404 0.00 MB/sec execute 11 sec latency 14543.944 ms 1 404 0.00 MB/sec execute 12 sec latency 15547.493 ms 1 404 0.00 MB/sec execute 13 sec latency 16548.047 ms 1 404 0.00 MB/sec execute 14 sec latency 17551.632 ms 1 404 0.00 MB/sec execute 15 sec latency 18552.416 ms 1 404 0.00 MB/sec execute 16 sec latency 19552.956 ms 1 404 0.00 MB/sec execute 17 sec latency 20555.719 ms 1 404 0.00 MB/sec execute 18 sec latency 21557.035 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 404 0.00 MB/sec execute 19 sec latency 22557.520 ms 1 404 0.00 MB/sec execute 20 sec latency 23558.289 ms 1 404 0.00 MB/sec execute 21 sec latency 24558.504 ms 1 404 0.00 MB/sec execute 22 sec latency 25558.958 ms 1 404 0.00 MB/sec execute 23 sec latency 26561.579 ms 1 404 0.00 MB/sec execute 24 sec latency 27561.871 ms 1 404 0.00 MB/sec execute 25 sec latency 28562.028 ms 1 404 0.00 MB/sec execute 26 sec latency 29562.364 ms 1 404 0.00 MB/sec execute 27 sec latency 30563.120 ms oleg458-server: oleg458-server.virtnet: executing set_default_debug -1 all 1 404 0.00 MB/sec execute 28 sec latency 31563.843 ms pdsh@oleg458-client: oleg458-server: ssh exited with exit code 1 1 404 0.00 MB/sec execute 29 sec latency 32564.112 ms Started lustre-MDT0000 14:22:18 (1779128538) targets are mounted 14:22:18 (1779128538) facet_failover done 1 404 0.00 MB/sec execute 30 sec latency 33564.275 ms 1 410 0.00 MB/sec execute 31 sec latency 34369.330 ms 1 449 0.04 MB/sec execute 32 sec latency 118.418 ms 1 494 0.09 MB/sec execute 33 sec latency 110.412 ms oleg458-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 528 0.11 MB/sec execute 34 sec latency 169.761 ms 1 586 0.16 MB/sec execute 35 sec latency 463.865 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 649 0.19 MB/sec execute 36 sec latency 102.005 ms 1 689 0.18 MB/sec execute 37 sec latency 100.951 ms 1 731 0.18 MB/sec execute 38 sec latency 108.719 ms 1 769 0.18 MB/sec execute 39 sec latency 96.324 ms 1 804 0.18 MB/sec execute 40 sec latency 122.166 ms 1 863 0.18 MB/sec execute 41 sec latency 89.145 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2088 1269216 1% /mnt/lustre[MDT:0] 1 892 0.17 MB/sec execute 42 sec latency 116.959 ms lustre-MDT0001_UUID 1414116 1900 1269404 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 34668 3571412 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 9596 3586580 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 44264 7157992 1% /mnt/lustre 1 918 0.17 MB/sec execute 43 sec latency 162.322 ms 1 955 0.17 MB/sec execute 44 sec latency 105.822 ms 1 986 0.17 MB/sec execute 45 sec latency 118.584 ms 1 1047 0.19 MB/sec execute 46 sec latency 105.983 ms 1 1102 0.18 MB/sec execute 47 sec latency 104.560 ms 1 1155 0.18 MB/sec execute 48 sec latency 77.433 ms 1 1173 0.18 MB/sec execute 49 sec latency 682.228 ms 1 1221 0.17 MB/sec execute 50 sec latency 137.472 ms 1 1265 0.17 MB/sec execute 51 sec latency 74.501 ms test_26 fail mds2 2 times 1 1399 0.22 MB/sec execute 52 sec latency 80.089 ms Failing mds2 on oleg458-server 1 1446 0.22 MB/sec execute 53 sec latency 101.205 ms Stopping /mnt/lustre-mds2 (opts:) on oleg458-server 1 1499 0.22 MB/sec execute 54 sec latency 71.958 ms 1 1560 0.21 MB/sec execute 55 sec latency 74.084 ms 14:22:44 (1779128564) shut down 1 1622 0.21 MB/sec execute 56 sec latency 77.870 ms facet: mds2 facet_host: oleg458-server facet_failover_host: oleg458-server 1 1686 0.21 MB/sec execute 57 sec latency 72.696 ms 1 1748 0.21 MB/sec execute 58 sec latency 150.539 ms 1 1814 0.20 MB/sec execute 59 sec latency 108.241 ms 1 1867 0.20 MB/sec execute 60 sec latency 111.638 ms 1 1942 0.20 MB/sec execute 61 sec latency 92.678 ms 1 2000 0.20 MB/sec execute 62 sec latency 96.040 ms 1 2065 0.19 MB/sec execute 63 sec latency 75.156 ms 1 2145 0.19 MB/sec execute 64 sec latency 82.551 ms 1 2193 0.19 MB/sec execute 65 sec latency 99.252 ms 1 2259 0.19 MB/sec execute 66 sec latency 268.193 ms Failover mds2 to oleg458-server mount facets: mds2 1 2259 0.19 MB/sec execute 67 sec latency 1270.970 ms 1 2259 0.18 MB/sec execute 68 sec latency 2271.209 ms 1 2259 0.18 MB/sec execute 69 sec latency 3273.918 ms 1 2259 0.18 MB/sec execute 70 sec latency 4274.163 ms 1 2259 0.17 MB/sec execute 71 sec latency 5276.419 ms 1 2259 0.17 MB/sec execute 72 sec latency 6281.944 ms 1 2259 0.17 MB/sec execute 73 sec latency 7282.141 ms 1 2259 0.17 MB/sec execute 74 sec latency 8282.449 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.17 MB/sec execute 75 sec latency 9282.668 ms 1 2259 0.16 MB/sec execute 76 sec latency 10283.039 ms 1 2259 0.16 MB/sec execute 77 sec latency 11283.391 ms 1 2259 0.16 MB/sec execute 78 sec latency 12283.632 ms oleg458-server: oleg458-server.virtnet: executing set_default_debug -1 all 1 2259 0.16 MB/sec execute 79 sec latency 13284.659 ms pdsh@oleg458-client: oleg458-server: ssh exited with exit code 1 Started lustre-MDT0001 14:23:08 (1779128588) targets are mounted 14:23:08 (1779128588) facet_failover done 1 2259 0.16 MB/sec execute 80 sec latency 14287.181 ms 1 2259 0.15 MB/sec execute 81 sec latency 15289.452 ms 1 2350 0.16 MB/sec execute 82 sec latency 15343.939 ms 1 2395 0.16 MB/sec execute 83 sec latency 101.968 ms oleg458-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 2428 0.16 MB/sec execute 84 sec latency 106.606 ms 1 2466 0.17 MB/sec execute 85 sec latency 115.103 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2558 0.17 MB/sec execute 86 sec latency 92.508 ms 1 2596 0.17 MB/sec execute 87 sec latency 97.833 ms 1 2770 0.20 MB/sec execute 88 sec latency 90.872 ms 1 2903 0.21 MB/sec execute 89 sec latency 82.807 ms 1 2978 0.21 MB/sec execute 90 sec latency 126.611 ms 1 3024 0.21 MB/sec execute 91 sec latency 123.070 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2328 1268976 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2188 1269116 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 35480 3570108 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 33044 3571824 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 68524 7141932 1% /mnt/lustre 1 3204 0.22 MB/sec execute 92 sec latency 88.241 ms 1 3276 0.23 MB/sec execute 93 sec latency 136.912 ms 1 3341 0.22 MB/sec execute 94 sec latency 134.478 ms 1 3392 0.22 MB/sec execute 95 sec latency 84.159 ms 1 3558 0.25 MB/sec execute 96 sec latency 73.811 ms 1 3620 0.25 MB/sec execute 97 sec latency 106.944 ms 1 3673 0.25 MB/sec execute 98 sec latency 69.812 ms 1 3707 0.25 MB/sec execute 99 sec latency 105.779 ms 1 cleanup 100 sec test_26 fail mds1 3 times 1 cleanup 101 sec 1 cleanup 102 sec Failing mds1 on oleg458-server 1 cleanup 103 sec Stopping /mnt/lustre-mds1 (opts:) on oleg458-server 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 502 78.563 15343.926 Close 422 91.716 34369.307 Rename 26 78.011 162.296 Unlink 64 23.612 65.989 Qpathinfo 477 15.351 105.960 Qfileinfo 125 2.226 11.740 Qfsinfo 94 2.779 31.376 Sfileinfo 50 53.155 99.609 Find 193 10.306 58.448 WriteX 428 12.262 84.273 ReadX 953 0.802 77.312 LockX 2 7.669 9.094 UnlockX 2 14.959 15.749 Flush 43 51.777 106.582 Throughput 0.246464 MB/sec 1 clients 1 procs max_latency=34369.330 ms stopping dbench on /mnt/lustre at Mon May 18 14:23:32 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre 14:23:35 (1779128615) shut down facet: mds1 facet_host: oleg458-server facet_failover_host: oleg458-server Failover mds1 to oleg458-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg458-server: oleg458-server.virtnet: executing set_default_debug -1 all pdsh@oleg458-client: oleg458-server: ssh exited with exit code 1 Started lustre-MDT0000 14:24:07 (1779128647) targets are mounted 14:24:07 (1779128647) facet_failover done removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench oleg458-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 Mon May 18 14:24:16 EDT 2026 waiting for dbench pid 67930 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 35 1.11 MB/sec warmup 1 sec latency 129.877 ms 1 105 2.46 MB/sec warmup 2 sec latency 137.515 ms 1 145 2.07 MB/sec warmup 3 sec latency 172.597 ms 1 182 1.83 MB/sec warmup 4 sec latency 134.274 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2644 1268660 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2480 1268824 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 3464 3602828 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46268 3560500 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 49732 7163328 1% /mnt/lustre 1 203 1.58 MB/sec warmup 5 sec latency 399.481 ms 1 244 1.54 MB/sec warmup 6 sec latency 100.845 ms 1 287 1.53 MB/sec warmup 7 sec latency 153.619 ms 1 323 1.47 MB/sec warmup 8 sec latency 128.480 ms 1 357 1.42 MB/sec warmup 9 sec latency 146.480 ms 1 409 1.44 MB/sec warmup 10 sec latency 117.329 ms 1 460 1.47 MB/sec warmup 11 sec latency 106.418 ms 1 511 1.48 MB/sec warmup 12 sec latency 135.435 ms 1 591 1.57 MB/sec warmup 13 sec latency 110.948 ms test_26 fail mds2 4 times 1 661 1.51 MB/sec warmup 14 sec latency 85.988 ms Failing mds2 on oleg458-server 1 695 1.41 MB/sec warmup 15 sec latency 129.061 ms Stopping /mnt/lustre-mds2 (opts:) on oleg458-server 1 731 1.33 MB/sec warmup 16 sec latency 107.805 ms 1 770 1.25 MB/sec warmup 17 sec latency 98.017 ms 1 805 1.19 MB/sec warmup 18 sec latency 109.721 ms 1 861 1.13 MB/sec warmup 19 sec latency 116.040 ms 14:24:35 (1779128675) shut down facet: mds2 facet_host: oleg458-server facet_failover_host: oleg458-server 1 898 0.01 MB/sec execute 1 sec latency 892.650 ms 1 940 0.05 MB/sec execute 2 sec latency 77.748 ms 1 981 0.08 MB/sec execute 3 sec latency 98.842 ms 1 995 0.06 MB/sec execute 4 sec latency 682.325 ms 1 995 0.05 MB/sec execute 5 sec latency 1682.525 ms 1 995 0.04 MB/sec execute 6 sec latency 2682.737 ms 1 995 0.03 MB/sec execute 7 sec latency 3682.961 ms 1 995 0.03 MB/sec execute 8 sec latency 4683.250 ms 1 995 0.03 MB/sec execute 9 sec latency 5683.434 ms Failover mds2 to oleg458-server mount facets: mds2 1 995 0.02 MB/sec execute 10 sec latency 6684.408 ms 1 995 0.02 MB/sec execute 11 sec latency 7684.580 ms 1 995 0.02 MB/sec execute 12 sec latency 8684.751 ms 1 995 0.02 MB/sec execute 13 sec latency 9685.731 ms 1 995 0.02 MB/sec execute 14 sec latency 10685.919 ms 1 995 0.02 MB/sec execute 15 sec latency 11686.703 ms 1 995 0.01 MB/sec execute 16 sec latency 12690.746 ms 1 995 0.01 MB/sec execute 17 sec latency 13693.386 ms 1 995 0.01 MB/sec execute 18 sec latency 14693.577 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 995 0.01 MB/sec execute 19 sec latency 15694.622 ms 1 995 0.01 MB/sec execute 20 sec latency 16696.376 ms 1 995 0.01 MB/sec execute 21 sec latency 17703.904 ms 1 995 0.01 MB/sec execute 22 sec latency 18704.097 ms 1 995 0.01 MB/sec execute 23 sec latency 19704.331 ms 1 995 0.01 MB/sec execute 24 sec latency 20704.588 ms oleg458-server: oleg458-server.virtnet: executing set_default_debug -1 all 1 995 0.01 MB/sec execute 25 sec latency 21707.225 ms 1 995 0.01 MB/sec execute 26 sec latency 22707.829 ms pdsh@oleg458-client: oleg458-server: ssh exited with exit code 1 1 995 0.01 MB/sec execute 27 sec latency 23708.099 ms Started lustre-MDT0001 14:25:03 (1779128703) targets are mounted 14:25:03 (1779128703) facet_failover done 1 1038 0.04 MB/sec execute 28 sec latency 23748.708 ms 1 1077 0.04 MB/sec execute 29 sec latency 126.525 ms 1 1127 0.04 MB/sec execute 30 sec latency 124.404 ms 1 1163 0.04 MB/sec execute 31 sec latency 112.731 ms oleg458-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 1204 0.04 MB/sec execute 32 sec latency 97.249 ms 1 1233 0.04 MB/sec execute 33 sec latency 107.337 ms 1 1270 0.04 MB/sec execute 34 sec latency 117.118 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1405 0.12 MB/sec execute 35 sec latency 123.021 ms 1 1440 0.12 MB/sec execute 36 sec latency 131.273 ms 1 1470 0.12 MB/sec execute 37 sec latency 354.717 ms 1 1508 0.12 MB/sec execute 38 sec latency 152.561 ms 1 1564 0.11 MB/sec execute 39 sec latency 93.648 ms 1 1619 0.11 MB/sec execute 40 sec latency 85.288 ms 1 1660 0.11 MB/sec execute 41 sec latency 104.185 ms 1 1698 0.11 MB/sec execute 42 sec latency 123.454 ms 1 1771 0.11 MB/sec execute 43 sec latency 75.331 ms 1 1825 0.11 MB/sec execute 44 sec latency 130.325 ms 1 1864 0.10 MB/sec execute 45 sec latency 116.697 ms 1 1946 0.10 MB/sec execute 46 sec latency 82.246 ms 1 1986 0.10 MB/sec execute 47 sec latency 125.655 ms 1 2022 0.10 MB/sec execute 48 sec latency 105.007 ms 1 2083 0.10 MB/sec execute 49 sec latency 111.960 ms 1 2150 0.10 MB/sec execute 50 sec latency 101.263 ms 1 2181 0.10 MB/sec execute 51 sec latency 151.685 ms 1 2264 0.10 MB/sec execute 52 sec latency 74.320 ms 1 2348 0.12 MB/sec execute 53 sec latency 74.835 ms 1 2378 0.12 MB/sec execute 54 sec latency 192.806 ms 1 2416 0.12 MB/sec execute 55 sec latency 94.532 ms 1 2453 0.11 MB/sec execute 56 sec latency 90.726 ms 1 2494 0.12 MB/sec execute 57 sec latency 141.883 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon May 18 14:25:34 EDT 2026 with return code 0 1 2580 0.13 MB/sec execute 58 sec latency 70.392 ms 67930 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67930 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished