== replay-dual test 26: dbench and tar with mds failover ========================================================== 22:45:04 (1788835504) Starting client oleg639-client.virtnet: -o user_xattr,flock 192.168.206.139@tcp:/lustre /mnt/lustre Started clients oleg639-client.virtnet: 192.168.206.139@tcp:/lustre on /mnt/lustre type lustre (rw,flock,checksum,encrypt,lazystatfs,lruresize,nolock,statfs_project,nosync_on_close,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 45168 Started dbench loop with 45170 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 2210560 2048 2206464 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 10240 3740672 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3762176 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 12288 7502848 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 Sep 7 22:45:12 EDT 2026 waiting for dbench pid 45238 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 26 0.78 MB/sec warmup 1 sec latency 70.760 ms 1 90 2.09 MB/sec warmup 2 sec latency 158.871 ms 1 117 1.76 MB/sec warmup 3 sec latency 227.757 ms 1 139 1.50 MB/sec warmup 4 sec latency 211.278 ms 1 165 1.36 MB/sec warmup 5 sec latency 182.491 ms test_26 fail mds1 1 times 1 189 1.26 MB/sec warmup 6 sec latency 285.397 ms 1 215 1.19 MB/sec warmup 7 sec latency 190.298 ms 1 247 1.17 MB/sec warmup 8 sec latency 250.143 ms Failing mds1 on oleg639-server 1 272 1.13 MB/sec warmup 9 sec latency 194.986 ms Stopping /mnt/lustre-mds1 (opts:) on oleg639-server 1 297 1.09 MB/sec warmup 10 sec latency 192.366 ms 1 324 1.06 MB/sec warmup 11 sec latency 143.812 ms 1 330 1.00 MB/sec warmup 12 sec latency 926.831 ms 1 330 0.92 MB/sec warmup 13 sec latency 1927.001 ms 1 330 0.86 MB/sec warmup 14 sec latency 2927.268 ms 22:45:26 (1788835526) shut down facet: mds1 facet_host: oleg639-server facet_failover_host: oleg639-server 1 330 0.80 MB/sec warmup 15 sec latency 3933.349 ms 1 330 0.75 MB/sec warmup 16 sec latency 4933.616 ms 1 330 0.70 MB/sec warmup 17 sec latency 5933.903 ms 1 330 0.67 MB/sec warmup 18 sec latency 6935.220 ms 1 330 0.63 MB/sec warmup 19 sec latency 7935.474 ms 1 330 0.00 MB/sec execute 1 sec latency 9938.085 ms 1 330 0.00 MB/sec execute 2 sec latency 10941.977 ms 1 330 0.00 MB/sec execute 3 sec latency 11942.443 ms 1 330 0.00 MB/sec execute 4 sec latency 12942.631 ms Failover mds1 to oleg639-server mount facets: mds1 1 330 0.00 MB/sec execute 5 sec latency 13952.186 ms 1 330 0.00 MB/sec execute 6 sec latency 14953.239 ms 1 330 0.00 MB/sec execute 7 sec latency 15953.764 ms 1 330 0.00 MB/sec execute 8 sec latency 16969.884 ms 1 330 0.00 MB/sec execute 9 sec latency 17970.133 ms 1 330 0.00 MB/sec execute 10 sec latency 18970.812 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 330 0.00 MB/sec execute 11 sec latency 19972.585 ms 1 330 0.00 MB/sec execute 12 sec latency 20973.297 ms 1 330 0.00 MB/sec execute 13 sec latency 21973.506 ms 1 330 0.00 MB/sec execute 14 sec latency 22973.807 ms 1 330 0.00 MB/sec execute 15 sec latency 23974.144 ms 1 330 0.00 MB/sec execute 16 sec latency 24975.124 ms 1 330 0.00 MB/sec execute 17 sec latency 25975.349 ms 1 330 0.00 MB/sec execute 18 sec latency 26975.606 ms 1 330 0.00 MB/sec execute 19 sec latency 27976.761 ms 1 330 0.00 MB/sec execute 20 sec latency 28977.441 ms 1 330 0.00 MB/sec execute 21 sec latency 29977.653 ms 1 330 0.00 MB/sec execute 22 sec latency 30978.730 ms 1 330 0.00 MB/sec execute 23 sec latency 31978.901 ms 1 330 0.00 MB/sec execute 24 sec latency 32979.077 ms 1 330 0.00 MB/sec execute 25 sec latency 33979.268 ms 1 330 0.00 MB/sec execute 26 sec latency 34979.642 ms 1 330 0.00 MB/sec execute 27 sec latency 35984.998 ms oleg639-server: oleg639-server.virtnet: executing set_default_debug -1 all 1 330 0.00 MB/sec execute 28 sec latency 36985.243 ms pdsh@oleg639-client: oleg639-server: ssh exited with exit code 1 1 330 0.00 MB/sec execute 29 sec latency 37988.253 ms Started lustre-MDT0000 1 330 0.00 MB/sec execute 30 sec latency 38994.705 ms 22:46:02 (1788835562) targets are mounted 22:46:02 (1788835562) facet_failover done 1 349 0.02 MB/sec execute 31 sec latency 39411.057 ms 1 378 0.04 MB/sec execute 32 sec latency 180.512 ms 1 413 0.08 MB/sec execute 33 sec latency 142.975 ms 1 454 0.11 MB/sec execute 34 sec latency 110.468 ms 1 493 0.15 MB/sec execute 35 sec latency 115.176 ms 1 523 0.17 MB/sec execute 36 sec latency 156.232 ms 1 608 0.24 MB/sec execute 37 sec latency 113.430 ms oleg639-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 654 0.24 MB/sec execute 38 sec latency 143.224 ms 1 673 0.23 MB/sec execute 39 sec latency 281.657 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 699 0.23 MB/sec execute 40 sec latency 139.618 ms 1 723 0.23 MB/sec execute 41 sec latency 276.808 ms 1 759 0.22 MB/sec execute 42 sec latency 110.533 ms 1 789 0.22 MB/sec execute 43 sec latency 155.808 ms 1 805 0.21 MB/sec execute 44 sec latency 211.209 ms 1 863 0.21 MB/sec execute 45 sec latency 101.998 ms 1 888 0.21 MB/sec execute 46 sec latency 184.553 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 38912 3701760 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 8192 3714048 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 47104 7415808 1% /mnt/lustre 1 913 0.21 MB/sec execute 47 sec latency 146.265 ms 1 934 0.20 MB/sec execute 48 sec latency 286.346 ms 1 972 0.20 MB/sec execute 49 sec latency 93.142 ms 1 993 0.20 MB/sec execute 50 sec latency 314.937 ms 1 1064 0.21 MB/sec execute 51 sec latency 72.311 ms 1 1127 0.21 MB/sec execute 52 sec latency 77.276 ms test_26 fail mds1 2 times 1 1163 0.21 MB/sec execute 53 sec latency 85.679 ms 1 1198 0.20 MB/sec execute 54 sec latency 88.524 ms Failing mds1 on oleg639-server 1 1231 0.20 MB/sec execute 55 sec latency 115.921 ms Stopping /mnt/lustre-mds1 (opts:) on oleg639-server 1 1285 0.20 MB/sec execute 56 sec latency 81.069 ms 1 1405 0.25 MB/sec execute 57 sec latency 283.270 ms 1 1405 0.24 MB/sec execute 58 sec latency 1287.848 ms 1 1405 0.24 MB/sec execute 59 sec latency 2289.684 ms 22:46:32 (1788835592) shut down facet: mds1 facet_host: oleg639-server facet_failover_host: oleg639-server 1 1405 0.23 MB/sec execute 60 sec latency 3290.879 ms 1 1405 0.23 MB/sec execute 61 sec latency 4291.274 ms 1 1405 0.23 MB/sec execute 62 sec latency 5292.576 ms 1 1405 0.22 MB/sec execute 63 sec latency 6294.594 ms 1 1405 0.22 MB/sec execute 64 sec latency 7294.895 ms 1 1405 0.22 MB/sec execute 65 sec latency 8298.172 ms 1 1405 0.21 MB/sec execute 66 sec latency 9299.346 ms 1 1405 0.21 MB/sec execute 67 sec latency 10299.930 ms 1 1405 0.21 MB/sec execute 68 sec latency 11300.163 ms 1 1405 0.20 MB/sec execute 69 sec latency 12300.506 ms 1 1405 0.20 MB/sec execute 70 sec latency 13300.805 ms Failover mds1 to oleg639-server mount facets: mds1 1 1405 0.20 MB/sec execute 71 sec latency 14301.006 ms 1 1405 0.19 MB/sec execute 72 sec latency 15301.225 ms 1 1405 0.19 MB/sec execute 73 sec latency 16301.835 ms 1 1405 0.19 MB/sec execute 74 sec latency 17302.165 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1405 0.19 MB/sec execute 75 sec latency 18303.549 ms 1 1405 0.18 MB/sec execute 76 sec latency 19303.878 ms 1 1405 0.18 MB/sec execute 77 sec latency 20304.270 ms 1 1405 0.18 MB/sec execute 78 sec latency 21304.527 ms 1 1405 0.18 MB/sec execute 79 sec latency 22309.453 ms 1 1405 0.17 MB/sec execute 80 sec latency 23309.764 ms 1 1405 0.17 MB/sec execute 81 sec latency 24310.943 ms 1 1405 0.17 MB/sec execute 82 sec latency 25311.223 ms 1 1405 0.17 MB/sec execute 83 sec latency 26316.455 ms 1 1405 0.17 MB/sec execute 84 sec latency 27316.720 ms 1 1405 0.16 MB/sec execute 85 sec latency 28319.093 ms 1 1405 0.16 MB/sec execute 86 sec latency 29319.343 ms 1 1405 0.16 MB/sec execute 87 sec latency 30321.135 ms 1 1405 0.16 MB/sec execute 88 sec latency 31321.395 ms 1 1405 0.16 MB/sec execute 89 sec latency 32321.671 ms oleg639-server: oleg639-server.virtnet: executing set_default_debug -1 all 1 1405 0.16 MB/sec execute 90 sec latency 33323.233 ms pdsh@oleg639-client: oleg639-server: ssh exited with exit code 1 1 1405 0.15 MB/sec execute 91 sec latency 34323.475 ms 1 1405 0.15 MB/sec execute 92 sec latency 35324.675 ms Started lustre-MDT0000 22:47:04 (1788835624) targets are mounted 22:47:04 (1788835624) facet_failover done 1 1405 0.15 MB/sec execute 93 sec latency 36324.879 ms 1 1405 0.15 MB/sec execute 94 sec latency 37326.865 ms 1 1405 0.15 MB/sec execute 95 sec latency 38327.087 ms 1 1405 0.15 MB/sec execute 96 sec latency 39331.365 ms 1 1405 0.14 MB/sec execute 97 sec latency 40336.493 ms 1 1405 0.14 MB/sec execute 98 sec latency 41336.724 ms 1 1428 0.14 MB/sec execute 99 sec latency 41420.576 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec oleg639-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 0 cleanup 105 sec 0 cleanup 105 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 163 327.854 41420.562 Close 148 278.915 39411.027 Rename 10 97.819 155.776 Unlink 19 25.855 48.826 Qpathinfo 108 21.410 86.025 Qfileinfo 60 2.375 15.196 Qfsinfo 33 4.246 27.139 Sfileinfo 34 62.655 145.649 Find 50 7.428 69.509 WriteX 265 13.938 70.196 ReadX 230 2.618 86.434 Flush 24 145.465 314.915 Throughput 0.141326 MB/sec 1 clients 1 procs max_latency=41420.576 ms stopping dbench on /mnt/lustre at Mon Sep 7 22:47:17 EDT 2026 with return code 0 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 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 Mon Sep 7 22:47:25 EDT 2026 waiting for dbench pid 47243 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 29 0.98 MB/sec warmup 1 sec latency 24.219 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2560 2205952 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 12288 3730432 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 37888 3702784 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 50176 7433216 1% /mnt/lustre 1 78 1.70 MB/sec warmup 2 sec latency 172.040 ms 1 114 1.74 MB/sec warmup 3 sec latency 174.956 ms 1 147 1.57 MB/sec warmup 4 sec latency 170.835 ms 1 173 1.41 MB/sec warmup 5 sec latency 154.825 ms 1 199 1.30 MB/sec warmup 6 sec latency 192.819 ms 1 245 1.33 MB/sec warmup 7 sec latency 123.169 ms 1 282 1.30 MB/sec warmup 8 sec latency 131.600 ms test_26 fail mds1 3 times 1 313 1.27 MB/sec warmup 9 sec latency 153.178 ms 1 340 1.22 MB/sec warmup 10 sec latency 162.569 ms 1 366 1.18 MB/sec warmup 11 sec latency 156.097 ms Failing mds1 on oleg639-server 1 400 1.17 MB/sec warmup 12 sec latency 150.722 ms Stopping /mnt/lustre-mds1 (opts:) on oleg639-server 1 437 1.18 MB/sec warmup 13 sec latency 130.454 ms 1 445 1.12 MB/sec warmup 14 sec latency 747.741 ms 1 445 1.04 MB/sec warmup 15 sec latency 1749.040 ms 1 445 0.98 MB/sec warmup 16 sec latency 2759.005 ms 22:47:41 (1788835661) shut down facet: mds1 facet_host: oleg639-server facet_failover_host: oleg639-server 1 445 0.92 MB/sec warmup 17 sec latency 3759.199 ms 1 445 0.87 MB/sec warmup 18 sec latency 4762.057 ms 1 445 0.82 MB/sec warmup 19 sec latency 5762.366 ms 1 445 0.00 MB/sec execute 1 sec latency 7762.713 ms 1 445 0.00 MB/sec execute 2 sec latency 8763.001 ms 1 445 0.00 MB/sec execute 3 sec latency 9763.468 ms 1 445 0.00 MB/sec execute 4 sec latency 10764.520 ms 1 445 0.00 MB/sec execute 5 sec latency 11764.766 ms 1 445 0.00 MB/sec execute 6 sec latency 12765.542 ms Failover mds1 to oleg639-server mount facets: mds1 1 445 0.00 MB/sec execute 7 sec latency 13767.704 ms 1 445 0.00 MB/sec execute 8 sec latency 14770.007 ms 1 445 0.00 MB/sec execute 9 sec latency 15775.133 ms 1 445 0.00 MB/sec execute 10 sec latency 16775.337 ms 1 445 0.00 MB/sec execute 11 sec latency 17775.534 ms 1 445 0.00 MB/sec execute 12 sec latency 18778.662 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 445 0.00 MB/sec execute 13 sec latency 19781.949 ms 1 445 0.00 MB/sec execute 14 sec latency 20782.179 ms 1 445 0.00 MB/sec execute 15 sec latency 21782.475 ms 1 445 0.00 MB/sec execute 16 sec latency 22783.132 ms 1 445 0.00 MB/sec execute 17 sec latency 23783.312 ms 1 445 0.00 MB/sec execute 18 sec latency 24783.633 ms 1 445 0.00 MB/sec execute 19 sec latency 25783.945 ms 1 445 0.00 MB/sec execute 20 sec latency 26784.121 ms 1 445 0.00 MB/sec execute 21 sec latency 27784.610 ms 1 445 0.00 MB/sec execute 22 sec latency 28785.682 ms 1 445 0.00 MB/sec execute 23 sec latency 29788.146 ms 1 445 0.00 MB/sec execute 24 sec latency 30788.382 ms 1 445 0.00 MB/sec execute 25 sec latency 31788.756 ms 1 445 0.00 MB/sec execute 26 sec latency 32788.978 ms 1 445 0.00 MB/sec execute 27 sec latency 33789.892 ms 1 445 0.00 MB/sec execute 28 sec latency 34790.332 ms 1 445 0.00 MB/sec execute 29 sec latency 35790.671 ms 1 445 0.00 MB/sec execute 30 sec latency 36791.152 ms 1 445 0.00 MB/sec execute 31 sec latency 37791.816 ms oleg639-server: oleg639-server.virtnet: executing set_default_debug -1 all 1 445 0.00 MB/sec execute 32 sec latency 38792.069 ms pdsh@oleg639-client: oleg639-server: ssh exited with exit code 1 1 445 0.00 MB/sec execute 33 sec latency 39797.526 ms 1 445 0.00 MB/sec execute 34 sec latency 40797.796 ms Started lustre-MDT0000 22:48:20 (1788835700) targets are mounted 22:48:20 (1788835700) facet_failover done 1 445 0.00 MB/sec execute 35 sec latency 41798.014 ms 1 469 0.02 MB/sec execute 36 sec latency 42057.413 ms 1 513 0.06 MB/sec execute 37 sec latency 131.842 ms 1 596 0.13 MB/sec execute 38 sec latency 116.922 ms 1 651 0.14 MB/sec execute 39 sec latency 126.435 ms 1 671 0.14 MB/sec execute 40 sec latency 318.415 ms 1 708 0.14 MB/sec execute 41 sec latency 118.553 ms oleg639-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 726 0.13 MB/sec execute 42 sec latency 294.241 ms 1 742 0.13 MB/sec execute 43 sec latency 208.114 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 776 0.13 MB/sec execute 44 sec latency 205.976 ms 1 796 0.13 MB/sec execute 45 sec latency 300.757 ms 1 816 0.13 MB/sec execute 46 sec latency 175.910 ms 1 873 0.13 MB/sec execute 47 sec latency 304.569 ms 1 902 0.13 MB/sec execute 48 sec latency 318.465 ms 1 925 0.12 MB/sec execute 49 sec latency 135.175 ms 1 970 0.12 MB/sec execute 50 sec latency 105.479 ms 1 1006 0.13 MB/sec execute 51 sec latency 299.066 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1082 0.14 MB/sec execute 52 sec latency 76.317 ms 1 1144 0.14 MB/sec execute 53 sec latency 76.180 ms 1 1190 0.14 MB/sec execute 54 sec latency 109.349 ms 1 1229 0.13 MB/sec execute 55 sec latency 85.288 ms 1 1268 0.13 MB/sec execute 56 sec latency 200.903 ms 1 1401 0.18 MB/sec execute 57 sec latency 84.804 ms 1 1451 0.18 MB/sec execute 58 sec latency 112.536 ms 1 1496 0.18 MB/sec execute 59 sec latency 361.097 ms 1 1534 0.17 MB/sec execute 60 sec latency 98.491 ms tar: Error is not recoverable: exiting now 1 1572 0.17 MB/sec execute 61 sec latency 92.134 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Sep 7 22:48:47 EDT 2026 with return code 0 47243 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47243 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished