== replay-dual test 26: dbench and tar with mds failover ========================================================== 15:44:57 (1782243897) Starting client oleg406-client.virtnet: -o user_xattr,flock 192.168.204.106@tcp:/lustre /mnt/lustre Started clients oleg406-client.virtnet: 192.168.204.106@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 44985 Started dbench loop with 44987 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 13312 3733504 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3765248 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 15360 7498752 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 Tue Jun 23 15:45:03 EDT 2026 waiting for dbench pid 45054 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 33.167 ms 1 71 1.57 MB/sec warmup 2 sec latency 263.733 ms 1 111 1.75 MB/sec warmup 3 sec latency 230.012 ms 1 128 1.44 MB/sec warmup 4 sec latency 357.398 ms 1 157 1.30 MB/sec warmup 5 sec latency 172.968 ms test_26 fail mds1 1 times 1 184 1.23 MB/sec warmup 6 sec latency 181.284 ms 1 205 1.14 MB/sec warmup 7 sec latency 264.166 ms 1 231 1.11 MB/sec warmup 8 sec latency 239.375 ms Failing mds1 on oleg406-server 1 256 1.07 MB/sec warmup 9 sec latency 252.733 ms Stopping /mnt/lustre-mds1 (opts:) on oleg406-server 1 287 1.07 MB/sec warmup 10 sec latency 162.129 ms 1 305 1.02 MB/sec warmup 11 sec latency 201.878 ms 1 312 0.95 MB/sec warmup 12 sec latency 759.984 ms 1 312 0.88 MB/sec warmup 13 sec latency 1761.948 ms 1 312 0.82 MB/sec warmup 14 sec latency 2765.006 ms 15:45:18 (1782243918) shut down 1 312 0.76 MB/sec warmup 15 sec latency 3765.318 ms facet: mds1 facet_host: oleg406-server facet_failover_host: oleg406-server 1 312 0.72 MB/sec warmup 16 sec latency 4765.580 ms 1 312 0.67 MB/sec warmup 17 sec latency 5766.734 ms 1 312 0.64 MB/sec warmup 18 sec latency 6767.076 ms 1 312 0.60 MB/sec warmup 19 sec latency 7767.393 ms 1 312 0.00 MB/sec execute 1 sec latency 9769.904 ms 1 312 0.00 MB/sec execute 2 sec latency 10770.984 ms 1 312 0.00 MB/sec execute 3 sec latency 11771.622 ms 1 312 0.00 MB/sec execute 4 sec latency 12773.876 ms 1 312 0.00 MB/sec execute 5 sec latency 13774.089 ms Failover mds1 to oleg406-server mount facets: mds1 1 312 0.00 MB/sec execute 6 sec latency 14774.748 ms 1 312 0.00 MB/sec execute 7 sec latency 15774.957 ms 1 312 0.00 MB/sec execute 8 sec latency 16775.173 ms 1 312 0.00 MB/sec execute 9 sec latency 17775.447 ms 1 312 0.00 MB/sec execute 10 sec latency 18775.778 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 312 0.00 MB/sec execute 11 sec latency 19777.105 ms 1 312 0.00 MB/sec execute 12 sec latency 20779.550 ms 1 312 0.00 MB/sec execute 13 sec latency 21779.943 ms 1 312 0.00 MB/sec execute 14 sec latency 22780.530 ms 1 312 0.00 MB/sec execute 15 sec latency 23781.972 ms 1 312 0.00 MB/sec execute 16 sec latency 24789.290 ms 1 312 0.00 MB/sec execute 17 sec latency 25790.527 ms 1 312 0.00 MB/sec execute 18 sec latency 26791.492 ms 1 312 0.00 MB/sec execute 19 sec latency 27794.842 ms 1 312 0.00 MB/sec execute 20 sec latency 28796.481 ms 1 312 0.00 MB/sec execute 21 sec latency 29797.788 ms 1 312 0.00 MB/sec execute 22 sec latency 30798.084 ms 1 312 0.00 MB/sec execute 23 sec latency 31802.744 ms 1 312 0.00 MB/sec execute 24 sec latency 32805.892 ms oleg406-server: oleg406-server.virtnet: executing set_default_debug -1 all 1 312 0.00 MB/sec execute 25 sec latency 33806.900 ms 1 312 0.00 MB/sec execute 26 sec latency 34808.001 ms pdsh@oleg406-client: oleg406-server: ssh exited with exit code 1 1 312 0.00 MB/sec execute 27 sec latency 35808.363 ms Started lustre-MDT0000 15:45:51 (1782243951) targets are mounted 15:45:51 (1782243951) facet_failover done 1 312 0.00 MB/sec execute 28 sec latency 36808.911 ms 1 312 0.00 MB/sec execute 29 sec latency 37809.136 ms 1 312 0.00 MB/sec execute 30 sec latency 38811.665 ms 1 312 0.00 MB/sec execute 31 sec latency 39814.020 ms 1 315 0.00 MB/sec execute 32 sec latency 40248.385 ms 1 341 0.02 MB/sec execute 33 sec latency 178.844 ms 1 373 0.05 MB/sec execute 34 sec latency 141.638 ms 1 408 0.08 MB/sec execute 35 sec latency 141.268 ms 1 441 0.11 MB/sec execute 36 sec latency 165.946 ms oleg406-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 470 0.13 MB/sec execute 37 sec latency 170.905 ms 1 499 0.16 MB/sec execute 38 sec latency 156.756 ms 1 518 0.16 MB/sec execute 39 sec latency 207.585 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 566 0.19 MB/sec execute 40 sec latency 197.734 ms 1 615 0.23 MB/sec execute 41 sec latency 106.053 ms 1 655 0.23 MB/sec execute 42 sec latency 143.789 ms 1 676 0.23 MB/sec execute 43 sec latency 240.275 ms 1 705 0.22 MB/sec execute 44 sec latency 133.753 ms 1 730 0.22 MB/sec execute 45 sec latency 146.106 ms 1 762 0.21 MB/sec execute 46 sec latency 105.862 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 35840 3693568 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 12288 3736576 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 48128 7430144 1% /mnt/lustre 1 780 0.21 MB/sec execute 47 sec latency 221.007 ms 1 796 0.21 MB/sec execute 48 sec latency 418.622 ms 1 824 0.20 MB/sec execute 49 sec latency 130.385 ms 1 867 0.20 MB/sec execute 50 sec latency 135.855 ms 1 888 0.20 MB/sec execute 51 sec latency 241.343 ms 1 913 0.20 MB/sec execute 52 sec latency 183.362 ms test_26 fail mds1 2 times 1 949 0.19 MB/sec execute 53 sec latency 199.286 ms 1 971 0.19 MB/sec execute 54 sec latency 140.136 ms 1 986 0.19 MB/sec execute 55 sec latency 344.216 ms Failing mds1 on oleg406-server 1 1041 0.20 MB/sec execute 56 sec latency 158.929 ms Stopping /mnt/lustre-mds1 (opts:) on oleg406-server 1 1080 0.20 MB/sec execute 57 sec latency 118.147 ms 1 1086 0.20 MB/sec execute 58 sec latency 737.264 ms 1 1086 0.19 MB/sec execute 59 sec latency 1737.924 ms 1 1086 0.19 MB/sec execute 60 sec latency 2738.502 ms 15:46:24 (1782243984) shut down facet: mds1 facet_host: oleg406-server facet_failover_host: oleg406-server 1 1086 0.19 MB/sec execute 61 sec latency 3739.007 ms 1 1086 0.18 MB/sec execute 62 sec latency 4739.391 ms 1 1086 0.18 MB/sec execute 63 sec latency 5739.711 ms 1 1086 0.18 MB/sec execute 64 sec latency 6741.505 ms 1 1086 0.18 MB/sec execute 65 sec latency 7743.379 ms 1 1086 0.17 MB/sec execute 66 sec latency 8744.835 ms 1 1086 0.17 MB/sec execute 67 sec latency 9745.044 ms 1 1086 0.17 MB/sec execute 68 sec latency 10745.572 ms 1 1086 0.17 MB/sec execute 69 sec latency 11746.120 ms 1 1086 0.16 MB/sec execute 70 sec latency 12746.510 ms Failover mds1 to oleg406-server mount facets: mds1 1 1086 0.16 MB/sec execute 71 sec latency 13746.711 ms 1 1086 0.16 MB/sec execute 72 sec latency 14747.067 ms 1 1086 0.16 MB/sec execute 73 sec latency 15747.449 ms 1 1086 0.15 MB/sec execute 74 sec latency 16747.714 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1086 0.15 MB/sec execute 75 sec latency 17748.001 ms 1 1086 0.15 MB/sec execute 76 sec latency 18750.474 ms 1 1086 0.15 MB/sec execute 77 sec latency 19750.793 ms 1 1086 0.15 MB/sec execute 78 sec latency 20754.466 ms 1 1086 0.14 MB/sec execute 79 sec latency 21754.704 ms 1 1086 0.14 MB/sec execute 80 sec latency 22754.921 ms 1 1086 0.14 MB/sec execute 81 sec latency 23755.167 ms 1 1086 0.14 MB/sec execute 82 sec latency 24755.963 ms 1 1086 0.14 MB/sec execute 83 sec latency 25756.359 ms 1 1086 0.14 MB/sec execute 84 sec latency 26756.572 ms 1 1086 0.13 MB/sec execute 85 sec latency 27756.789 ms 1 1086 0.13 MB/sec execute 86 sec latency 28757.003 ms 1 1086 0.13 MB/sec execute 87 sec latency 29757.276 ms 1 1086 0.13 MB/sec execute 88 sec latency 30757.567 ms 1 1086 0.13 MB/sec execute 89 sec latency 31759.160 ms 1 1086 0.13 MB/sec execute 90 sec latency 32759.464 ms 1 1086 0.13 MB/sec execute 91 sec latency 33761.137 ms 1 1086 0.12 MB/sec execute 92 sec latency 34761.452 ms oleg406-server: oleg406-server.virtnet: executing set_default_debug -1 all 1 1086 0.12 MB/sec execute 93 sec latency 35762.188 ms pdsh@oleg406-client: oleg406-server: ssh exited with exit code 1 1 1086 0.12 MB/sec execute 94 sec latency 36767.391 ms Started lustre-MDT0000 15:46:58 (1782244018) targets are mounted 15:46:58 (1782244018) facet_failover done 1 1086 0.12 MB/sec execute 95 sec latency 37774.221 ms 1 1086 0.12 MB/sec execute 96 sec latency 38776.495 ms 1 1086 0.12 MB/sec execute 97 sec latency 39776.743 ms 1 1088 0.12 MB/sec execute 98 sec latency 40544.792 ms 1 1124 0.12 MB/sec execute 99 sec latency 203.108 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec oleg406-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 cleanup 104 sec 0 cleanup 105 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 119 440.631 40544.764 Close 112 375.800 40248.347 Rename 6 135.379 220.976 Unlink 12 36.676 91.349 Qpathinfo 59 30.438 128.338 Qfileinfo 52 4.046 22.166 Qfsinfo 26 5.915 33.864 Sfileinfo 23 78.619 130.053 Find 32 17.219 203.062 WriteX 256 17.544 84.165 ReadX 114 6.413 95.539 Flush 24 139.867 418.537 Throughput 0.115985 MB/sec 1 clients 1 procs max_latency=40544.792 ms stopping dbench on /mnt/lustre at Tue Jun 23 15:47:08 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 Tue Jun 23 15:47:16 EDT 2026 waiting for dbench pid 47032 dbench version 4.00 - Copyright Andrew Tridgell 1999-2004 Running for 100 seconds with load 'client.txt' and minimum warmup 20 secs 1 of 1 processes prepared for launch 0 sec releasing clients 1 31 1.05 MB/sec warmup 1 sec latency 41.854 ms 1 75 1.60 MB/sec warmup 2 sec latency 154.620 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 3734528 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 28672 3703808 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 40960 7438336 1% /mnt/lustre 1 114 1.74 MB/sec warmup 3 sec latency 225.199 ms 1 140 1.50 MB/sec warmup 4 sec latency 215.238 ms 1 165 1.36 MB/sec warmup 5 sec latency 162.858 ms 1 189 1.26 MB/sec warmup 6 sec latency 204.134 ms 1 214 1.19 MB/sec warmup 7 sec latency 210.047 ms 1 242 1.14 MB/sec warmup 8 sec latency 185.633 ms 1 274 1.13 MB/sec warmup 9 sec latency 178.446 ms test_26 fail mds1 3 times 1 305 1.12 MB/sec warmup 10 sec latency 168.299 ms 1 326 1.06 MB/sec warmup 11 sec latency 213.194 ms 1 346 1.03 MB/sec warmup 12 sec latency 202.252 ms Failing mds1 on oleg406-server 1 373 1.02 MB/sec warmup 13 sec latency 221.797 ms Stopping /mnt/lustre-mds1 (opts:) on oleg406-server 1 398 1.00 MB/sec warmup 14 sec latency 154.166 ms 1 421 0.99 MB/sec warmup 15 sec latency 385.153 ms 1 421 0.93 MB/sec warmup 16 sec latency 1386.007 ms 1 421 0.87 MB/sec warmup 17 sec latency 2387.076 ms 15:47:33 (1782244053) shut down 1 421 0.82 MB/sec warmup 18 sec latency 3388.406 ms facet: mds1 facet_host: oleg406-server facet_failover_host: oleg406-server 1 421 0.78 MB/sec warmup 19 sec latency 4389.125 ms 1 421 0.00 MB/sec execute 1 sec latency 6389.873 ms 1 421 0.00 MB/sec execute 2 sec latency 7390.179 ms 1 421 0.00 MB/sec execute 3 sec latency 8390.544 ms 1 421 0.00 MB/sec execute 4 sec latency 9390.810 ms 1 421 0.00 MB/sec execute 5 sec latency 10391.084 ms 1 421 0.00 MB/sec execute 6 sec latency 11392.288 ms 1 421 0.00 MB/sec execute 7 sec latency 12392.771 ms 1 421 0.00 MB/sec execute 8 sec latency 13392.971 ms Failover mds1 to oleg406-server mount facets: mds1 1 421 0.00 MB/sec execute 9 sec latency 14393.145 ms 1 421 0.00 MB/sec execute 10 sec latency 15393.356 ms 1 421 0.00 MB/sec execute 11 sec latency 16394.315 ms 1 421 0.00 MB/sec execute 12 sec latency 17394.603 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 421 0.00 MB/sec execute 13 sec latency 18395.736 ms 1 421 0.00 MB/sec execute 14 sec latency 19396.433 ms 1 421 0.00 MB/sec execute 15 sec latency 20397.300 ms 1 421 0.00 MB/sec execute 16 sec latency 21397.664 ms 1 421 0.00 MB/sec execute 17 sec latency 22397.836 ms 1 421 0.00 MB/sec execute 18 sec latency 23399.272 ms 1 421 0.00 MB/sec execute 19 sec latency 24399.600 ms 1 421 0.00 MB/sec execute 20 sec latency 25413.056 ms 1 421 0.00 MB/sec execute 21 sec latency 26413.415 ms 1 421 0.00 MB/sec execute 22 sec latency 27414.391 ms 1 421 0.00 MB/sec execute 23 sec latency 28414.782 ms 1 421 0.00 MB/sec execute 24 sec latency 29415.694 ms 1 421 0.00 MB/sec execute 25 sec latency 30416.268 ms 1 421 0.00 MB/sec execute 26 sec latency 31416.600 ms 1 421 0.00 MB/sec execute 27 sec latency 32416.933 ms oleg406-server: oleg406-server.virtnet: executing set_default_debug -1 all 1 421 0.00 MB/sec execute 28 sec latency 33417.272 ms pdsh@oleg406-client: oleg406-server: ssh exited with exit code 1 1 421 0.00 MB/sec execute 29 sec latency 34417.966 ms 1 421 0.00 MB/sec execute 30 sec latency 35418.948 ms Started lustre-MDT0000 15:48:06 (1782244086) targets are mounted 15:48:06 (1782244086) facet_failover done 1 421 0.00 MB/sec execute 31 sec latency 36419.896 ms 1 421 0.00 MB/sec execute 32 sec latency 37430.081 ms 1 421 0.00 MB/sec execute 33 sec latency 38432.724 ms 1 421 0.00 MB/sec execute 34 sec latency 39433.498 ms 1 421 0.00 MB/sec execute 35 sec latency 40436.552 ms 1 421 0.00 MB/sec execute 36 sec latency 41437.764 ms 1 429 0.01 MB/sec execute 37 sec latency 42136.541 ms 1 461 0.03 MB/sec execute 38 sec latency 195.073 ms 1 491 0.06 MB/sec execute 39 sec latency 134.136 ms 1 514 0.07 MB/sec execute 40 sec latency 179.400 ms 1 573 0.11 MB/sec execute 41 sec latency 228.397 ms oleg406-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 616 0.15 MB/sec execute 42 sec latency 104.416 ms 1 661 0.15 MB/sec execute 43 sec latency 172.568 ms 1 674 0.14 MB/sec execute 44 sec latency 322.155 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 699 0.14 MB/sec execute 45 sec latency 161.203 ms 1 718 0.14 MB/sec execute 46 sec latency 161.345 ms 1 728 0.14 MB/sec execute 47 sec latency 448.496 ms 1 745 0.13 MB/sec execute 48 sec latency 234.630 ms 1 778 0.13 MB/sec execute 49 sec latency 140.152 ms 1 798 0.13 MB/sec execute 50 sec latency 312.848 ms 1 820 0.13 MB/sec execute 51 sec latency 181.777 ms 1 864 0.13 MB/sec execute 52 sec latency 168.630 ms 1 885 0.13 MB/sec execute 53 sec latency 313.950 ms 1 913 0.13 MB/sec execute 54 sec latency 133.396 ms 1 940 0.13 MB/sec execute 55 sec latency 196.130 ms 1 977 0.13 MB/sec execute 56 sec latency 115.144 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 995 0.12 MB/sec execute 57 sec latency 321.028 ms 1 1062 0.14 MB/sec execute 58 sec latency 139.557 ms 1 1112 0.14 MB/sec execute 59 sec latency 87.737 ms 1 1147 0.14 MB/sec execute 60 sec latency 100.771 ms 1 1177 0.13 MB/sec execute 61 sec latency 140.475 ms 1 1202 0.13 MB/sec execute 62 sec latency 126.491 ms 1 1233 0.13 MB/sec execute 63 sec latency 112.510 ms 1 1271 0.13 MB/sec execute 64 sec latency 103.643 ms 1 1403 0.17 MB/sec execute 65 sec latency 96.215 ms 1 1446 0.17 MB/sec execute 66 sec latency 101.285 ms tar: Error is not recoverable: exiting now 1 1481 0.17 MB/sec execute 67 sec latency 201.341 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Tue Jun 23 15:48:43 EDT 2026 with return code 0 47032 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47032 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished