== replay-dual test 26: dbench and tar with mds failover ========================================================== 21:56:19 (1789610179) Starting client oleg153-client.virtnet: -o user_xattr,flock 192.168.201.153@tcp:/lustre /mnt/lustre Started clients oleg153-client.virtnet: 192.168.201.153@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 45170 Started dbench loop with 45171 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 2048 3745792 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3765248 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 4096 7511040 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 Wed Sep 16 21:56:26 EDT 2026 waiting for dbench pid 45241 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 18 0.26 MB/sec warmup 1 sec latency 98.376 ms 1 71 1.57 MB/sec warmup 2 sec latency 148.823 ms 1 120 1.83 MB/sec warmup 3 sec latency 163.240 ms test_26 fail mds1 1 times 1 154 1.63 MB/sec warmup 4 sec latency 132.324 ms 1 181 1.46 MB/sec warmup 5 sec latency 185.994 ms Failing mds1 on oleg153-server 1 210 1.35 MB/sec warmup 6 sec latency 147.558 ms Stopping /mnt/lustre-mds1 (opts:) on oleg153-server 1 254 1.38 MB/sec warmup 7 sec latency 168.374 ms 1 286 1.33 MB/sec warmup 8 sec latency 135.795 ms 1 286 1.19 MB/sec warmup 9 sec latency 1052.344 ms 1 286 1.07 MB/sec warmup 10 sec latency 2053.441 ms 21:56:37 (1789610197) shut down facet: mds1 facet_host: oleg153-server facet_failover_host: oleg153-server 1 286 0.97 MB/sec warmup 11 sec latency 3053.714 ms 1 286 0.89 MB/sec warmup 12 sec latency 4053.963 ms 1 286 0.82 MB/sec warmup 13 sec latency 5054.758 ms 1 286 0.76 MB/sec warmup 14 sec latency 6057.549 ms 1 286 0.71 MB/sec warmup 15 sec latency 7057.785 ms 1 286 0.67 MB/sec warmup 16 sec latency 8058.333 ms 1 286 0.63 MB/sec warmup 17 sec latency 9058.579 ms 1 286 0.59 MB/sec warmup 18 sec latency 10058.928 ms 1 286 0.56 MB/sec warmup 19 sec latency 11059.222 ms 1 286 0.00 MB/sec execute 1 sec latency 13060.111 ms Failover mds1 to oleg153-server mount facets: mds1 1 286 0.00 MB/sec execute 2 sec latency 14060.358 ms 1 286 0.00 MB/sec execute 3 sec latency 15061.416 ms 1 286 0.00 MB/sec execute 4 sec latency 16066.965 ms 1 286 0.00 MB/sec execute 5 sec latency 17067.197 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 286 0.00 MB/sec execute 6 sec latency 18067.421 ms 1 286 0.00 MB/sec execute 7 sec latency 19067.623 ms 1 286 0.00 MB/sec execute 8 sec latency 20068.036 ms 1 286 0.00 MB/sec execute 9 sec latency 21068.265 ms 1 286 0.00 MB/sec execute 10 sec latency 22069.045 ms 1 286 0.00 MB/sec execute 11 sec latency 23070.579 ms 1 286 0.00 MB/sec execute 12 sec latency 24070.790 ms 1 286 0.00 MB/sec execute 13 sec latency 25071.175 ms 1 286 0.00 MB/sec execute 14 sec latency 26072.045 ms 1 286 0.00 MB/sec execute 15 sec latency 27072.253 ms 1 286 0.00 MB/sec execute 16 sec latency 28072.616 ms 1 286 0.00 MB/sec execute 17 sec latency 29080.546 ms 1 286 0.00 MB/sec execute 18 sec latency 30080.754 ms 1 286 0.00 MB/sec execute 19 sec latency 31080.954 ms 1 286 0.00 MB/sec execute 20 sec latency 32081.275 ms 1 286 0.00 MB/sec execute 21 sec latency 33083.941 ms 1 286 0.00 MB/sec execute 22 sec latency 34084.209 ms oleg153-server: oleg153-server.virtnet: executing set_default_debug -1 all 1 286 0.00 MB/sec execute 23 sec latency 35084.478 ms pdsh@oleg153-client: oleg153-server: ssh exited with exit code 1 1 286 0.00 MB/sec execute 24 sec latency 36084.718 ms Started lustre-MDT0000 21:57:11 (1789610231) targets are mounted 21:57:11 (1789610231) facet_failover done 1 286 0.00 MB/sec execute 25 sec latency 37085.463 ms 1 286 0.00 MB/sec execute 26 sec latency 38086.792 ms 1 286 0.00 MB/sec execute 27 sec latency 39093.589 ms 1 287 0.00 MB/sec execute 28 sec latency 39949.503 ms 1 313 0.03 MB/sec execute 29 sec latency 387.776 ms 1 346 0.06 MB/sec execute 30 sec latency 120.644 ms 1 374 0.08 MB/sec execute 31 sec latency 229.783 ms 1 405 0.11 MB/sec execute 32 sec latency 173.047 ms 1 437 0.14 MB/sec execute 33 sec latency 175.307 ms oleg153-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 471 0.17 MB/sec execute 34 sec latency 135.086 ms 1 504 0.19 MB/sec execute 35 sec latency 148.170 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 542 0.23 MB/sec execute 36 sec latency 132.856 ms 1 616 0.28 MB/sec execute 37 sec latency 116.365 ms 1 664 0.27 MB/sec execute 38 sec latency 137.601 ms 1 678 0.27 MB/sec execute 39 sec latency 307.112 ms 1 710 0.26 MB/sec execute 40 sec latency 132.202 ms 1 728 0.26 MB/sec execute 41 sec latency 299.556 ms 1 743 0.25 MB/sec execute 42 sec latency 190.181 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 36864 3706880 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 10240 3741696 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 47104 7448576 1% /mnt/lustre 1 773 0.25 MB/sec execute 43 sec latency 179.207 ms 1 789 0.24 MB/sec execute 44 sec latency 296.554 ms 1 803 0.24 MB/sec execute 45 sec latency 266.717 ms 1 845 0.24 MB/sec execute 46 sec latency 150.862 ms 1 877 0.23 MB/sec execute 47 sec latency 180.385 ms 1 913 0.23 MB/sec execute 48 sec latency 132.542 ms 1 949 0.23 MB/sec execute 49 sec latency 229.156 ms test_26 fail mds1 2 times 1 970 0.22 MB/sec execute 50 sec latency 155.093 ms 1 983 0.22 MB/sec execute 51 sec latency 471.601 ms Failing mds1 on oleg153-server 1 1031 0.23 MB/sec execute 52 sec latency 160.240 ms 1 1074 0.23 MB/sec execute 53 sec latency 109.055 ms Stopping /mnt/lustre-mds1 (opts:) on oleg153-server 1 1116 0.23 MB/sec execute 54 sec latency 137.553 ms 1 1128 0.22 MB/sec execute 55 sec latency 603.702 ms 1 1128 0.22 MB/sec execute 56 sec latency 1603.902 ms 1 1128 0.21 MB/sec execute 57 sec latency 2604.898 ms 21:57:44 (1789610264) shut down facet: mds1 facet_host: oleg153-server facet_failover_host: oleg153-server 1 1128 0.21 MB/sec execute 58 sec latency 3611.722 ms 1 1128 0.21 MB/sec execute 59 sec latency 4612.621 ms 1 1128 0.20 MB/sec execute 60 sec latency 5612.807 ms 1 1128 0.20 MB/sec execute 61 sec latency 6615.355 ms 1 1128 0.20 MB/sec execute 62 sec latency 7615.557 ms 1 1128 0.19 MB/sec execute 63 sec latency 8615.801 ms 1 1128 0.19 MB/sec execute 64 sec latency 9616.131 ms 1 1128 0.19 MB/sec execute 65 sec latency 10618.686 ms 1 1128 0.19 MB/sec execute 66 sec latency 11618.937 ms 1 1128 0.18 MB/sec execute 67 sec latency 12619.951 ms 1 1128 0.18 MB/sec execute 68 sec latency 13620.637 ms Failover mds1 to oleg153-server mount facets: mds1 1 1128 0.18 MB/sec execute 69 sec latency 14620.903 ms 1 1128 0.18 MB/sec execute 70 sec latency 15621.586 ms 1 1128 0.17 MB/sec execute 71 sec latency 16621.848 ms 1 1128 0.17 MB/sec execute 72 sec latency 17622.116 ms 1 1128 0.17 MB/sec execute 73 sec latency 18624.195 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1128 0.17 MB/sec execute 74 sec latency 19624.480 ms 1 1128 0.16 MB/sec execute 75 sec latency 20624.731 ms 1 1128 0.16 MB/sec execute 76 sec latency 21632.860 ms 1 1128 0.16 MB/sec execute 77 sec latency 22633.028 ms 1 1128 0.16 MB/sec execute 78 sec latency 23633.547 ms 1 1128 0.16 MB/sec execute 79 sec latency 24633.913 ms oleg153-server: oleg153-server.virtnet: executing set_default_debug -1 all 1 1128 0.15 MB/sec execute 80 sec latency 25634.743 ms 1 1128 0.15 MB/sec execute 81 sec latency 26634.974 ms pdsh@oleg153-client: oleg153-server: ssh exited with exit code 1 1 1128 0.15 MB/sec execute 82 sec latency 27635.207 ms Started lustre-MDT0000 21:58:09 (1789610289) targets are mounted 21:58:09 (1789610289) facet_failover done 1 1128 0.15 MB/sec execute 83 sec latency 28635.620 ms 1 1128 0.15 MB/sec execute 84 sec latency 29643.024 ms 1 1128 0.14 MB/sec execute 85 sec latency 30643.983 ms 1 1128 0.14 MB/sec execute 86 sec latency 31644.856 ms 1 1128 0.14 MB/sec execute 87 sec latency 32645.677 ms 1 1128 0.14 MB/sec execute 88 sec latency 33646.047 ms 1 1128 0.14 MB/sec execute 89 sec latency 34646.329 ms 1 1128 0.14 MB/sec execute 90 sec latency 35646.544 ms 1 1128 0.13 MB/sec execute 91 sec latency 36646.764 ms 1 1128 0.13 MB/sec execute 92 sec latency 37647.044 ms 1 1128 0.13 MB/sec execute 93 sec latency 38650.399 ms 1 1130 0.13 MB/sec execute 94 sec latency 39592.830 ms 1 1147 0.13 MB/sec execute 95 sec latency 214.285 ms 1 1181 0.13 MB/sec execute 96 sec latency 135.288 ms 1 1223 0.13 MB/sec execute 97 sec latency 104.591 ms 1 1263 0.13 MB/sec execute 98 sec latency 131.118 ms 1 1387 0.15 MB/sec execute 99 sec latency 103.789 ms oleg153-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 cleanup 100 sec 1 cleanup 101 sec mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 0 cleanup 106 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 154 89.746 387.757 Close 140 301.383 39949.473 Rename 10 128.954 296.528 Unlink 17 33.405 85.170 Qpathinfo 95 445.623 39592.748 Qfileinfo 62 2.294 16.768 Qfsinfo 33 3.603 20.208 Sfileinfo 34 70.880 125.536 Find 47 8.310 65.115 WriteX 285 15.100 76.805 ReadX 223 3.526 104.572 Flush 24 160.770 471.587 Throughput 0.154208 MB/sec 1 clients 1 procs max_latency=39949.503 ms stopping dbench on /mnt/lustre at Wed Sep 16 21:58:32 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished 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 2560 2205952 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 48128 3698688 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 7168 3739648 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 55296 7438336 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 Wed Sep 16 21:58:39 EDT 2026 waiting for dbench pid 47276 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 31 1.05 MB/sec warmup 1 sec latency 28.291 ms 1 97 2.19 MB/sec warmup 2 sec latency 126.223 ms 1 142 2.00 MB/sec warmup 3 sec latency 127.657 ms test_26 fail mds1 3 times 1 181 1.83 MB/sec warmup 4 sec latency 148.519 ms 1 203 1.58 MB/sec warmup 5 sec latency 164.277 ms 1 238 1.52 MB/sec warmup 6 sec latency 156.471 ms Failing mds1 on oleg153-server 1 272 1.45 MB/sec warmup 7 sec latency 153.921 ms Stopping /mnt/lustre-mds1 (opts:) on oleg153-server 1 310 1.42 MB/sec warmup 8 sec latency 138.252 ms 1 315 1.27 MB/sec warmup 9 sec latency 860.080 ms 1 315 1.15 MB/sec warmup 10 sec latency 1860.371 ms 21:58:50 (1789610330) shut down 1 315 1.04 MB/sec warmup 11 sec latency 2861.957 ms facet: mds1 facet_host: oleg153-server facet_failover_host: oleg153-server 1 315 0.96 MB/sec warmup 12 sec latency 3862.655 ms 1 315 0.88 MB/sec warmup 13 sec latency 4862.939 ms 1 315 0.82 MB/sec warmup 14 sec latency 5863.144 ms 1 315 0.76 MB/sec warmup 15 sec latency 6865.513 ms 1 315 0.72 MB/sec warmup 16 sec latency 7865.765 ms 1 315 0.67 MB/sec warmup 17 sec latency 8866.006 ms 1 315 0.64 MB/sec warmup 18 sec latency 9866.549 ms 1 315 0.60 MB/sec warmup 19 sec latency 10866.813 ms 1 315 0.00 MB/sec execute 1 sec latency 12867.639 ms Failover mds1 to oleg153-server mount facets: mds1 1 315 0.00 MB/sec execute 2 sec latency 13869.909 ms 1 315 0.00 MB/sec execute 3 sec latency 14870.091 ms 1 315 0.00 MB/sec execute 4 sec latency 15870.297 ms 1 315 0.00 MB/sec execute 5 sec latency 16875.096 ms 1 315 0.00 MB/sec execute 6 sec latency 17876.527 ms 1 315 0.00 MB/sec execute 7 sec latency 18877.939 ms 1 315 0.00 MB/sec execute 8 sec latency 19878.152 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 315 0.00 MB/sec execute 9 sec latency 20878.326 ms 1 315 0.00 MB/sec execute 10 sec latency 21886.000 ms 1 315 0.00 MB/sec execute 11 sec latency 22887.389 ms 1 315 0.00 MB/sec execute 12 sec latency 23887.596 ms 1 315 0.00 MB/sec execute 13 sec latency 24888.149 ms 1 315 0.00 MB/sec execute 14 sec latency 25888.362 ms 1 315 0.00 MB/sec execute 15 sec latency 26888.602 ms 1 315 0.00 MB/sec execute 16 sec latency 27890.212 ms 1 315 0.00 MB/sec execute 17 sec latency 28890.487 ms 1 315 0.00 MB/sec execute 18 sec latency 29890.934 ms 1 315 0.00 MB/sec execute 19 sec latency 30891.198 ms 1 315 0.00 MB/sec execute 20 sec latency 31891.803 ms 1 315 0.00 MB/sec execute 21 sec latency 32892.067 ms oleg153-server: oleg153-server.virtnet: executing set_default_debug -1 all 1 315 0.00 MB/sec execute 22 sec latency 33895.194 ms pdsh@oleg153-client: oleg153-server: ssh exited with exit code 1 1 315 0.00 MB/sec execute 23 sec latency 34895.433 ms Started lustre-MDT0000 21:59:23 (1789610363) targets are mounted 21:59:23 (1789610363) facet_failover done 1 315 0.00 MB/sec execute 24 sec latency 35896.196 ms 1 315 0.00 MB/sec execute 25 sec latency 36898.250 ms 1 315 0.00 MB/sec execute 26 sec latency 37898.504 ms 1 315 0.00 MB/sec execute 27 sec latency 38900.785 ms 1 315 0.00 MB/sec execute 28 sec latency 39901.289 ms 1 315 0.00 MB/sec execute 29 sec latency 40901.541 ms 1 315 0.00 MB/sec execute 30 sec latency 41902.132 ms 1 315 0.00 MB/sec execute 31 sec latency 42903.091 ms 1 315 0.00 MB/sec execute 32 sec latency 43903.411 ms 1 315 0.00 MB/sec execute 33 sec latency 44903.744 ms 1 315 0.00 MB/sec execute 34 sec latency 45904.603 ms 1 315 0.00 MB/sec execute 35 sec latency 46906.462 ms 1 315 0.00 MB/sec execute 36 sec latency 47906.812 ms 1 315 0.00 MB/sec execute 37 sec latency 48907.315 ms 1 315 0.00 MB/sec execute 38 sec latency 49907.583 ms 1 315 0.00 MB/sec execute 39 sec latency 50910.534 ms 1 315 0.00 MB/sec execute 40 sec latency 51912.513 ms 1 315 0.00 MB/sec execute 41 sec latency 52918.499 ms 1 334 0.01 MB/sec execute 42 sec latency 53231.627 ms 1 363 0.03 MB/sec execute 43 sec latency 160.096 ms 1 397 0.06 MB/sec execute 44 sec latency 141.988 ms 1 440 0.09 MB/sec execute 45 sec latency 116.783 ms 1 477 0.11 MB/sec execute 46 sec latency 170.208 ms 1 511 0.13 MB/sec execute 47 sec latency 143.954 ms oleg153-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 583 0.17 MB/sec execute 48 sec latency 122.679 ms 1 639 0.20 MB/sec execute 49 sec latency 135.422 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 664 0.19 MB/sec execute 50 sec latency 157.478 ms 1 686 0.19 MB/sec execute 51 sec latency 269.523 ms 1 726 0.19 MB/sec execute 52 sec latency 153.061 ms 1 743 0.19 MB/sec execute 53 sec latency 133.212 ms 1 778 0.18 MB/sec execute 54 sec latency 144.090 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 799 0.18 MB/sec execute 55 sec latency 194.109 ms 1 848 0.18 MB/sec execute 56 sec latency 99.857 ms 1 873 0.18 MB/sec execute 57 sec latency 229.382 ms 1 892 0.18 MB/sec execute 58 sec latency 357.708 ms 1 913 0.17 MB/sec execute 59 sec latency 174.600 ms 1 925 0.17 MB/sec execute 60 sec latency 290.271 ms 1 964 0.17 MB/sec execute 61 sec latency 143.433 ms 1 985 0.17 MB/sec execute 62 sec latency 247.054 ms 1 1050 0.18 MB/sec execute 63 sec latency 77.138 ms 1 1099 0.18 MB/sec execute 64 sec latency 92.691 ms 1 1145 0.18 MB/sec execute 65 sec latency 99.406 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Sep 16 22:00:05 EDT 2026 with return code 0 47276 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47276 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished