== replay-dual test 26: dbench and tar with mds failover ========================================================== 16:11:33 (1788466293) Starting client oleg248-client.virtnet: -o user_xattr,flock 192.168.202.148@tcp:/lustre /mnt/lustre Started clients oleg248-client.virtnet: 192.168.202.148@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 45173 Started dbench loop with 45174 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 22528 3732480 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3755008 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 24576 7487488 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 Thu Sep 3 16:11:39 EDT 2026 waiting for dbench pid 45225 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 14 0.00 MB/sec warmup 1 sec latency 4.321 ms 1 31 0.52 MB/sec warmup 2 sec latency 368.804 ms 1 70 1.05 MB/sec warmup 3 sec latency 242.808 ms 1 109 1.29 MB/sec warmup 4 sec latency 228.073 ms 1 122 1.10 MB/sec warmup 5 sec latency 401.659 ms 1 155 1.09 MB/sec warmup 6 sec latency 185.747 ms 1 170 0.98 MB/sec warmup 7 sec latency 248.090 ms test_26 fail mds1 1 times 1 184 0.92 MB/sec warmup 8 sec latency 280.368 ms 1 200 0.87 MB/sec warmup 9 sec latency 451.102 ms 1 231 0.88 MB/sec warmup 10 sec latency 171.816 ms Failing mds1 on oleg248-server 1 256 0.87 MB/sec warmup 11 sec latency 234.609 ms Stopping /mnt/lustre-mds1 (opts:) on oleg248-server 1 279 0.86 MB/sec warmup 12 sec latency 243.850 ms 1 295 0.83 MB/sec warmup 13 sec latency 289.671 ms 1 312 0.81 MB/sec warmup 14 sec latency 338.589 ms 1 312 0.76 MB/sec warmup 15 sec latency 1340.175 ms 1 312 0.71 MB/sec warmup 16 sec latency 2340.421 ms 16:11:57 (1788466317) shut down 1 312 0.67 MB/sec warmup 17 sec latency 3340.635 ms facet: mds1 facet_host: oleg248-server facet_failover_host: oleg248-server 1 312 0.63 MB/sec warmup 18 sec latency 4342.558 ms 1 312 0.60 MB/sec warmup 19 sec latency 5342.764 ms 1 312 0.00 MB/sec execute 1 sec latency 7343.624 ms 1 312 0.00 MB/sec execute 2 sec latency 8347.577 ms 1 312 0.00 MB/sec execute 3 sec latency 9347.895 ms 1 312 0.00 MB/sec execute 4 sec latency 10348.413 ms 1 312 0.00 MB/sec execute 5 sec latency 11348.836 ms 1 312 0.00 MB/sec execute 6 sec latency 12349.328 ms 1 312 0.00 MB/sec execute 7 sec latency 13349.603 ms Failover mds1 to oleg248-server mount facets: mds1 1 312 0.00 MB/sec execute 8 sec latency 14354.424 ms 1 312 0.00 MB/sec execute 9 sec latency 15355.846 ms 1 312 0.00 MB/sec execute 10 sec latency 16356.834 ms 1 312 0.00 MB/sec execute 11 sec latency 17357.268 ms 1 312 0.00 MB/sec execute 12 sec latency 18357.603 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 312 0.00 MB/sec execute 13 sec latency 19357.882 ms 1 312 0.00 MB/sec execute 14 sec latency 20359.864 ms 1 312 0.00 MB/sec execute 15 sec latency 21360.134 ms 1 312 0.00 MB/sec execute 16 sec latency 22360.647 ms 1 312 0.00 MB/sec execute 17 sec latency 23361.595 ms 1 312 0.00 MB/sec execute 18 sec latency 24361.870 ms oleg248-server: oleg248-server.virtnet: executing set_default_debug -1 all 1 312 0.00 MB/sec execute 19 sec latency 25364.901 ms pdsh@oleg248-client: oleg248-server: ssh exited with exit code 1 1 312 0.00 MB/sec execute 20 sec latency 26371.480 ms Started lustre-MDT0000 16:12:20 (1788466340) targets are mounted 16:12:20 (1788466340) facet_failover done 1 312 0.00 MB/sec execute 21 sec latency 27371.849 ms 1 312 0.00 MB/sec execute 22 sec latency 28377.305 ms 1 312 0.00 MB/sec execute 23 sec latency 29378.104 ms 1 312 0.00 MB/sec execute 24 sec latency 30378.430 ms 1 312 0.00 MB/sec execute 25 sec latency 31379.473 ms 1 312 0.00 MB/sec execute 26 sec latency 32379.937 ms 1 312 0.00 MB/sec execute 27 sec latency 33380.581 ms 1 312 0.00 MB/sec execute 28 sec latency 34380.838 ms 1 312 0.00 MB/sec execute 29 sec latency 35381.332 ms 1 312 0.00 MB/sec execute 30 sec latency 36381.660 ms 1 312 0.00 MB/sec execute 31 sec latency 37383.972 ms 1 312 0.00 MB/sec execute 32 sec latency 38384.188 ms 1 312 0.00 MB/sec execute 33 sec latency 39384.494 ms 1 312 0.00 MB/sec execute 34 sec latency 40384.732 ms 1 312 0.00 MB/sec execute 35 sec latency 41386.565 ms 1 331 0.01 MB/sec execute 36 sec latency 41478.771 ms 1 368 0.04 MB/sec execute 37 sec latency 148.070 ms 1 397 0.07 MB/sec execute 38 sec latency 134.414 ms 1 437 0.10 MB/sec execute 39 sec latency 130.951 ms 1 474 0.13 MB/sec execute 40 sec latency 135.196 ms oleg248-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 503 0.15 MB/sec execute 41 sec latency 181.782 ms 1 542 0.18 MB/sec execute 42 sec latency 176.394 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 616 0.22 MB/sec execute 43 sec latency 110.454 ms 1 664 0.22 MB/sec execute 44 sec latency 160.394 ms 1 676 0.22 MB/sec execute 45 sec latency 288.513 ms 1 711 0.21 MB/sec execute 46 sec latency 177.700 ms 1 738 0.21 MB/sec execute 47 sec latency 216.832 ms 1 783 0.21 MB/sec execute 48 sec latency 94.191 ms 1 801 0.20 MB/sec execute 49 sec latency 225.121 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 40960 3651584 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 6144 3742720 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 47104 7394304 1% /mnt/lustre 1 845 0.20 MB/sec execute 50 sec latency 163.651 ms 1 870 0.20 MB/sec execute 51 sec latency 181.821 ms 1 888 0.20 MB/sec execute 52 sec latency 313.603 ms 1 913 0.19 MB/sec execute 53 sec latency 156.327 ms 1 943 0.19 MB/sec execute 54 sec latency 132.651 ms 1 983 0.19 MB/sec execute 55 sec latency 145.657 ms test_26 fail mds1 2 times 1 1051 0.20 MB/sec execute 56 sec latency 153.893 ms 1 1083 0.20 MB/sec execute 57 sec latency 111.128 ms 1 1132 0.20 MB/sec execute 58 sec latency 95.788 ms Failing mds1 on oleg248-server 1 1164 0.20 MB/sec execute 59 sec latency 106.671 ms Stopping /mnt/lustre-mds1 (opts:) on oleg248-server 1 1198 0.19 MB/sec execute 60 sec latency 92.367 ms 1 1207 0.19 MB/sec execute 61 sec latency 748.377 ms 1 1207 0.19 MB/sec execute 62 sec latency 1748.538 ms 16:13:03 (1788466383) shut down 1 1207 0.18 MB/sec execute 63 sec latency 2753.090 ms facet: mds1 facet_host: oleg248-server facet_failover_host: oleg248-server 1 1207 0.18 MB/sec execute 64 sec latency 3759.898 ms 1 1207 0.18 MB/sec execute 65 sec latency 4760.770 ms 1 1207 0.17 MB/sec execute 66 sec latency 5761.092 ms 1 1207 0.17 MB/sec execute 67 sec latency 6761.439 ms 1 1207 0.17 MB/sec execute 68 sec latency 7761.644 ms 1 1207 0.17 MB/sec execute 69 sec latency 8762.254 ms 1 1207 0.16 MB/sec execute 70 sec latency 9764.030 ms 1 1207 0.16 MB/sec execute 71 sec latency 10765.181 ms 1 1207 0.16 MB/sec execute 72 sec latency 11765.632 ms 1 1207 0.16 MB/sec execute 73 sec latency 12766.592 ms Failover mds1 to oleg248-server mount facets: mds1 1 1207 0.16 MB/sec execute 74 sec latency 13770.817 ms 1 1207 0.15 MB/sec execute 75 sec latency 14771.154 ms 1 1207 0.15 MB/sec execute 76 sec latency 15772.113 ms 1 1207 0.15 MB/sec execute 77 sec latency 16774.651 ms 1 1207 0.15 MB/sec execute 78 sec latency 17776.728 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1207 0.15 MB/sec execute 79 sec latency 18777.316 ms 1 1207 0.14 MB/sec execute 80 sec latency 19778.551 ms 1 1207 0.14 MB/sec execute 81 sec latency 20780.413 ms 1 1207 0.14 MB/sec execute 82 sec latency 21780.586 ms 1 1207 0.14 MB/sec execute 83 sec latency 22780.931 ms 1 1207 0.14 MB/sec execute 84 sec latency 23781.225 ms 1 1207 0.14 MB/sec execute 85 sec latency 24782.148 ms oleg248-server: oleg248-server.virtnet: executing set_default_debug -1 all 1 1207 0.13 MB/sec execute 86 sec latency 25782.560 ms pdsh@oleg248-client: oleg248-server: ssh exited with exit code 1 1 1207 0.13 MB/sec execute 87 sec latency 26782.964 ms Started lustre-MDT0000 16:13:27 (1788466407) targets are mounted 16:13:27 (1788466407) facet_failover done 1 1207 0.13 MB/sec execute 88 sec latency 27783.643 ms 1 1207 0.13 MB/sec execute 89 sec latency 28783.930 ms 1 1207 0.13 MB/sec execute 90 sec latency 29784.768 ms 1 1207 0.13 MB/sec execute 91 sec latency 30785.039 ms 1 1207 0.13 MB/sec execute 92 sec latency 31785.327 ms 1 1207 0.12 MB/sec execute 93 sec latency 32785.913 ms 1 1207 0.12 MB/sec execute 94 sec latency 33786.567 ms 1 1207 0.12 MB/sec execute 95 sec latency 34790.866 ms 1 1207 0.12 MB/sec execute 96 sec latency 35790.995 ms 1 1207 0.12 MB/sec execute 97 sec latency 36791.324 ms 1 1207 0.12 MB/sec execute 98 sec latency 37791.479 ms 1 1207 0.12 MB/sec execute 99 sec latency 38793.481 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 1 cleanup 105 sec 1 cleanup 106 sec 0 cleanup 106 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 128 402.930 40971.710 Close 117 367.965 41478.752 Rename 8 106.583 177.655 Unlink 13 34.961 67.252 Qpathinfo 75 23.873 92.186 Qfileinfo 54 2.056 9.942 Qfsinfo 28 4.827 31.378 Sfileinfo 27 70.937 137.503 Find 37 7.932 68.677 WriteX 261 13.590 61.783 ReadX 124 5.187 83.301 Flush 24 131.586 313.580 Throughput 0.116637 MB/sec 1 clients 1 procs max_latency=41478.771 ms stopping dbench on /mnt/lustre at Thu Sep 3 16:13:46 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished oleg248-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 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 Thu Sep 3 16:13:54 EDT 2026 waiting for dbench pid 47188 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 137.127 ms 1 83 1.86 MB/sec warmup 2 sec latency 198.929 ms 1 113 1.74 MB/sec warmup 3 sec latency 259.700 ms 1 147 1.57 MB/sec warmup 4 sec latency 189.327 ms 1 173 1.41 MB/sec warmup 5 sec latency 190.701 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2560 2205952 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 45056 3712000 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 12288 3749888 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 57344 7461888 1% /mnt/lustre 1 196 1.30 MB/sec warmup 6 sec latency 198.713 ms 1 223 1.23 MB/sec warmup 7 sec latency 158.027 ms 1 255 1.20 MB/sec warmup 8 sec latency 177.524 ms 1 293 1.19 MB/sec warmup 9 sec latency 139.836 ms 1 331 1.20 MB/sec warmup 10 sec latency 136.905 ms 1 381 1.23 MB/sec warmup 11 sec latency 127.310 ms test_26 fail mds1 3 times 1 429 1.26 MB/sec warmup 12 sec latency 144.240 ms 1 472 1.26 MB/sec warmup 13 sec latency 147.473 ms Failing mds1 on oleg248-server Stopping /mnt/lustre-mds1 (opts:) on oleg248-server 1 514 1.26 MB/sec warmup 14 sec latency 140.277 ms 1 591 1.36 MB/sec warmup 15 sec latency 136.878 ms 1 600 1.31 MB/sec warmup 16 sec latency 852.701 ms 1 600 1.23 MB/sec warmup 17 sec latency 1854.663 ms 16:14:12 (1788466452) shut down facet: mds1 facet_host: oleg248-server facet_failover_host: oleg248-server 1 600 1.16 MB/sec warmup 18 sec latency 2855.034 ms 1 600 1.10 MB/sec warmup 19 sec latency 3856.375 ms 1 600 0.00 MB/sec execute 1 sec latency 5858.257 ms 1 600 0.00 MB/sec execute 2 sec latency 6858.877 ms 1 600 0.00 MB/sec execute 3 sec latency 7859.272 ms 1 600 0.00 MB/sec execute 4 sec latency 8859.539 ms 1 600 0.00 MB/sec execute 5 sec latency 9859.827 ms 1 600 0.00 MB/sec execute 6 sec latency 10860.286 ms 1 600 0.00 MB/sec execute 7 sec latency 11865.045 ms Failover mds1 to oleg248-server 1 600 0.00 MB/sec execute 8 sec latency 12865.354 ms mount facets: mds1 1 600 0.00 MB/sec execute 9 sec latency 13866.425 ms 1 600 0.00 MB/sec execute 10 sec latency 14867.963 ms 1 600 0.00 MB/sec execute 11 sec latency 15868.280 ms 1 600 0.00 MB/sec execute 12 sec latency 16868.720 ms 1 600 0.00 MB/sec execute 13 sec latency 17869.876 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 600 0.00 MB/sec execute 14 sec latency 18872.175 ms 1 600 0.00 MB/sec execute 15 sec latency 19872.464 ms 1 600 0.00 MB/sec execute 16 sec latency 20878.766 ms 1 600 0.00 MB/sec execute 17 sec latency 21879.029 ms 1 600 0.00 MB/sec execute 18 sec latency 22879.434 ms 1 600 0.00 MB/sec execute 19 sec latency 23880.339 ms 1 600 0.00 MB/sec execute 20 sec latency 24880.639 ms 1 600 0.00 MB/sec execute 21 sec latency 25881.292 ms 1 600 0.00 MB/sec execute 22 sec latency 26882.314 ms 1 600 0.00 MB/sec execute 23 sec latency 27884.139 ms 1 600 0.00 MB/sec execute 24 sec latency 28884.956 ms 1 600 0.00 MB/sec execute 25 sec latency 29893.126 ms 1 600 0.00 MB/sec execute 26 sec latency 30895.978 ms 1 600 0.00 MB/sec execute 27 sec latency 31896.471 ms 1 600 0.00 MB/sec execute 28 sec latency 32898.712 ms oleg248-server: oleg248-server.virtnet: executing set_default_debug -1 all 1 600 0.00 MB/sec execute 29 sec latency 33898.989 ms 1 600 0.00 MB/sec execute 30 sec latency 34899.201 ms pdsh@oleg248-client: oleg248-server: ssh exited with exit code 1 1 600 0.00 MB/sec execute 31 sec latency 35899.683 ms Started lustre-MDT0000 16:14:46 (1788466486) targets are mounted 16:14:46 (1788466486) facet_failover done 1 600 0.00 MB/sec execute 32 sec latency 36899.954 ms 1 600 0.00 MB/sec execute 33 sec latency 37901.597 ms 1 600 0.00 MB/sec execute 34 sec latency 38903.347 ms 1 600 0.00 MB/sec execute 35 sec latency 39905.865 ms 1 600 0.00 MB/sec execute 36 sec latency 40906.093 ms 1 600 0.00 MB/sec execute 37 sec latency 41906.311 ms 1 642 0.00 MB/sec execute 38 sec latency 42050.523 ms 1 671 0.01 MB/sec execute 39 sec latency 237.319 ms 1 692 0.01 MB/sec execute 40 sec latency 166.375 ms 1 712 0.01 MB/sec execute 41 sec latency 148.620 ms 1 733 0.01 MB/sec execute 42 sec latency 190.727 ms oleg248-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 765 0.01 MB/sec execute 43 sec latency 218.920 ms 1 786 0.01 MB/sec execute 44 sec latency 174.645 ms 1 798 0.01 MB/sec execute 45 sec latency 382.376 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 821 0.01 MB/sec execute 46 sec latency 179.300 ms 1 861 0.01 MB/sec execute 47 sec latency 137.771 ms 1 882 0.01 MB/sec execute 48 sec latency 312.303 ms 1 907 0.02 MB/sec execute 49 sec latency 197.199 ms 1 921 0.02 MB/sec execute 50 sec latency 450.811 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 976 0.02 MB/sec execute 51 sec latency 103.132 ms 1 1000 0.02 MB/sec execute 52 sec latency 213.469 ms 1 1058 0.04 MB/sec execute 53 sec latency 206.408 ms 1 1126 0.04 MB/sec execute 54 sec latency 77.042 ms 1 1160 0.04 MB/sec execute 55 sec latency 116.179 ms 1 1198 0.04 MB/sec execute 56 sec latency 116.471 ms 1 1223 0.04 MB/sec execute 57 sec latency 236.264 ms 1 1244 0.04 MB/sec execute 58 sec latency 137.936 ms 1 1274 0.04 MB/sec execute 59 sec latency 155.260 ms 1 1392 0.08 MB/sec execute 60 sec latency 136.796 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Thu Sep 3 16:15:15 EDT 2026 with return code 0 1 1419 0.08 MB/sec execute 61 sec latency 139.244 ms 47188 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 47188 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished