== replay-dual test 26: dbench and tar with mds failover ========================================================== 13:46:55 (1780854415) Starting client oleg250-client.virtnet: -o user_xattr,flock 192.168.202.150@tcp:/lustre /mnt/lustre Started clients oleg250-client.virtnet: 192.168.202.150@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 44556 Started dbench loop with 44557 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 26624 3730432 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 2048 3751936 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 28672 7482368 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 Sun Jun 7 13:47:00 EDT 2026 waiting for dbench pid 44610 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 32 1.04 MB/sec warmup 1 sec latency 90.253 ms 1 85 1.92 MB/sec warmup 2 sec latency 157.651 ms 1 113 1.74 MB/sec warmup 3 sec latency 370.519 ms 1 140 1.50 MB/sec warmup 4 sec latency 163.888 ms 1 181 1.46 MB/sec warmup 5 sec latency 119.092 ms 1 215 1.39 MB/sec warmup 6 sec latency 130.450 ms test_26 fail mds1 1 times 1 240 1.30 MB/sec warmup 7 sec latency 132.972 ms 1 278 1.30 MB/sec warmup 8 sec latency 131.003 ms Failing mds1 on oleg250-server 1 305 1.24 MB/sec warmup 9 sec latency 137.345 ms Stopping /mnt/lustre-mds1 (opts:) on oleg250-server 1 339 1.22 MB/sec warmup 10 sec latency 155.354 ms 1 341 1.11 MB/sec warmup 11 sec latency 940.556 ms 1 341 1.02 MB/sec warmup 12 sec latency 1940.830 ms 13:47:13 (1780854433) shut down facet: mds1 facet_host: oleg250-server facet_failover_host: oleg250-server 1 341 0.94 MB/sec warmup 13 sec latency 2941.155 ms 1 341 0.87 MB/sec warmup 14 sec latency 3941.413 ms 1 341 0.82 MB/sec warmup 15 sec latency 4941.671 ms 1 341 0.76 MB/sec warmup 16 sec latency 5944.112 ms 1 341 0.72 MB/sec warmup 17 sec latency 6944.452 ms 1 341 0.68 MB/sec warmup 18 sec latency 7945.392 ms 1 341 0.64 MB/sec warmup 19 sec latency 8945.910 ms 1 341 0.00 MB/sec execute 1 sec latency 10948.230 ms 1 341 0.00 MB/sec execute 2 sec latency 11948.522 ms 1 341 0.00 MB/sec execute 3 sec latency 12948.909 ms Failover mds1 to oleg250-server mount facets: mds1 1 341 0.00 MB/sec execute 4 sec latency 13958.776 ms 1 341 0.00 MB/sec execute 5 sec latency 14960.673 ms 1 341 0.00 MB/sec execute 6 sec latency 15961.284 ms 1 341 0.00 MB/sec execute 7 sec latency 16961.578 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 341 0.00 MB/sec execute 8 sec latency 17961.930 ms 1 341 0.00 MB/sec execute 9 sec latency 18963.525 ms 1 341 0.00 MB/sec execute 10 sec latency 19963.925 ms 1 341 0.00 MB/sec execute 11 sec latency 20966.029 ms 1 341 0.00 MB/sec execute 12 sec latency 21966.288 ms 1 341 0.00 MB/sec execute 13 sec latency 22966.513 ms 1 341 0.00 MB/sec execute 14 sec latency 23966.725 ms 1 341 0.00 MB/sec execute 15 sec latency 24967.649 ms 1 341 0.00 MB/sec execute 16 sec latency 25967.893 ms 1 341 0.00 MB/sec execute 17 sec latency 26968.232 ms 1 341 0.00 MB/sec execute 18 sec latency 27968.483 ms 1 341 0.00 MB/sec execute 19 sec latency 28969.474 ms 1 341 0.00 MB/sec execute 20 sec latency 29997.338 ms 1 341 0.00 MB/sec execute 21 sec latency 30997.549 ms 1 341 0.00 MB/sec execute 22 sec latency 31998.054 ms 1 341 0.00 MB/sec execute 23 sec latency 32999.941 ms 1 341 0.00 MB/sec execute 24 sec latency 34001.770 ms oleg250-server: oleg250-server.virtnet: executing set_default_debug -1 all 1 341 0.00 MB/sec execute 25 sec latency 35003.069 ms pdsh@oleg250-client: oleg250-server: ssh exited with exit code 1 1 341 0.00 MB/sec execute 26 sec latency 36017.946 ms Started lustre-MDT0000 13:47:47 (1780854467) targets are mounted 1 341 0.00 MB/sec execute 27 sec latency 37023.982 ms 13:47:47 (1780854467) facet_failover done 1 341 0.00 MB/sec execute 28 sec latency 38025.889 ms 1 341 0.00 MB/sec execute 29 sec latency 39026.153 ms 1 341 0.00 MB/sec execute 30 sec latency 40027.301 ms 1 341 0.00 MB/sec execute 31 sec latency 41036.786 ms 1 349 0.01 MB/sec execute 32 sec latency 41887.534 ms 1 381 0.04 MB/sec execute 33 sec latency 139.414 ms 1 408 0.06 MB/sec execute 34 sec latency 192.673 ms oleg250-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 453 0.10 MB/sec execute 35 sec latency 135.186 ms 1 489 0.13 MB/sec execute 36 sec latency 134.000 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 511 0.15 MB/sec execute 37 sec latency 162.424 ms 1 583 0.20 MB/sec execute 38 sec latency 171.977 ms 1 649 0.23 MB/sec execute 39 sec latency 113.231 ms 1 686 0.22 MB/sec execute 40 sec latency 192.249 ms 1 721 0.22 MB/sec execute 41 sec latency 95.144 ms 1 738 0.21 MB/sec execute 42 sec latency 227.257 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2304 2206208 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 37888 3700736 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 8192 3738624 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 46080 7439360 1% /mnt/lustre 1 778 0.21 MB/sec execute 43 sec latency 166.563 ms 1 801 0.21 MB/sec execute 44 sec latency 193.324 ms 1 825 0.20 MB/sec execute 45 sec latency 177.147 ms 1 873 0.20 MB/sec execute 46 sec latency 177.571 ms 1 892 0.20 MB/sec execute 47 sec latency 249.759 ms 1 916 0.20 MB/sec execute 48 sec latency 232.839 ms test_26 fail mds1 2 times 1 943 0.19 MB/sec execute 49 sec latency 143.945 ms 1 969 0.19 MB/sec execute 50 sec latency 170.543 ms 1 983 0.19 MB/sec execute 51 sec latency 419.357 ms Failing mds1 on oleg250-server 1 1026 0.20 MB/sec execute 52 sec latency 183.777 ms Stopping /mnt/lustre-mds1 (opts:) on oleg250-server 1 1062 0.20 MB/sec execute 53 sec latency 137.338 ms 1 1102 0.20 MB/sec execute 54 sec latency 122.300 ms 1 1102 0.19 MB/sec execute 55 sec latency 1122.714 ms 1 1102 0.19 MB/sec execute 56 sec latency 2132.802 ms 1 1102 0.19 MB/sec execute 57 sec latency 3134.828 ms 13:48:17 (1780854497) shut down facet: mds1 facet_host: oleg250-server facet_failover_host: oleg250-server 1 1102 0.18 MB/sec execute 58 sec latency 4135.139 ms 1 1102 0.18 MB/sec execute 59 sec latency 5136.935 ms 1 1102 0.18 MB/sec execute 60 sec latency 6137.156 ms 1 1102 0.17 MB/sec execute 61 sec latency 7137.414 ms 1 1102 0.17 MB/sec execute 62 sec latency 8138.258 ms 1 1102 0.17 MB/sec execute 63 sec latency 9145.899 ms 1 1102 0.17 MB/sec execute 64 sec latency 10146.669 ms 1 1102 0.16 MB/sec execute 65 sec latency 11146.900 ms 1 1102 0.16 MB/sec execute 66 sec latency 12147.159 ms 1 1102 0.16 MB/sec execute 67 sec latency 13147.385 ms 1 1102 0.16 MB/sec execute 68 sec latency 14185.089 ms Failover mds1 to oleg250-server mount facets: mds1 1 1102 0.15 MB/sec execute 69 sec latency 15185.261 ms 1 1102 0.15 MB/sec execute 70 sec latency 16186.249 ms 1 1102 0.15 MB/sec execute 71 sec latency 17186.474 ms 1 1102 0.15 MB/sec execute 72 sec latency 18186.925 ms 1 1102 0.15 MB/sec execute 73 sec latency 19187.132 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1102 0.14 MB/sec execute 74 sec latency 20187.583 ms 1 1102 0.14 MB/sec execute 75 sec latency 21187.824 ms 1 1102 0.14 MB/sec execute 76 sec latency 22188.037 ms 1 1102 0.14 MB/sec execute 77 sec latency 23188.248 ms 1 1102 0.14 MB/sec execute 78 sec latency 24188.909 ms 1 1102 0.13 MB/sec execute 79 sec latency 25189.269 ms 1 1102 0.13 MB/sec execute 80 sec latency 26189.461 ms 1 1102 0.13 MB/sec execute 81 sec latency 27190.978 ms 1 1102 0.13 MB/sec execute 82 sec latency 28191.325 ms 1 1102 0.13 MB/sec execute 83 sec latency 29191.562 ms 1 1102 0.13 MB/sec execute 84 sec latency 30192.041 ms 1 1102 0.13 MB/sec execute 85 sec latency 31192.689 ms 1 1102 0.12 MB/sec execute 86 sec latency 32195.498 ms 1 1102 0.12 MB/sec execute 87 sec latency 33196.542 ms oleg250-server: oleg250-server.virtnet: executing set_default_debug -1 all 1 1102 0.12 MB/sec execute 88 sec latency 34198.775 ms pdsh@oleg250-client: oleg250-server: ssh exited with exit code 1 1 1102 0.12 MB/sec execute 89 sec latency 35201.481 ms Started lustre-MDT0000 13:48:50 (1780854530) targets are mounted 13:48:50 (1780854530) facet_failover done 1 1102 0.12 MB/sec execute 90 sec latency 36206.488 ms 1 1102 0.12 MB/sec execute 91 sec latency 37206.772 ms 1 1102 0.12 MB/sec execute 92 sec latency 38207.117 ms 1 1102 0.11 MB/sec execute 93 sec latency 39207.951 ms 1 1102 0.11 MB/sec execute 94 sec latency 40208.179 ms 1 1102 0.11 MB/sec execute 95 sec latency 41210.384 ms 1 1102 0.11 MB/sec execute 96 sec latency 42210.657 ms 1 1102 0.11 MB/sec execute 97 sec latency 43210.978 ms 1 1102 0.11 MB/sec execute 98 sec latency 44212.562 ms 1 1102 0.11 MB/sec execute 99 sec latency 45212.848 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 1 cleanup 107 sec 1 cleanup 108 sec 1 cleanup 109 sec 1 cleanup 110 sec oleg250-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 0 cleanup 111 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 106 484.955 41887.516 Close 97 15.191 44.433 Rename 5 126.042 166.275 Unlink 12 34.129 73.825 Qpathinfo 50 1085.646 52892.841 Qfileinfo 48 2.464 9.982 Qfsinfo 24 4.753 20.930 Sfileinfo 20 61.158 95.896 Find 31 8.140 62.997 WriteX 238 13.704 79.494 ReadX 107 3.804 69.460 Flush 24 131.367 419.339 Throughput 0.107643 MB/sec 1 clients 1 procs max_latency=45212.848 ms stopping dbench on /mnt/lustre at Sun Jun 7 13:49:11 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 Sun Jun 7 13:49:17 EDT 2026 waiting for dbench pid 46560 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 43 1.64 MB/sec warmup 1 sec latency 93.164 ms 1 95 2.13 MB/sec warmup 2 sec latency 126.888 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 2560 2205952 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 40960 3704832 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 26624 3724288 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 67584 7429120 1% /mnt/lustre 1 136 2.01 MB/sec warmup 3 sec latency 157.412 ms 1 163 1.68 MB/sec warmup 4 sec latency 170.093 ms 1 197 1.57 MB/sec warmup 5 sec latency 143.993 ms 1 231 1.48 MB/sec warmup 6 sec latency 167.096 ms 1 271 1.45 MB/sec warmup 7 sec latency 113.888 ms test_26 fail mds1 3 times 1 306 1.40 MB/sec warmup 8 sec latency 133.191 ms 1 341 1.36 MB/sec warmup 9 sec latency 130.588 ms Failing mds1 on oleg250-server 1 374 1.33 MB/sec warmup 10 sec latency 142.524 ms Stopping /mnt/lustre-mds1 (opts:) on oleg250-server 1 421 1.35 MB/sec warmup 11 sec latency 125.329 ms 1 437 1.28 MB/sec warmup 12 sec latency 732.007 ms 1 437 1.18 MB/sec warmup 13 sec latency 1740.183 ms 13:49:30 (1780854570) shut down facet: mds1 facet_host: oleg250-server facet_failover_host: oleg250-server 1 437 1.10 MB/sec warmup 14 sec latency 2743.590 ms 1 437 1.02 MB/sec warmup 15 sec latency 3743.861 ms 1 437 0.96 MB/sec warmup 16 sec latency 4745.689 ms 1 437 0.90 MB/sec warmup 17 sec latency 5746.153 ms 1 437 0.85 MB/sec warmup 18 sec latency 6746.687 ms 1 437 0.81 MB/sec warmup 19 sec latency 7750.699 ms 1 437 0.00 MB/sec execute 1 sec latency 9755.899 ms 1 437 0.00 MB/sec execute 2 sec latency 10757.123 ms 1 437 0.00 MB/sec execute 3 sec latency 11758.862 ms Failover mds1 to oleg250-server 1 437 0.00 MB/sec execute 4 sec latency 12759.094 ms mount facets: mds1 1 437 0.00 MB/sec execute 5 sec latency 13761.295 ms 1 437 0.00 MB/sec execute 6 sec latency 14765.196 ms 1 437 0.00 MB/sec execute 7 sec latency 15766.601 ms Start mds1: mount -t lustre -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 437 0.00 MB/sec execute 8 sec latency 16766.853 ms 1 437 0.00 MB/sec execute 9 sec latency 17767.649 ms 1 437 0.00 MB/sec execute 10 sec latency 18768.005 ms 1 437 0.00 MB/sec execute 11 sec latency 19768.798 ms 1 437 0.00 MB/sec execute 12 sec latency 20769.052 ms 1 437 0.00 MB/sec execute 13 sec latency 21770.486 ms 1 437 0.00 MB/sec execute 14 sec latency 22770.790 ms 1 437 0.00 MB/sec execute 15 sec latency 23771.049 ms 1 437 0.00 MB/sec execute 16 sec latency 24775.039 ms 1 437 0.00 MB/sec execute 17 sec latency 25777.686 ms 1 437 0.00 MB/sec execute 18 sec latency 26778.045 ms 1 437 0.00 MB/sec execute 19 sec latency 27778.251 ms 1 437 0.00 MB/sec execute 20 sec latency 28778.493 ms 1 437 0.00 MB/sec execute 21 sec latency 29779.053 ms 1 437 0.00 MB/sec execute 22 sec latency 30781.737 ms 1 437 0.00 MB/sec execute 23 sec latency 31782.078 ms oleg250-server: oleg250-server.virtnet: executing set_default_debug -1 all 1 437 0.00 MB/sec execute 24 sec latency 32783.053 ms pdsh@oleg250-client: oleg250-server: ssh exited with exit code 1 1 437 0.00 MB/sec execute 25 sec latency 33786.164 ms Started lustre-MDT0000 13:50:02 (1780854602) targets are mounted 13:50:02 (1780854602) facet_failover done 1 437 0.00 MB/sec execute 26 sec latency 34787.402 ms 1 437 0.00 MB/sec execute 27 sec latency 35792.385 ms 1 437 0.00 MB/sec execute 28 sec latency 36793.607 ms 1 437 0.00 MB/sec execute 29 sec latency 37793.838 ms 1 437 0.00 MB/sec execute 30 sec latency 38795.969 ms 1 437 0.00 MB/sec execute 31 sec latency 39799.364 ms 1 465 0.03 MB/sec execute 32 sec latency 40072.610 ms 1 501 0.06 MB/sec execute 33 sec latency 126.115 ms oleg250-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 532 0.09 MB/sec execute 34 sec latency 153.974 ms 1 606 0.16 MB/sec execute 35 sec latency 162.416 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 655 0.16 MB/sec execute 36 sec latency 129.153 ms 1 678 0.16 MB/sec execute 37 sec latency 159.382 ms 1 713 0.15 MB/sec execute 38 sec latency 122.880 ms 1 735 0.15 MB/sec execute 39 sec latency 221.983 ms 1 769 0.15 MB/sec execute 40 sec latency 145.487 ms 1 798 0.15 MB/sec execute 41 sec latency 237.634 ms 1 825 0.15 MB/sec execute 42 sec latency 118.632 ms 1 873 0.15 MB/sec execute 43 sec latency 305.478 ms 1 898 0.14 MB/sec execute 44 sec latency 347.506 ms 1 919 0.14 MB/sec execute 45 sec latency 203.578 ms 1 963 0.14 MB/sec execute 46 sec latency 119.242 ms 1 985 0.14 MB/sec execute 47 sec latency 280.980 ms 1 1050 0.16 MB/sec execute 48 sec latency 104.267 ms 1 1095 0.15 MB/sec execute 49 sec latency 104.304 ms 1 1145 0.15 MB/sec execute 50 sec latency 99.736 ms 1 1192 0.15 MB/sec execute 51 sec latency 109.985 ms 1 1244 0.15 MB/sec execute 52 sec latency 62.052 ms 1 1296 0.15 MB/sec execute 53 sec latency 118.504 ms 1 1410 0.20 MB/sec execute 54 sec latency 99.429 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Sun Jun 7 13:50:32 EDT 2026 with return code 0 1 1481 0.19 MB/sec execute 55 sec latency 74.411 ms 46560 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 46560 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished