== replay-dual test 26: dbench and tar with mds failover ========================================================== 15:17:19 (1780341439) Starting client oleg314-client.virtnet: -o user_xattr,flock 192.168.203.114@tcp:/lustre /mnt/lustre Started clients oleg314-client.virtnet: 192.168.203.114@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 64914 Started dbench loop with 64915 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar 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 1414116 1944 1269360 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1756 1269548 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 1564 3605456 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17928 3580768 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 19492 7186224 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 Jun 1 15:17:24 EDT 2026 waiting for dbench pid 64980 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 23 0.59 MB/sec warmup 1 sec latency 18.568 ms 1 85 1.93 MB/sec warmup 2 sec latency 128.673 ms 1 129 1.91 MB/sec warmup 3 sec latency 204.711 ms 1 163 1.68 MB/sec warmup 4 sec latency 142.632 ms 1 184 1.47 MB/sec warmup 5 sec latency 385.509 ms 1 206 1.35 MB/sec warmup 6 sec latency 424.409 ms 1 244 1.32 MB/sec warmup 7 sec latency 133.415 ms 1 289 1.34 MB/sec warmup 8 sec latency 102.907 ms test_26 fail mds1 1 times 1 316 1.27 MB/sec warmup 9 sec latency 171.287 ms 1 350 1.25 MB/sec warmup 10 sec latency 123.287 ms Failing mds1 on oleg314-server 1 389 1.25 MB/sec warmup 11 sec latency 135.256 ms Stopping /mnt/lustre-mds1 (opts:) on oleg314-server 1 429 1.26 MB/sec warmup 12 sec latency 108.553 ms 1 461 1.24 MB/sec warmup 13 sec latency 308.572 ms 1 461 1.15 MB/sec warmup 14 sec latency 1310.501 ms 1 461 1.08 MB/sec warmup 15 sec latency 2311.472 ms 15:17:40 (1780341460) shut down facet: mds1 facet_host: oleg314-server facet_failover_host: oleg314-server 1 461 1.01 MB/sec warmup 16 sec latency 3311.667 ms 1 461 0.95 MB/sec warmup 17 sec latency 4312.074 ms 1 461 0.90 MB/sec warmup 18 sec latency 5312.292 ms 1 461 0.85 MB/sec warmup 19 sec latency 6312.425 ms 1 461 0.00 MB/sec execute 1 sec latency 8312.755 ms 1 461 0.00 MB/sec execute 2 sec latency 9312.944 ms 1 461 0.00 MB/sec execute 3 sec latency 10313.906 ms 1 461 0.00 MB/sec execute 4 sec latency 11314.161 ms 1 461 0.00 MB/sec execute 5 sec latency 12314.890 ms Failover mds1 to oleg314-server mount facets: mds1 1 461 0.00 MB/sec execute 6 sec latency 13315.015 ms 1 461 0.00 MB/sec execute 7 sec latency 14315.303 ms 1 461 0.00 MB/sec execute 8 sec latency 15315.511 ms 1 461 0.00 MB/sec execute 9 sec latency 16315.754 ms 1 461 0.00 MB/sec execute 10 sec latency 17315.903 ms 1 461 0.00 MB/sec execute 11 sec latency 18316.345 ms 1 461 0.00 MB/sec execute 12 sec latency 19316.737 ms 1 461 0.00 MB/sec execute 13 sec latency 20317.731 ms 1 461 0.00 MB/sec execute 14 sec latency 21317.938 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 461 0.00 MB/sec execute 15 sec latency 22318.505 ms 1 461 0.00 MB/sec execute 16 sec latency 23321.140 ms 1 461 0.00 MB/sec execute 17 sec latency 24321.344 ms 1 461 0.00 MB/sec execute 18 sec latency 25321.618 ms 1 461 0.00 MB/sec execute 19 sec latency 26321.789 ms 1 461 0.00 MB/sec execute 20 sec latency 27322.011 ms 1 461 0.00 MB/sec execute 21 sec latency 28322.922 ms 1 461 0.00 MB/sec execute 22 sec latency 29323.171 ms 1 461 0.00 MB/sec execute 23 sec latency 30323.820 ms 1 461 0.00 MB/sec execute 24 sec latency 31324.515 ms 1 461 0.00 MB/sec execute 25 sec latency 32325.025 ms 1 461 0.00 MB/sec execute 26 sec latency 33325.334 ms 1 461 0.00 MB/sec execute 27 sec latency 34325.640 ms oleg314-server: oleg314-server.virtnet: executing set_default_debug -1 all 1 461 0.00 MB/sec execute 28 sec latency 35325.879 ms 1 461 0.00 MB/sec execute 29 sec latency 36327.172 ms pdsh@oleg314-client: oleg314-server: ssh exited with exit code 1 Started lustre-MDT0000 15:18:14 (1780341494) targets are mounted 15:18:14 (1780341494) facet_failover done 1 461 0.00 MB/sec execute 30 sec latency 37327.569 ms 1 469 0.01 MB/sec execute 31 sec latency 38139.698 ms 1 508 0.04 MB/sec execute 32 sec latency 143.949 ms 1 552 0.09 MB/sec execute 33 sec latency 170.524 ms 1 603 0.14 MB/sec execute 34 sec latency 726.798 ms oleg314-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 656 0.14 MB/sec execute 35 sec latency 101.585 ms 1 695 0.14 MB/sec execute 36 sec latency 130.989 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 726 0.14 MB/sec execute 37 sec latency 113.882 ms 1 759 0.14 MB/sec execute 38 sec latency 133.631 ms 1 789 0.14 MB/sec execute 39 sec latency 124.018 ms 1 827 0.13 MB/sec execute 40 sec latency 92.883 ms 1 876 0.13 MB/sec execute 41 sec latency 102.224 ms 1 913 0.13 MB/sec execute 42 sec latency 122.776 ms UUID 1K-blocks Used Available Use% Mounted on 1 951 0.13 MB/sec execute 43 sec latency 101.437 ms lustre-MDT0000_UUID 1414116 2056 1269248 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1860 1269444 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 9012 3595572 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 41232 3558944 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 50244 7154516 1% /mnt/lustre 1 980 0.13 MB/sec execute 44 sec latency 112.733 ms 1 1028 0.15 MB/sec execute 45 sec latency 120.767 ms 1 1082 0.15 MB/sec execute 46 sec latency 62.696 ms 1 1134 0.14 MB/sec execute 47 sec latency 98.613 ms 1 1163 0.14 MB/sec execute 48 sec latency 191.805 ms 1 1172 0.14 MB/sec execute 49 sec latency 888.432 ms 1 1198 0.14 MB/sec execute 50 sec latency 1073.252 ms 1 1231 0.14 MB/sec execute 51 sec latency 115.940 ms 1 1285 0.13 MB/sec execute 52 sec latency 92.057 ms 1 1419 0.19 MB/sec execute 53 sec latency 107.242 ms test_26 fail mds2 2 times 1 1459 0.18 MB/sec execute 54 sec latency 124.946 ms 1 1493 0.18 MB/sec execute 55 sec latency 122.531 ms Failing mds2 on oleg314-server 1 1532 0.18 MB/sec execute 56 sec latency 134.004 ms Stopping /mnt/lustre-mds2 (opts:) on oleg314-server 1 1568 0.17 MB/sec execute 57 sec latency 99.991 ms 1 1608 0.17 MB/sec execute 58 sec latency 80.583 ms 1 1662 0.17 MB/sec execute 59 sec latency 81.451 ms 15:18:44 (1780341524) shut down facet: mds2 facet_host: oleg314-server facet_failover_host: oleg314-server 1 1731 0.17 MB/sec execute 60 sec latency 98.908 ms 1 1825 0.17 MB/sec execute 61 sec latency 79.953 ms 1 1864 0.16 MB/sec execute 62 sec latency 109.821 ms 1 1978 0.16 MB/sec execute 63 sec latency 52.451 ms 1 2071 0.16 MB/sec execute 64 sec latency 81.766 ms 1 2152 0.16 MB/sec execute 65 sec latency 89.716 ms 1 2206 0.16 MB/sec execute 66 sec latency 82.285 ms 1 2259 0.16 MB/sec execute 67 sec latency 634.540 ms 1 2259 0.16 MB/sec execute 68 sec latency 1639.209 ms 1 2259 0.15 MB/sec execute 69 sec latency 2639.392 ms Failover mds2 to oleg314-server mount facets: mds2 1 2259 0.15 MB/sec execute 70 sec latency 3639.765 ms 1 2259 0.15 MB/sec execute 71 sec latency 4640.596 ms 1 2259 0.15 MB/sec execute 72 sec latency 5640.778 ms 1 2259 0.15 MB/sec execute 73 sec latency 6641.027 ms 1 2259 0.14 MB/sec execute 74 sec latency 7644.340 ms 1 2259 0.14 MB/sec execute 75 sec latency 8645.263 ms 1 2259 0.14 MB/sec execute 76 sec latency 9645.431 ms 1 2259 0.14 MB/sec execute 77 sec latency 10645.632 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2259 0.14 MB/sec execute 78 sec latency 11645.910 ms 1 2259 0.13 MB/sec execute 79 sec latency 12646.108 ms 1 2259 0.13 MB/sec execute 80 sec latency 13646.690 ms 1 2259 0.13 MB/sec execute 81 sec latency 14646.979 ms 1 2259 0.13 MB/sec execute 82 sec latency 15647.218 ms oleg314-server: oleg314-server.virtnet: executing set_default_debug -1 all 1 2259 0.13 MB/sec execute 83 sec latency 16647.549 ms pdsh@oleg314-client: oleg314-server: ssh exited with exit code 1 Started lustre-MDT0001 1 2259 0.13 MB/sec execute 84 sec latency 17647.661 ms 15:19:09 (1780341549) targets are mounted 15:19:09 (1780341549) facet_failover done 1 2259 0.12 MB/sec execute 85 sec latency 18647.840 ms 1 2305 0.13 MB/sec execute 86 sec latency 19006.707 ms 1 2359 0.13 MB/sec execute 87 sec latency 79.425 ms 1 2400 0.13 MB/sec execute 88 sec latency 109.666 ms oleg314-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 2439 0.13 MB/sec execute 89 sec latency 98.289 ms 1 2473 0.14 MB/sec execute 90 sec latency 101.534 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2554 0.14 MB/sec execute 91 sec latency 101.685 ms 1 2594 0.14 MB/sec execute 92 sec latency 91.073 ms 1 2752 0.17 MB/sec execute 93 sec latency 95.977 ms 1 2877 0.17 MB/sec execute 94 sec latency 123.174 ms 1 2932 0.18 MB/sec execute 95 sec latency 72.038 ms 1 3010 0.18 MB/sec execute 96 sec latency 76.464 ms 1 3197 0.19 MB/sec execute 97 sec latency 101.185 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2336 1268968 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2132 1269172 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 11572 3594608 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 56984 3547556 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 68556 7142164 1% /mnt/lustre 1 3277 0.20 MB/sec execute 98 sec latency 128.410 ms 1 3354 0.19 MB/sec execute 99 sec latency 67.179 ms 1 cleanup 100 sec 1 cleanup 101 sec 1 cleanup 102 sec 1 cleanup 103 sec 1 cleanup 104 sec 0 cleanup 104 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 439 178.570 38139.677 Close 364 10.795 43.440 Rename 22 85.519 191.787 Unlink 53 25.547 56.485 Qpathinfo 419 16.436 113.687 Qfileinfo 114 2.077 11.768 Qfsinfo 78 3.313 27.241 Sfileinfo 50 61.721 119.953 Find 185 10.707 101.572 WriteX 365 11.886 86.245 ReadX 894 1.147 101.520 LockX 2 9.962 11.985 UnlockX 2 7.122 8.546 Flush 43 51.148 130.973 Throughput 0.193776 MB/sec 1 clients 1 procs max_latency=38139.698 ms stopping dbench on /mnt/lustre at Mon Jun 1 15:19:29 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished test_26 fail mds1 3 times striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench Failing mds1 on oleg314-server Stopping /mnt/lustre-mds1 (opts:) on oleg314-server looking for dbench program /usr/bin/dbench found dbench client file /usr/share/dbench/client.txt 15:19:36 (1780341576) shut down facet: mds1 facet_host: oleg314-server facet_failover_host: oleg314-server Failover mds1 to oleg314-server mount facets: mds1 Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 oleg314-server: oleg314-server.virtnet: executing set_default_debug -1 all pdsh@oleg314-client: oleg314-server: ssh exited with exit code 1 Started lustre-MDT0000 15:20:01 (1780341601) targets are mounted 15:20:01 (1780341601) facet_failover done '/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 Jun 1 15:20:05 EDT 2026 waiting for dbench pid 67721 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 oleg314-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 31 1.05 MB/sec warmup 1 sec latency 20.966 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 92 2.10 MB/sec warmup 2 sec latency 114.037 ms 1 139 2.00 MB/sec warmup 3 sec latency 122.082 ms 1 184 1.83 MB/sec warmup 4 sec latency 138.963 ms 1 223 1.72 MB/sec warmup 5 sec latency 320.927 ms 1 283 1.75 MB/sec warmup 6 sec latency 73.132 ms 1 334 1.71 MB/sec warmup 7 sec latency 99.197 ms 1 381 1.69 MB/sec warmup 8 sec latency 111.288 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2668 1268636 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2404 1268900 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 31824 3569232 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 20920 3585872 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 52744 7155104 1% /mnt/lustre 1 422 1.65 MB/sec warmup 9 sec latency 111.202 ms 1 480 1.67 MB/sec warmup 10 sec latency 83.458 ms 1 528 1.66 MB/sec warmup 11 sec latency 159.278 ms 1 642 1.75 MB/sec warmup 12 sec latency 92.365 ms 1 705 1.63 MB/sec warmup 13 sec latency 81.143 ms 1 762 1.52 MB/sec warmup 14 sec latency 72.121 ms 1 818 1.43 MB/sec warmup 15 sec latency 57.001 ms test_26 fail mds2 4 times 1 882 1.35 MB/sec warmup 16 sec latency 70.822 ms 1 885 1.27 MB/sec warmup 17 sec latency 962.428 ms Failing mds2 on oleg314-server 1 914 1.21 MB/sec warmup 18 sec latency 141.525 ms Stopping /mnt/lustre-mds2 (opts:) on oleg314-server 1 967 1.15 MB/sec warmup 19 sec latency 78.850 ms 1 995 0.00 MB/sec execute 1 sec latency 999.165 ms 15:20:27 (1780341627) shut down facet: mds2 facet_host: oleg314-server facet_failover_host: oleg314-server 1 995 0.00 MB/sec execute 2 sec latency 1999.420 ms 1 995 0.00 MB/sec execute 3 sec latency 2999.598 ms 1 995 0.00 MB/sec execute 4 sec latency 4001.019 ms 1 995 0.00 MB/sec execute 5 sec latency 5003.394 ms 1 995 0.00 MB/sec execute 6 sec latency 6003.708 ms 1 995 0.00 MB/sec execute 7 sec latency 7003.908 ms 1 995 0.00 MB/sec execute 8 sec latency 8004.156 ms 1 995 0.00 MB/sec execute 9 sec latency 9004.354 ms 1 995 0.00 MB/sec execute 10 sec latency 10004.507 ms 1 995 0.00 MB/sec execute 11 sec latency 11005.394 ms Failover mds2 to oleg314-server mount facets: mds2 1 995 0.00 MB/sec execute 12 sec latency 12005.580 ms 1 995 0.00 MB/sec execute 13 sec latency 13017.415 ms 1 995 0.00 MB/sec execute 14 sec latency 14017.962 ms 1 995 0.00 MB/sec execute 15 sec latency 15018.161 ms 1 995 0.00 MB/sec execute 16 sec latency 16018.379 ms 1 995 0.00 MB/sec execute 17 sec latency 17018.557 ms 1 995 0.00 MB/sec execute 18 sec latency 18018.761 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 995 0.00 MB/sec execute 19 sec latency 19018.973 ms 1 995 0.00 MB/sec execute 20 sec latency 20019.176 ms 1 995 0.00 MB/sec execute 21 sec latency 21019.355 ms 1 995 0.00 MB/sec execute 22 sec latency 22025.773 ms 1 995 0.00 MB/sec execute 23 sec latency 23026.005 ms 1 995 0.00 MB/sec execute 24 sec latency 24026.224 ms oleg314-server: oleg314-server.virtnet: executing set_default_debug -1 all 1 995 0.00 MB/sec execute 25 sec latency 25027.368 ms pdsh@oleg314-client: oleg314-server: ssh exited with exit code 1 1 995 0.00 MB/sec execute 26 sec latency 26028.107 ms Started lustre-MDT0001 15:20:52 (1780341652) targets are mounted 15:20:52 (1780341652) facet_failover done 1 995 0.00 MB/sec execute 27 sec latency 27029.161 ms 1 1046 0.04 MB/sec execute 28 sec latency 27499.238 ms 1 1118 0.04 MB/sec execute 29 sec latency 78.011 ms 1 1164 0.04 MB/sec execute 30 sec latency 96.672 ms oleg314-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 1214 0.04 MB/sec execute 31 sec latency 88.565 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 1246 0.04 MB/sec execute 32 sec latency 120.910 ms 1 1387 0.12 MB/sec execute 33 sec latency 81.604 ms 1 1434 0.12 MB/sec execute 34 sec latency 100.580 ms 1 1492 0.12 MB/sec execute 35 sec latency 233.647 ms 1 1551 0.12 MB/sec execute 36 sec latency 120.579 ms 1 1621 0.11 MB/sec execute 37 sec latency 82.645 ms 1 1676 0.11 MB/sec execute 38 sec latency 96.711 ms 1 1757 0.11 MB/sec execute 39 sec latency 69.456 ms 1 1834 0.11 MB/sec execute 40 sec latency 61.379 ms 1 1909 0.11 MB/sec execute 41 sec latency 89.349 ms 1 2000 0.11 MB/sec execute 42 sec latency 64.609 ms 1 2083 0.11 MB/sec execute 43 sec latency 59.457 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 2156 0.11 MB/sec execute 44 sec latency 62.121 ms 1 2233 0.11 MB/sec execute 45 sec latency 69.829 ms 1 2347 0.13 MB/sec execute 46 sec latency 133.451 ms 1 2388 0.13 MB/sec execute 47 sec latency 99.805 ms 1 2439 0.13 MB/sec execute 48 sec latency 88.983 ms 1 2495 0.14 MB/sec execute 49 sec latency 92.286 ms 1 2596 0.14 MB/sec execute 50 sec latency 84.215 ms 1 2773 0.20 MB/sec execute 51 sec latency 78.655 ms tar: Error is not recoverable: exiting now 1 2926 0.22 MB/sec execute 52 sec latency 62.744 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Jun 1 15:21:18 EDT 2026 with return code 0 67721 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67721 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished