== replay-dual test 26: dbench and tar with mds failover ========================================================== 03:21:55 (1786951315) Starting client oleg308-client.virtnet: -o user_xattr,flock 192.168.203.108@tcp:/lustre /mnt/lustre Started clients oleg308-client.virtnet: 192.168.203.108@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 65654 Started dbench loop with 65655 striped dir -i0 -c2 -H crush2 /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H crush /mnt/lustre2/d26.replay-dual/run_dbench 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 3588900 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1544 3605476 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 3108 7194376 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 Aug 17 03:22:01 EDT 2026 waiting for dbench pid 65733 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 0 11 0.00 MB/sec warmup 1 sec latency 5.621 ms 1 72 1.57 MB/sec warmup 2 sec latency 125.651 ms 1 123 1.83 MB/sec warmup 3 sec latency 177.415 ms 1 157 1.63 MB/sec warmup 4 sec latency 175.105 ms 1 189 1.51 MB/sec warmup 5 sec latency 330.694 ms 1 216 1.39 MB/sec warmup 6 sec latency 173.755 ms 1 256 1.38 MB/sec warmup 7 sec latency 128.174 ms test_26 fail mds1 1 times 1 297 1.37 MB/sec warmup 8 sec latency 85.838 ms 1 329 1.32 MB/sec warmup 9 sec latency 187.553 ms Failing mds1 on oleg308-server 1 364 1.30 MB/sec warmup 10 sec latency 181.035 ms Stopping /mnt/lustre-mds1 (opts:) on oleg308-server 1 405 1.30 MB/sec warmup 11 sec latency 110.339 ms 1 428 1.26 MB/sec warmup 12 sec latency 333.102 ms 1 428 1.16 MB/sec warmup 13 sec latency 1333.391 ms 1 428 1.08 MB/sec warmup 14 sec latency 2335.410 ms 1 428 1.01 MB/sec warmup 15 sec latency 3335.554 ms 1 428 0.94 MB/sec warmup 16 sec latency 4335.785 ms 1 428 0.89 MB/sec warmup 17 sec latency 5337.343 ms 03:22:19 (1786951339) shut down 1 428 0.84 MB/sec warmup 18 sec latency 6338.787 ms facet: mds1 facet_host: oleg308-server facet_failover_host: oleg308-server 1 428 0.79 MB/sec warmup 19 sec latency 7338.976 ms 1 428 0.00 MB/sec execute 1 sec latency 9341.801 ms 1 428 0.00 MB/sec execute 2 sec latency 10342.006 ms 1 428 0.00 MB/sec execute 3 sec latency 11342.212 ms 1 428 0.00 MB/sec execute 4 sec latency 12343.659 ms 1 428 0.00 MB/sec execute 5 sec latency 13343.974 ms 1 428 0.00 MB/sec execute 6 sec latency 14346.649 ms 1 428 0.00 MB/sec execute 7 sec latency 15346.993 ms 1 428 0.00 MB/sec execute 8 sec latency 16347.291 ms Failover mds1 to oleg308-server mount facets: mds1 1 428 0.00 MB/sec execute 9 sec latency 17348.057 ms 1 428 0.00 MB/sec execute 10 sec latency 18349.459 ms 1 428 0.00 MB/sec execute 11 sec latency 19349.664 ms 1 428 0.00 MB/sec execute 12 sec latency 20351.020 ms 1 428 0.00 MB/sec execute 13 sec latency 21351.280 ms 1 428 0.00 MB/sec execute 14 sec latency 22353.815 ms 1 428 0.00 MB/sec execute 15 sec latency 23354.324 ms 1 428 0.00 MB/sec execute 16 sec latency 24357.940 ms 1 428 0.00 MB/sec execute 17 sec latency 25358.237 ms 1 428 0.00 MB/sec execute 18 sec latency 26359.667 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 428 0.00 MB/sec execute 19 sec latency 27359.891 ms 1 428 0.00 MB/sec execute 20 sec latency 28360.247 ms 1 428 0.00 MB/sec execute 21 sec latency 29360.456 ms 1 428 0.00 MB/sec execute 22 sec latency 30360.941 ms 1 428 0.00 MB/sec execute 23 sec latency 31362.983 ms 1 428 0.00 MB/sec execute 24 sec latency 32363.735 ms 1 428 0.00 MB/sec execute 25 sec latency 33365.170 ms 1 428 0.00 MB/sec execute 26 sec latency 34365.442 ms 1 428 0.00 MB/sec execute 27 sec latency 35365.727 ms 1 428 0.00 MB/sec execute 28 sec latency 36367.037 ms 1 428 0.00 MB/sec execute 29 sec latency 37367.259 ms 1 428 0.00 MB/sec execute 30 sec latency 38367.454 ms oleg308-server: oleg308-server.virtnet: executing set_default_debug -1 all 1 428 0.00 MB/sec execute 31 sec latency 39368.726 ms 1 428 0.00 MB/sec execute 32 sec latency 40369.007 ms pdsh@oleg308-client: oleg308-server: ssh exited with exit code 1 1 445 0.02 MB/sec execute 33 sec latency 40682.213 ms Started lustre-MDT0000 03:22:55 (1786951375) targets are mounted 03:22:55 (1786951375) facet_failover done 1 476 0.05 MB/sec execute 34 sec latency 160.301 ms 1 504 0.07 MB/sec execute 35 sec latency 210.617 ms 1 540 0.11 MB/sec execute 36 sec latency 142.018 ms 1 555 0.11 MB/sec execute 37 sec latency 671.743 ms 1 610 0.15 MB/sec execute 38 sec latency 110.391 ms 1 652 0.15 MB/sec execute 39 sec latency 125.078 ms 1 676 0.15 MB/sec execute 40 sec latency 170.138 ms 1 699 0.15 MB/sec execute 41 sec latency 224.670 ms 1 721 0.15 MB/sec execute 42 sec latency 242.613 ms oleg308-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 749 0.14 MB/sec execute 43 sec latency 156.753 ms 1 773 0.14 MB/sec execute 44 sec latency 250.204 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 803 0.14 MB/sec execute 45 sec latency 175.617 ms 1 821 0.14 MB/sec execute 46 sec latency 176.747 ms 1 869 0.14 MB/sec execute 47 sec latency 133.687 ms 1 888 0.14 MB/sec execute 48 sec latency 166.106 ms 1 912 0.14 MB/sec execute 49 sec latency 186.193 ms 1 943 0.13 MB/sec execute 50 sec latency 109.816 ms 1 969 0.13 MB/sec execute 51 sec latency 138.671 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2120 1269184 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1932 1269372 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 42008 3561080 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 12840 3593136 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 54848 7154216 1% /mnt/lustre 1 986 0.13 MB/sec execute 52 sec latency 157.832 ms 1 1028 0.15 MB/sec execute 53 sec latency 195.714 ms 1 1060 0.14 MB/sec execute 54 sec latency 130.665 ms 1 1084 0.14 MB/sec execute 55 sec latency 262.076 ms 1 1126 0.14 MB/sec execute 56 sec latency 115.514 ms 1 1145 0.14 MB/sec execute 57 sec latency 153.365 ms 1 1172 0.14 MB/sec execute 58 sec latency 158.096 ms 1 1172 0.13 MB/sec execute 59 sec latency 1117.162 ms 1 1193 0.13 MB/sec execute 60 sec latency 1311.073 ms 1 1224 0.13 MB/sec execute 61 sec latency 151.056 ms 1 1251 0.13 MB/sec execute 62 sec latency 112.032 ms 1 1318 0.14 MB/sec execute 63 sec latency 135.439 ms 1 1401 0.17 MB/sec execute 64 sec latency 120.368 ms test_26 fail mds2 2 times 1 1422 0.17 MB/sec execute 65 sec latency 237.676 ms 1 1446 0.16 MB/sec execute 66 sec latency 431.415 ms 1 1468 0.16 MB/sec execute 67 sec latency 159.708 ms Failing mds2 on oleg308-server 1 1499 0.16 MB/sec execute 68 sec latency 165.641 ms 1 1520 0.16 MB/sec execute 69 sec latency 146.440 ms Stopping /mnt/lustre-mds2 (opts:) on oleg308-server 1 1560 0.16 MB/sec execute 70 sec latency 159.358 ms 1 1574 0.15 MB/sec execute 71 sec latency 119.671 ms 1 1605 0.15 MB/sec execute 72 sec latency 212.776 ms 1 1643 0.15 MB/sec execute 73 sec latency 170.814 ms 1 1676 0.15 MB/sec execute 74 sec latency 124.152 ms 03:23:36 (1786951416) shut down facet: mds2 facet_host: oleg308-server facet_failover_host: oleg308-server 1 1698 0.15 MB/sec execute 75 sec latency 167.909 ms 1 1743 0.15 MB/sec execute 76 sec latency 128.377 ms 1 1806 0.15 MB/sec execute 77 sec latency 63.966 ms 1 1849 0.14 MB/sec execute 78 sec latency 119.038 ms 1 1909 0.14 MB/sec execute 79 sec latency 101.100 ms 1 1995 0.14 MB/sec execute 80 sec latency 78.670 ms 1 2040 0.14 MB/sec execute 81 sec latency 131.436 ms 1 2108 0.14 MB/sec execute 82 sec latency 101.375 ms 1 2158 0.14 MB/sec execute 83 sec latency 88.629 ms 1 2168 0.14 MB/sec execute 84 sec latency 482.729 ms Failover mds2 to oleg308-server 1 2187 0.14 MB/sec execute 85 sec latency 977.081 ms mount facets: mds2 1 2193 0.14 MB/sec execute 86 sec latency 841.736 ms 1 2206 0.13 MB/sec execute 87 sec latency 1174.248 ms 1 2226 0.13 MB/sec execute 88 sec latency 605.239 ms 1 2259 0.13 MB/sec execute 89 sec latency 355.987 ms 1 2259 0.13 MB/sec execute 90 sec latency 1359.802 ms 1 2259 0.13 MB/sec execute 91 sec latency 2361.226 ms 1 2259 0.13 MB/sec execute 92 sec latency 3375.937 ms 1 2259 0.13 MB/sec execute 93 sec latency 4376.909 ms 1 2259 0.12 MB/sec execute 94 sec latency 5377.095 ms 1 2259 0.12 MB/sec execute 95 sec latency 6431.592 ms 1 2259 0.12 MB/sec execute 96 sec latency 7434.674 ms 1 2259 0.12 MB/sec execute 97 sec latency 8435.003 ms 1 2259 0.12 MB/sec execute 98 sec latency 9437.363 ms 1 2259 0.12 MB/sec execute 99 sec latency 10437.559 ms 1 cleanup 100 sec Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 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 oleg308-server: oleg308-server.virtnet: executing set_default_debug -1 all 1 cleanup 109 sec pdsh@oleg308-client: oleg308-server: ssh exited with exit code 1 1 cleanup 110 sec Started lustre-MDT0001 03:24:12 (1786951452) targets are mounted 03:24:12 (1786951452) facet_failover done 1 cleanup 111 sec 1 cleanup 112 sec 1 cleanup 113 sec 1 cleanup 114 sec 0 cleanup 115 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 329 146.340 21942.902 Close 286 157.441 40682.181 Rename 11 125.903 186.606 Unlink 30 33.709 81.588 Qpathinfo 295 24.385 1174.226 Qfileinfo 78 3.388 21.253 Qfsinfo 33 5.619 32.484 Sfileinfo 34 89.706 170.121 Find 92 18.164 284.490 WriteX 266 22.349 605.226 ReadX 348 3.905 112.382 Flush 30 60.212 166.080 Throughput 0.11752 MB/sec 1 clients 1 procs max_latency=40682.213 ms stopping dbench on /mnt/lustre at Mon Aug 17 03:24:16 EDT 2026 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H crush2 /mnt/lustre2/d26.replay-dual/run_dbench oleg308-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1475 0 mdc.lustre-MDT0001-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 Mon Aug 17 03:24:24 EDT 2026 waiting for dbench pid 67808 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 0 10 0.00 MB/sec warmup 1 sec latency 32.691 ms 1 71 1.57 MB/sec warmup 2 sec latency 94.813 ms 1 121 1.83 MB/sec warmup 3 sec latency 136.443 ms 1 156 1.63 MB/sec warmup 4 sec latency 174.165 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2368 1268936 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2140 1269164 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 35720 3569740 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 10916 3595232 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 46636 7164972 1% /mnt/lustre 1 184 1.48 MB/sec warmup 5 sec latency 147.162 ms 1 200 1.31 MB/sec warmup 6 sec latency 458.900 ms 1 239 1.30 MB/sec warmup 7 sec latency 182.283 ms 1 271 1.27 MB/sec warmup 8 sec latency 132.677 ms 1 305 1.25 MB/sec warmup 9 sec latency 115.493 ms 1 339 1.23 MB/sec warmup 10 sec latency 166.636 ms 1 339 1.11 MB/sec warmup 11 sec latency 1131.119 ms 1 365 1.09 MB/sec warmup 12 sec latency 1174.640 ms 1 404 1.10 MB/sec warmup 13 sec latency 131.529 ms 1 445 1.12 MB/sec warmup 14 sec latency 127.499 ms test_26 fail mds1 3 times 1 480 1.11 MB/sec warmup 15 sec latency 130.482 ms 1 503 1.09 MB/sec warmup 16 sec latency 169.446 ms Failing mds1 on oleg308-server 1 522 1.06 MB/sec warmup 17 sec latency 217.789 ms 1 603 1.16 MB/sec warmup 18 sec latency 218.967 ms Stopping /mnt/lustre-mds1 (opts:) on oleg308-server 1 649 1.11 MB/sec warmup 19 sec latency 163.508 ms 1 674 0.00 MB/sec execute 1 sec latency 1122.952 ms 1 674 0.00 MB/sec execute 2 sec latency 2123.207 ms 03:24:47 (1786951487) shut down facet: mds1 facet_host: oleg308-server facet_failover_host: oleg308-server 1 674 0.00 MB/sec execute 3 sec latency 3123.466 ms 1 674 0.00 MB/sec execute 4 sec latency 4126.712 ms 1 674 0.00 MB/sec execute 5 sec latency 5127.772 ms 1 674 0.00 MB/sec execute 6 sec latency 6128.776 ms 1 674 0.00 MB/sec execute 7 sec latency 7131.057 ms 1 674 0.00 MB/sec execute 8 sec latency 8131.473 ms 1 674 0.00 MB/sec execute 9 sec latency 9131.752 ms 1 674 0.00 MB/sec execute 10 sec latency 10131.913 ms 1 674 0.00 MB/sec execute 11 sec latency 11132.484 ms 1 674 0.00 MB/sec execute 12 sec latency 12135.011 ms 1 674 0.00 MB/sec execute 13 sec latency 13137.616 ms Failover mds1 to oleg308-server mount facets: mds1 1 674 0.00 MB/sec execute 14 sec latency 14138.325 ms 1 674 0.00 MB/sec execute 15 sec latency 15139.456 ms 1 674 0.00 MB/sec execute 16 sec latency 16139.729 ms 1 674 0.00 MB/sec execute 17 sec latency 17140.060 ms 1 674 0.00 MB/sec execute 18 sec latency 18140.558 ms 1 674 0.00 MB/sec execute 19 sec latency 19140.970 ms 1 674 0.00 MB/sec execute 20 sec latency 20141.252 ms 1 674 0.00 MB/sec execute 21 sec latency 21141.753 ms 1 674 0.00 MB/sec execute 22 sec latency 22141.927 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 674 0.00 MB/sec execute 23 sec latency 23142.111 ms 1 674 0.00 MB/sec execute 24 sec latency 24145.834 ms 1 674 0.00 MB/sec execute 25 sec latency 25146.013 ms 1 674 0.00 MB/sec execute 26 sec latency 26146.210 ms 1 674 0.00 MB/sec execute 27 sec latency 27146.476 ms 1 674 0.00 MB/sec execute 28 sec latency 28147.605 ms 1 674 0.00 MB/sec execute 29 sec latency 29147.809 ms 1 674 0.00 MB/sec execute 30 sec latency 30148.030 ms oleg308-server: oleg308-server.virtnet: executing set_default_debug -1 all 1 674 0.00 MB/sec execute 31 sec latency 31148.216 ms 1 674 0.00 MB/sec execute 32 sec latency 32148.504 ms pdsh@oleg308-client: oleg308-server: ssh exited with exit code 1 1 674 0.00 MB/sec execute 33 sec latency 33148.962 ms Started lustre-MDT0000 03:25:17 (1786951517) targets are mounted 03:25:17 (1786951517) facet_failover done 1 676 0.00 MB/sec execute 34 sec latency 34131.931 ms 1 709 0.00 MB/sec execute 35 sec latency 163.693 ms 1 735 0.00 MB/sec execute 36 sec latency 136.095 ms 1 770 0.01 MB/sec execute 37 sec latency 147.949 ms 1 801 0.01 MB/sec execute 38 sec latency 148.387 ms 1 845 0.01 MB/sec execute 39 sec latency 126.737 ms 1 873 0.01 MB/sec execute 40 sec latency 150.397 ms oleg308-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1475 0 1 884 0.01 MB/sec execute 41 sec latency 600.891 ms 1 900 0.01 MB/sec execute 42 sec latency 968.474 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 919 0.01 MB/sec execute 43 sec latency 196.697 ms 1 952 0.01 MB/sec execute 44 sec latency 159.780 ms 1 970 0.01 MB/sec execute 45 sec latency 171.106 ms 1 988 0.02 MB/sec execute 46 sec latency 171.222 ms 1 1057 0.04 MB/sec execute 47 sec latency 135.993 ms 1 1101 0.04 MB/sec execute 48 sec latency 78.977 ms 1 1138 0.04 MB/sec execute 49 sec latency 177.583 ms 1 1173 0.04 MB/sec execute 50 sec latency 177.425 ms 1 1202 0.04 MB/sec execute 51 sec latency 143.049 ms 1 1244 0.04 MB/sec execute 52 sec latency 145.293 ms 1 1280 0.04 MB/sec execute 53 sec latency 165.383 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1405 0.09 MB/sec execute 54 sec latency 81.819 ms 1 1447 0.09 MB/sec execute 55 sec latency 90.025 ms 1 1476 0.09 MB/sec execute 56 sec latency 400.375 ms 1 1504 0.09 MB/sec execute 57 sec latency 133.600 ms 1 1538 0.08 MB/sec execute 58 sec latency 131.886 ms 1 1568 0.08 MB/sec execute 59 sec latency 130.916 ms 1 1593 0.08 MB/sec execute 60 sec latency 124.297 ms 1 1625 0.08 MB/sec execute 61 sec latency 136.074 ms 1 1667 0.08 MB/sec execute 62 sec latency 128.788 ms 1 1705 0.08 MB/sec execute 63 sec latency 202.015 ms 1 1771 0.08 MB/sec execute 64 sec latency 76.748 ms 1 1819 0.08 MB/sec execute 65 sec latency 90.228 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Mon Aug 17 03:25:50 EDT 2026 with return code 0 1 1858 0.08 MB/sec execute 66 sec latency 109.995 ms 67808 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 67808 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished