== replay-dual test 26: dbench and tar with mds failover ========================================================== 14:50:36 (1776192636) Starting client oleg311-client.virtnet: -o user_xattr,flock oleg311-server@tcp:/lustre /mnt/lustre Started clients oleg311-client.virtnet: 192.168.203.111@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,encrypt) Started tar loop with pid 66869 Started dbench loop with 66871 striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar striped dir -i0 -c2 -H all_char /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 2016 1285672 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 1836 1285852 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 9600 3580856 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1388 3605632 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 10988 7186488 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 Tue Apr 14 14:50:42 EDT 2026 waiting for dbench pid 66943 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 30 1.05 MB/sec warmup 1 sec latency 23.114 ms 1 91 2.10 MB/sec warmup 2 sec latency 119.500 ms 1 126 1.88 MB/sec warmup 3 sec latency 181.782 ms 1 157 1.63 MB/sec warmup 4 sec latency 190.417 ms 1 195 1.55 MB/sec warmup 5 sec latency 139.266 ms 1 223 1.43 MB/sec warmup 6 sec latency 155.723 ms 1 256 1.38 MB/sec warmup 7 sec latency 143.499 ms test_26 fail mds1 1 times 1 290 1.33 MB/sec warmup 8 sec latency 145.887 ms 1 316 1.27 MB/sec warmup 9 sec latency 183.607 ms 1 342 1.22 MB/sec warmup 10 sec latency 225.162 ms Failing mds1 on oleg311-server 1 371 1.20 MB/sec warmup 11 sec latency 178.841 ms Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 396 1.17 MB/sec warmup 12 sec latency 214.872 ms 1 429 1.16 MB/sec warmup 13 sec latency 152.032 ms 1 482 1.20 MB/sec warmup 14 sec latency 145.054 ms 1 501 1.16 MB/sec warmup 15 sec latency 562.105 ms 1 501 1.09 MB/sec warmup 16 sec latency 1562.488 ms 1 501 1.03 MB/sec warmup 17 sec latency 2562.682 ms 1 501 0.97 MB/sec warmup 18 sec latency 3562.899 ms 1 501 0.92 MB/sec warmup 19 sec latency 4563.758 ms reboot facets: mds1 1 501 0.00 MB/sec execute 1 sec latency 6568.810 ms 1 501 0.00 MB/sec execute 2 sec latency 7570.302 ms 1 501 0.00 MB/sec execute 3 sec latency 8570.751 ms 1 501 0.00 MB/sec execute 4 sec latency 9572.311 ms 1 501 0.00 MB/sec execute 5 sec latency 10572.661 ms 1 501 0.00 MB/sec execute 6 sec latency 11572.992 ms 1 501 0.00 MB/sec execute 7 sec latency 12573.269 ms 1 501 0.00 MB/sec execute 8 sec latency 13573.552 ms 1 501 0.00 MB/sec execute 9 sec latency 14573.871 ms 1 501 0.00 MB/sec execute 10 sec latency 15582.709 ms Failover mds1 to oleg311-server 1 501 0.00 MB/sec execute 11 sec latency 16582.871 ms 1 501 0.00 MB/sec execute 12 sec latency 17583.097 ms 1 501 0.00 MB/sec execute 13 sec latency 18583.359 ms mount facets: mds1 1 501 0.00 MB/sec execute 14 sec latency 19584.161 ms 1 501 0.00 MB/sec execute 15 sec latency 20584.579 ms 1 501 0.00 MB/sec execute 16 sec latency 21584.736 ms 1 501 0.00 MB/sec execute 17 sec latency 22584.961 ms 1 501 0.00 MB/sec execute 18 sec latency 23588.644 ms 1 501 0.00 MB/sec execute 19 sec latency 24591.571 ms 1 501 0.00 MB/sec execute 20 sec latency 25595.331 ms 1 501 0.00 MB/sec execute 21 sec latency 26597.524 ms Starting mds1: -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 501 0.00 MB/sec execute 22 sec latency 27598.139 ms 1 501 0.00 MB/sec execute 23 sec latency 28598.390 ms 1 501 0.00 MB/sec execute 24 sec latency 29599.065 ms 1 501 0.00 MB/sec execute 25 sec latency 30599.386 ms 1 501 0.00 MB/sec execute 26 sec latency 31620.092 ms 1 501 0.00 MB/sec execute 27 sec latency 32621.604 ms 1 501 0.00 MB/sec execute 28 sec latency 33622.212 ms 1 501 0.00 MB/sec execute 29 sec latency 34624.397 ms 1 501 0.00 MB/sec execute 30 sec latency 35625.685 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all 8 1 501 0.00 MB/sec execute 31 sec latency 36625.898 ms pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 1 501 0.00 MB/sec execute 32 sec latency 37627.874 ms Started lustre-MDT0000 1 501 0.00 MB/sec execute 33 sec latency 38629.334 ms 1 512 0.01 MB/sec execute 34 sec latency 39222.018 ms 1 603 0.10 MB/sec execute 35 sec latency 117.441 ms 1 671 0.10 MB/sec execute 36 sec latency 89.452 ms 1 711 0.10 MB/sec execute 37 sec latency 143.649 ms 1 740 0.10 MB/sec execute 38 sec latency 94.860 ms 1 781 0.10 MB/sec execute 39 sec latency 106.249 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 808 0.10 MB/sec execute 40 sec latency 133.255 ms 1 865 0.10 MB/sec execute 41 sec latency 113.661 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 900 0.10 MB/sec execute 42 sec latency 115.183 ms 1 926 0.10 MB/sec execute 43 sec latency 125.986 ms 1 969 0.10 MB/sec execute 44 sec latency 107.290 ms 1 1033 0.12 MB/sec execute 45 sec latency 93.952 ms 1 1099 0.12 MB/sec execute 46 sec latency 67.526 ms 1 1163 0.12 MB/sec execute 47 sec latency 76.449 ms 1 1221 0.12 MB/sec execute 48 sec latency 72.000 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2232 1285456 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2056 1285632 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 37236 3569220 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 21120 3580988 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 58356 7150208 1% /mnt/lustre 1 1267 0.12 MB/sec execute 49 sec latency 141.599 ms 1 1418 0.17 MB/sec execute 50 sec latency 84.141 ms 1 1470 0.17 MB/sec execute 51 sec latency 75.451 ms 1 1504 0.16 MB/sec execute 52 sec latency 128.391 ms 1 1558 0.16 MB/sec execute 53 sec latency 120.858 ms 1 1619 0.16 MB/sec execute 54 sec latency 85.219 ms 1 1654 0.16 MB/sec execute 55 sec latency 315.078 ms 1 1696 0.16 MB/sec execute 56 sec latency 99.220 ms 1 1775 0.15 MB/sec execute 57 sec latency 79.868 ms test_26 fail mds2 2 times 1 1843 0.15 MB/sec execute 58 sec latency 75.146 ms 1 1888 0.15 MB/sec execute 59 sec latency 133.508 ms Failing mds2 on oleg311-server 1 1950 0.15 MB/sec execute 60 sec latency 108.221 ms 1 1992 0.15 MB/sec execute 61 sec latency 115.452 ms Stopping /mnt/lustre-mds2 (opts:) on oleg311-server 1 2042 0.15 MB/sec execute 62 sec latency 116.508 ms 1 2069 0.15 MB/sec execute 63 sec latency 542.818 ms 1 2069 0.14 MB/sec execute 64 sec latency 1543.055 ms 1 2069 0.14 MB/sec execute 65 sec latency 2543.497 ms reboot facets: mds2 1 2069 0.14 MB/sec execute 66 sec latency 3544.899 ms 1 2069 0.14 MB/sec execute 67 sec latency 4545.257 ms 1 2069 0.13 MB/sec execute 68 sec latency 5545.526 ms 1 2069 0.13 MB/sec execute 69 sec latency 6546.278 ms 1 2069 0.13 MB/sec execute 70 sec latency 7546.558 ms 1 2069 0.13 MB/sec execute 71 sec latency 8547.146 ms 1 2069 0.13 MB/sec execute 72 sec latency 9549.269 ms 1 2069 0.13 MB/sec execute 73 sec latency 10549.978 ms 1 2069 0.12 MB/sec execute 74 sec latency 11550.417 ms 1 2069 0.12 MB/sec execute 75 sec latency 12550.700 ms Failover mds2 to oleg311-server 1 2069 0.12 MB/sec execute 76 sec latency 13550.968 ms 1 2069 0.12 MB/sec execute 77 sec latency 14551.449 ms mount facets: mds2 1 2069 0.12 MB/sec execute 78 sec latency 15551.625 ms 1 2069 0.12 MB/sec execute 79 sec latency 16551.875 ms 1 2069 0.11 MB/sec execute 80 sec latency 17552.481 ms 1 2069 0.11 MB/sec execute 81 sec latency 18555.425 ms 1 2069 0.11 MB/sec execute 82 sec latency 19555.811 ms 1 2069 0.11 MB/sec execute 83 sec latency 20556.073 ms 1 2069 0.11 MB/sec execute 84 sec latency 21556.438 ms 1 2069 0.11 MB/sec execute 85 sec latency 22556.687 ms 1 2069 0.11 MB/sec execute 86 sec latency 23556.908 ms Starting mds2: -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 2069 0.11 MB/sec execute 87 sec latency 24557.150 ms 1 2069 0.10 MB/sec execute 88 sec latency 25558.125 ms 1 2069 0.10 MB/sec execute 89 sec latency 26558.773 ms 1 2069 0.10 MB/sec execute 90 sec latency 27559.292 ms 1 2069 0.10 MB/sec execute 91 sec latency 28559.716 ms 1 2069 0.10 MB/sec execute 92 sec latency 29560.047 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all 8 1 2069 0.10 MB/sec execute 93 sec latency 30560.408 ms pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 1 2069 0.10 MB/sec execute 94 sec latency 31560.657 ms Started lustre-MDT0001 1 2069 0.10 MB/sec execute 95 sec latency 32562.068 ms 1 2124 0.10 MB/sec execute 96 sec latency 32751.500 ms 1 2160 0.10 MB/sec execute 97 sec latency 109.292 ms 1 2204 0.09 MB/sec execute 98 sec latency 95.378 ms 1 2297 0.10 MB/sec execute 99 sec latency 160.740 ms 1 cleanup 100 sec 1 cleanup 101 sec oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 cleanup 102 sec 1 cleanup 103 sec 0 cleanup 103 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 326 273.343 39221.997 Close 281 12.411 42.332 Rename 11 73.251 141.579 Unlink 31 24.226 52.635 Qpathinfo 307 12.305 109.605 Qfileinfo 71 1.615 9.962 Qfsinfo 37 3.223 28.907 Sfileinfo 37 39.415 91.826 Find 100 10.741 50.876 WriteX 239 11.189 130.954 ReadX 377 0.468 51.181 Flush 31 68.698 315.055 Throughput 0.10385 MB/sec 1 clients 1 procs max_latency=39222.018 ms stopping dbench on /mnt/lustre at Tue Apr 14 14:52:45 EDT 2026 with return code 0 mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished striped dir -i0 -c2 -H all_char /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 2408 1285280 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2288 1285400 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 10496 3596324 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 24140 3580816 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 34636 7177140 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 Tue Apr 14 14:52:54 EDT 2026 waiting for dbench pid 69230 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 45.353 ms 1 91 2.10 MB/sec warmup 2 sec latency 130.815 ms 1 134 1.96 MB/sec warmup 3 sec latency 153.608 ms 1 137 1.51 MB/sec warmup 4 sec latency 984.510 ms 1 165 1.36 MB/sec warmup 5 sec latency 1264.773 ms 1 207 1.35 MB/sec warmup 6 sec latency 149.080 ms 1 255 1.38 MB/sec warmup 7 sec latency 102.784 ms test_26 fail mds1 3 times 1 290 1.34 MB/sec warmup 8 sec latency 120.355 ms 1 319 1.28 MB/sec warmup 9 sec latency 147.401 ms Failing mds1 on oleg311-server 1 349 1.25 MB/sec warmup 10 sec latency 149.236 ms Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 384 1.23 MB/sec warmup 11 sec latency 136.484 ms 1 422 1.24 MB/sec warmup 12 sec latency 137.742 ms 1 470 1.26 MB/sec warmup 13 sec latency 114.933 ms reboot facets: mds1 1 501 1.24 MB/sec warmup 14 sec latency 424.854 ms 1 501 1.16 MB/sec warmup 15 sec latency 1425.097 ms 1 501 1.09 MB/sec warmup 16 sec latency 2425.315 ms 1 501 1.03 MB/sec warmup 17 sec latency 3425.500 ms 1 501 0.97 MB/sec warmup 18 sec latency 4425.906 ms 1 501 0.92 MB/sec warmup 19 sec latency 5426.178 ms 1 501 0.00 MB/sec execute 1 sec latency 7426.603 ms 1 501 0.00 MB/sec execute 2 sec latency 8426.884 ms 1 501 0.00 MB/sec execute 3 sec latency 9427.253 ms Failover mds1 to oleg311-server 1 501 0.00 MB/sec execute 4 sec latency 10427.431 ms 1 501 0.00 MB/sec execute 5 sec latency 11429.983 ms mount facets: mds1 1 501 0.00 MB/sec execute 6 sec latency 12431.428 ms 1 501 0.00 MB/sec execute 7 sec latency 13433.604 ms 1 501 0.00 MB/sec execute 8 sec latency 14435.254 ms 1 501 0.00 MB/sec execute 9 sec latency 15435.906 ms 1 501 0.00 MB/sec execute 10 sec latency 16437.165 ms 1 501 0.00 MB/sec execute 11 sec latency 17437.616 ms 1 501 0.00 MB/sec execute 12 sec latency 18437.900 ms 1 501 0.00 MB/sec execute 13 sec latency 19438.598 ms Starting mds1: -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 501 0.00 MB/sec execute 14 sec latency 20439.354 ms 1 501 0.00 MB/sec execute 15 sec latency 21440.016 ms 1 501 0.00 MB/sec execute 16 sec latency 22441.339 ms 1 501 0.00 MB/sec execute 17 sec latency 23441.525 ms 1 501 0.00 MB/sec execute 18 sec latency 24444.212 ms 1 501 0.00 MB/sec execute 19 sec latency 25445.118 ms 1 501 0.00 MB/sec execute 20 sec latency 26446.011 ms 1 501 0.00 MB/sec execute 21 sec latency 27446.655 ms 1 501 0.00 MB/sec execute 22 sec latency 28450.661 ms 1 501 0.00 MB/sec execute 23 sec latency 29452.269 ms 1 501 0.00 MB/sec execute 24 sec latency 30454.844 ms 1 501 0.00 MB/sec execute 25 sec latency 31455.123 ms 1 501 0.00 MB/sec execute 26 sec latency 32455.492 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all 8 1 501 0.00 MB/sec execute 27 sec latency 33467.726 ms pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 1 501 0.00 MB/sec execute 28 sec latency 34468.612 ms 1 503 0.00 MB/sec execute 29 sec latency 35386.413 ms Started lustre-MDT0000 1 550 0.05 MB/sec execute 30 sec latency 138.649 ms 1 616 0.11 MB/sec execute 31 sec latency 87.734 ms 1 656 0.11 MB/sec execute 32 sec latency 143.941 ms 1 688 0.11 MB/sec execute 33 sec latency 123.784 ms 1 710 0.11 MB/sec execute 34 sec latency 187.436 ms 1 731 0.11 MB/sec execute 35 sec latency 165.079 ms 1 765 0.11 MB/sec execute 36 sec latency 157.853 ms 1 789 0.11 MB/sec execute 37 sec latency 154.133 ms 1 811 0.11 MB/sec execute 38 sec latency 139.052 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 857 0.11 MB/sec execute 39 sec latency 160.234 ms 1 878 0.10 MB/sec execute 40 sec latency 140.553 ms 1 901 0.10 MB/sec execute 41 sec latency 154.381 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 914 0.10 MB/sec execute 42 sec latency 192.080 ms 1 940 0.10 MB/sec execute 43 sec latency 135.976 ms 1 970 0.10 MB/sec execute 44 sec latency 151.472 ms 1 1006 0.10 MB/sec execute 45 sec latency 116.818 ms 1 1080 0.12 MB/sec execute 46 sec latency 80.158 ms 1 1118 0.12 MB/sec execute 47 sec latency 128.279 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 1154 0.12 MB/sec execute 48 sec latency 127.275 ms 1 1193 0.11 MB/sec execute 49 sec latency 145.700 ms 1 1231 0.11 MB/sec execute 50 sec latency 102.494 ms 1 1274 0.11 MB/sec execute 51 sec latency 111.902 ms 1 1418 0.16 MB/sec execute 52 sec latency 134.159 ms 1 1449 0.16 MB/sec execute 53 sec latency 129.233 ms 1 1497 0.16 MB/sec execute 54 sec latency 88.926 ms 1 1532 0.16 MB/sec execute 55 sec latency 174.173 ms 1 1593 0.15 MB/sec execute 56 sec latency 107.675 ms 1 1647 0.15 MB/sec execute 57 sec latency 95.964 ms 1 1691 0.15 MB/sec execute 58 sec latency 96.344 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 1 1770 0.15 MB/sec execute 59 sec latency 85.107 ms stopping dbench on /mnt/lustre at Tue Apr 14 14:54:13 EDT 2026 with return code 0 69230 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 69230 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished