== replay-dual test 26: dbench and tar with mds failover ========================================================== 13:13:55 (1736360035) Starting client oleg409-client.virtnet: -o user_xattr,flock oleg409-server@tcp:/lustre /mnt/lustre Started clients oleg409-client.virtnet: 192.168.204.109@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,flock,user_xattr,lruresize,lazystatfs,nouser_fid2path,verbose,noencrypt) Started tar loop with pid 6317 Started dbench loop with 6318 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 '/usr/share/dbench/client.txt' -> 'client.txt' running 'dbench 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100' on /mnt/lustre at Wed Jan 8 13:13:56 EST 2025 waiting for dbench pid 6353 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 1 271 10.18 MB/sec warmup 1 sec latency 17.520 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2272 1285416 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2092 1285596 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 25984 3556056 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1388 3605632 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27372 7161688 1% /mnt/lustre 1 521 9.03 MB/sec warmup 2 sec latency 17.778 ms 1 900 7.23 MB/sec warmup 3 sec latency 19.579 ms 1 1257 5.77 MB/sec warmup 4 sec latency 17.987 ms test_26 fail mds1 1 times 1 1736 5.26 MB/sec warmup 5 sec latency 13.636 ms Failing mds1 on oleg409-server Stopping /mnt/lustre-mds1 (opts:) on oleg409-server 1 2061 4.44 MB/sec warmup 6 sec latency 256.645 ms reboot facets: mds1 1 2061 3.80 MB/sec warmup 7 sec latency 1256.790 ms 1 2061 3.33 MB/sec warmup 8 sec latency 2256.991 ms 1 2061 2.96 MB/sec warmup 9 sec latency 3257.164 ms 1 2061 2.66 MB/sec warmup 10 sec latency 4257.401 ms 1 2061 2.42 MB/sec warmup 11 sec latency 5257.574 ms 1 2061 2.22 MB/sec warmup 12 sec latency 6257.754 ms 1 2061 2.05 MB/sec warmup 13 sec latency 7257.898 ms 1 2061 1.90 MB/sec warmup 14 sec latency 8258.098 ms 1 2061 1.77 MB/sec warmup 15 sec latency 9258.327 ms 1 2061 1.66 MB/sec warmup 16 sec latency 10258.447 ms Failover mds1 to oleg409-server mount facets: mds1 1 2061 1.57 MB/sec warmup 17 sec latency 11258.543 ms 1 2061 1.48 MB/sec warmup 18 sec latency 12258.691 ms Starting mds1: -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 2061 1.40 MB/sec warmup 19 sec latency 13258.811 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0000 1 2061 0.00 MB/sec execute 1 sec latency 15259.077 ms 1 2061 0.00 MB/sec execute 2 sec latency 16259.290 ms 1 2061 0.00 MB/sec execute 3 sec latency 17259.440 ms 1 2061 0.00 MB/sec execute 4 sec latency 18259.603 ms 1 2098 0.01 MB/sec execute 5 sec latency 19186.726 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 2455 0.25 MB/sec execute 6 sec latency 38.699 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3023 0.99 MB/sec execute 7 sec latency 18.151 ms 1 3685 1.52 MB/sec execute 8 sec latency 13.643 ms 1 3975 1.49 MB/sec execute 9 sec latency 14.745 ms 1 4311 1.38 MB/sec execute 10 sec latency 31.868 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2812 1284876 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2812 1284876 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 35416 3561440 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 5880 3594220 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 41296 7155660 1% /mnt/lustre 1 4684 1.41 MB/sec execute 11 sec latency 28.962 ms 1 5119 1.55 MB/sec execute 12 sec latency 16.402 ms 1 5407 1.45 MB/sec execute 13 sec latency 25.541 ms test_26 fail mds2 2 times 1 5884 1.45 MB/sec execute 14 sec latency 11.129 ms Failing mds2 on oleg409-server Stopping /mnt/lustre-mds2 (opts:) on oleg409-server 1 6345 1.63 MB/sec execute 15 sec latency 21.790 ms reboot facets: mds2 1 6933 1.75 MB/sec execute 16 sec latency 15.026 ms 1 7373 1.90 MB/sec execute 17 sec latency 13.334 ms 1 7627 1.81 MB/sec execute 18 sec latency 32.730 ms 1 7627 1.71 MB/sec execute 19 sec latency 1032.945 ms 1 7627 1.63 MB/sec execute 20 sec latency 2033.082 ms 1 7627 1.55 MB/sec execute 21 sec latency 3033.225 ms 1 7627 1.48 MB/sec execute 22 sec latency 4033.372 ms 1 7627 1.42 MB/sec execute 23 sec latency 5033.575 ms 1 7627 1.36 MB/sec execute 24 sec latency 6033.717 ms 1 7627 1.30 MB/sec execute 25 sec latency 7033.883 ms Failover mds2 to oleg409-server mount facets: mds2 1 7627 1.25 MB/sec execute 26 sec latency 8033.974 ms 1 7627 1.21 MB/sec execute 27 sec latency 9034.113 ms Starting mds2: -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 7627 1.16 MB/sec execute 28 sec latency 10034.252 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 1 7627 1.12 MB/sec execute 29 sec latency 11034.391 ms pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0001 1 7627 1.09 MB/sec execute 30 sec latency 12034.538 ms 1 7627 1.05 MB/sec execute 31 sec latency 13034.681 ms 1 7627 1.02 MB/sec execute 32 sec latency 14034.834 ms 1 7627 0.99 MB/sec execute 33 sec latency 15034.958 ms 1 7627 0.96 MB/sec execute 34 sec latency 16035.065 ms 1 7834 0.94 MB/sec execute 35 sec latency 16468.168 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8177 0.96 MB/sec execute 36 sec latency 14.031 ms 1 8611 1.02 MB/sec execute 37 sec latency 16.967 ms 1 8953 1.00 MB/sec execute 38 sec latency 15.910 ms 1 9432 1.01 MB/sec execute 39 sec latency 16.335 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2648 1285040 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3412 1284276 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 42776 3562888 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 16612 3589516 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 59388 7152404 1% /mnt/lustre 1 9870 1.09 MB/sec execute 40 sec latency 13.247 ms 1 10296 1.12 MB/sec execute 41 sec latency 359.204 ms 1 10766 1.20 MB/sec execute 42 sec latency 469.582 ms 1 11048 1.20 MB/sec execute 43 sec latency 14.686 ms test_26 fail mds1 3 times Failing mds1 on oleg409-server Stopping /mnt/lustre-mds1 (opts:) on oleg409-server 1 11370 1.18 MB/sec execute 44 sec latency 32.561 ms reboot facets: mds1 1 11653 1.17 MB/sec execute 45 sec latency 99.569 ms 1 11653 1.14 MB/sec execute 46 sec latency 1099.674 ms 1 11653 1.12 MB/sec execute 47 sec latency 2099.875 ms 1 11653 1.10 MB/sec execute 48 sec latency 3099.987 ms 1 11653 1.07 MB/sec execute 49 sec latency 4100.075 ms 1 11653 1.05 MB/sec execute 50 sec latency 5100.188 ms 1 11653 1.03 MB/sec execute 51 sec latency 6100.328 ms 1 11653 1.01 MB/sec execute 52 sec latency 7100.522 ms 1 11653 0.99 MB/sec execute 53 sec latency 8100.740 ms 1 11653 0.97 MB/sec execute 54 sec latency 9100.954 ms Failover mds1 to oleg409-server 1 11653 0.96 MB/sec execute 55 sec latency 10101.088 ms mount facets: mds1 1 11653 0.94 MB/sec execute 56 sec latency 11101.264 ms 1 11653 0.92 MB/sec execute 57 sec latency 12101.472 ms Starting mds1: -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 11653 0.91 MB/sec execute 58 sec latency 13101.650 ms 1 11653 0.89 MB/sec execute 59 sec latency 14101.827 ms 1 11653 0.88 MB/sec execute 60 sec latency 15101.966 ms 1 11653 0.86 MB/sec execute 61 sec latency 16102.104 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 1 11653 0.85 MB/sec execute 62 sec latency 17102.230 ms pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0000 1 11653 0.84 MB/sec execute 63 sec latency 18102.332 ms 1 11653 0.82 MB/sec execute 64 sec latency 19102.489 ms 1 11653 0.81 MB/sec execute 65 sec latency 20102.639 ms 1 11653 0.80 MB/sec execute 66 sec latency 21102.807 ms 1 11858 0.80 MB/sec execute 67 sec latency 21529.180 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 12267 0.84 MB/sec execute 68 sec latency 15.093 ms 1 12640 0.83 MB/sec execute 69 sec latency 18.258 ms 1 13060 0.84 MB/sec execute 70 sec latency 13.016 ms 1 13596 0.90 MB/sec execute 71 sec latency 14.560 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3132 1284556 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 4768 1282920 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 51400 3542808 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 17156 3577744 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 68556 7120552 1% /mnt/lustre 1 14217 0.96 MB/sec execute 72 sec latency 25.830 ms 1 14523 0.97 MB/sec execute 73 sec latency 15.724 ms 1 14820 0.96 MB/sec execute 74 sec latency 14.949 ms 1 15175 0.96 MB/sec execute 75 sec latency 17.469 ms test_26 fail mds2 4 times Failing mds2 on oleg409-server 1 15605 1.00 MB/sec execute 76 sec latency 14.559 ms Stopping /mnt/lustre-mds2 (opts:) on oleg409-server reboot facets: mds2 1 15710 0.99 MB/sec execute 77 sec latency 647.989 ms 1 15710 0.97 MB/sec execute 78 sec latency 1648.169 ms 1 15710 0.96 MB/sec execute 79 sec latency 2648.335 ms 1 15710 0.95 MB/sec execute 80 sec latency 3648.541 ms 1 15710 0.94 MB/sec execute 81 sec latency 4648.728 ms 1 15710 0.93 MB/sec execute 82 sec latency 5648.975 ms 1 15710 0.91 MB/sec execute 83 sec latency 6649.176 ms 1 15710 0.90 MB/sec execute 84 sec latency 7649.423 ms 1 15710 0.89 MB/sec execute 85 sec latency 8649.643 ms 1 15710 0.88 MB/sec execute 86 sec latency 9649.929 ms Failover mds2 to oleg409-server 1 15710 0.87 MB/sec execute 87 sec latency 10650.121 ms mount facets: mds2 1 15710 0.86 MB/sec execute 88 sec latency 11650.274 ms 1 15710 0.85 MB/sec execute 89 sec latency 12650.441 ms 1 15710 0.84 MB/sec execute 90 sec latency 13650.615 ms Starting mds2: -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 15710 0.83 MB/sec execute 91 sec latency 14650.788 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 1 15710 0.83 MB/sec execute 92 sec latency 15650.992 ms pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0001 1 15710 0.82 MB/sec execute 93 sec latency 16651.213 ms 1 15710 0.81 MB/sec execute 94 sec latency 17651.458 ms 1 15710 0.80 MB/sec execute 95 sec latency 18651.754 ms 1 15710 0.79 MB/sec execute 96 sec latency 19652.009 ms 1 15718 0.78 MB/sec execute 97 sec latency 20616.732 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 16035 0.78 MB/sec execute 98 sec latency 18.668 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 16487 0.78 MB/sec execute 99 sec latency 13.236 ms 1 cleanup 100 sec 0 cleanup 100 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 2525 16.063 21529.170 Close 1881 12.361 20616.717 Rename 109 10.906 25.518 Unlink 507 3.729 13.981 Qpathinfo 2336 1.920 13.103 Qfileinfo 410 0.350 2.359 Qfsinfo 418 0.658 7.274 Sfileinfo 216 5.145 12.630 Find 897 41.030 19186.720 WriteX 1275 1.997 10.095 ReadX 3955 0.037 27.838 LockX 8 1.284 1.486 UnlockX 8 1.418 1.704 Flush 176 9.966 469.570 Throughput 0.783945 MB/sec 1 clients 1 procs max_latency=21529.180 ms stopping dbench on /mnt/lustre at Wed Jan 8 13:15:57 EST 2025 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 crush /mnt/lustre2/d26.replay-dual/run_dbench 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 Wed Jan 8 13:15:58 EST 2025 waiting for dbench pid 11193 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 UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3596 1284092 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 5200 1282488 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20308 3579976 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 18460 3556624 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 38768 7136600 1% /mnt/lustre 1 238 9.14 MB/sec warmup 1 sec latency 22.056 ms 1 389 6.91 MB/sec warmup 2 sec latency 30.111 ms 1 712 7.07 MB/sec warmup 3 sec latency 27.858 ms 1 974 5.45 MB/sec warmup 4 sec latency 37.945 ms test_26 fail mds1 5 times Failing mds1 on oleg409-server Stopping /mnt/lustre-mds1 (opts:) on oleg409-server 1 1412 5.20 MB/sec warmup 5 sec latency 17.993 ms reboot facets: mds1 1 1481 4.34 MB/sec warmup 6 sec latency 829.981 ms 1 1481 3.72 MB/sec warmup 7 sec latency 1830.112 ms 1 1481 3.26 MB/sec warmup 8 sec latency 2830.251 ms 1 1481 2.89 MB/sec warmup 9 sec latency 3830.486 ms 1 1481 2.60 MB/sec warmup 10 sec latency 4830.678 ms 1 1481 2.37 MB/sec warmup 11 sec latency 5830.837 ms 1 1481 2.17 MB/sec warmup 12 sec latency 6830.990 ms 1 1481 2.00 MB/sec warmup 13 sec latency 7831.148 ms 1 1481 1.86 MB/sec warmup 14 sec latency 8831.362 ms 1 1481 1.74 MB/sec warmup 15 sec latency 9831.552 ms Failover mds1 to oleg409-server 1 1481 1.63 MB/sec warmup 16 sec latency 10831.670 ms mount facets: mds1 1 1481 1.53 MB/sec warmup 17 sec latency 11831.779 ms 1 1481 1.45 MB/sec warmup 18 sec latency 12831.947 ms Starting mds1: -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1481 1.37 MB/sec warmup 19 sec latency 13832.098 ms 1 1481 0.00 MB/sec execute 1 sec latency 15832.484 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 1 1481 0.00 MB/sec execute 2 sec latency 16832.660 ms pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0000 1 1481 0.00 MB/sec execute 3 sec latency 17832.866 ms 1 1481 0.00 MB/sec execute 4 sec latency 18833.099 ms 1 1481 0.00 MB/sec execute 5 sec latency 19833.341 ms 1 1481 0.00 MB/sec execute 6 sec latency 20833.537 ms 1 1482 0.00 MB/sec execute 7 sec latency 21822.027 ms 1 1820 0.04 MB/sec execute 8 sec latency 24.446 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2201 0.08 MB/sec execute 9 sec latency 13.890 ms 1 2600 0.30 MB/sec execute 10 sec latency 27.014 ms 1 3275 0.85 MB/sec execute 11 sec latency 19.816 ms 1 3782 1.14 MB/sec execute 12 sec latency 13.452 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2496 1285192 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3816 1283872 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 15680 3588408 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 46684 3559764 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 62364 7148172 1% /mnt/lustre 1 4014 1.08 MB/sec execute 13 sec latency 23.414 ms 1 4354 1.03 MB/sec execute 14 sec latency 15.195 ms 1 4721 1.07 MB/sec execute 15 sec latency 12.981 ms 1 5141 1.20 MB/sec execute 16 sec latency 13.819 ms test_26 fail mds2 6 times Failing mds2 on oleg409-server Stopping /mnt/lustre-mds2 (opts:) on oleg409-server 1 5474 1.15 MB/sec execute 17 sec latency 61.021 ms reboot facets: mds2 1 5820 1.10 MB/sec execute 18 sec latency 267.169 ms 1 5820 1.05 MB/sec execute 19 sec latency 1267.302 ms 1 5820 0.99 MB/sec execute 20 sec latency 2267.437 ms 1 5820 0.95 MB/sec execute 21 sec latency 3267.605 ms 1 5820 0.90 MB/sec execute 22 sec latency 4267.780 ms 1 5820 0.86 MB/sec execute 23 sec latency 5267.968 ms 1 5820 0.83 MB/sec execute 24 sec latency 6268.138 ms 1 5820 0.79 MB/sec execute 25 sec latency 7268.288 ms 1 5820 0.76 MB/sec execute 26 sec latency 8268.444 ms 1 5820 0.74 MB/sec execute 27 sec latency 9268.607 ms Failover mds2 to oleg409-server mount facets: mds2 1 5820 0.71 MB/sec execute 28 sec latency 10268.805 ms 1 5820 0.68 MB/sec execute 29 sec latency 11269.007 ms 1 5820 0.66 MB/sec execute 30 sec latency 12269.179 ms Starting mds2: -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 5820 0.64 MB/sec execute 31 sec latency 13269.332 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0001 1 5820 0.62 MB/sec execute 32 sec latency 14269.489 ms 1 5820 0.60 MB/sec execute 33 sec latency 15269.663 ms 1 5820 0.58 MB/sec execute 34 sec latency 16269.815 ms 1 5820 0.57 MB/sec execute 35 sec latency 17269.970 ms 1 5820 0.55 MB/sec execute 36 sec latency 18270.142 ms 1 5823 0.54 MB/sec execute 37 sec latency 19267.156 ms 1 6128 0.58 MB/sec execute 38 sec latency 28.243 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 6574 0.68 MB/sec execute 39 sec latency 19.542 ms 1 7062 0.79 MB/sec execute 40 sec latency 16.694 ms 1 7312 0.80 MB/sec execute 41 sec latency 21.612 ms 1 7534 0.79 MB/sec execute 42 sec latency 19.861 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2500 1285188 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2804 1284884 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 13056 3589556 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 43684 3562416 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 56740 7151972 1% /mnt/lustre 1 7828 0.78 MB/sec execute 43 sec latency 29.809 ms 1 7985 0.77 MB/sec execute 44 sec latency 467.936 ms 1 8280 0.78 MB/sec execute 45 sec latency 503.180 ms 1 8621 0.83 MB/sec execute 46 sec latency 22.392 ms test_26 fail mds1 7 times Failing mds1 on oleg409-server Stopping /mnt/lustre-mds1 (opts:) on oleg409-server 1 8916 0.82 MB/sec execute 47 sec latency 24.147 ms striped dir -i0 -c2 -H all_char /mnt/lustre/d26.replay-dual/run_tar reboot facets: mds1 1 9011 0.80 MB/sec execute 48 sec latency 701.080 ms 1 9011 0.79 MB/sec execute 49 sec latency 1701.315 ms 1 9011 0.77 MB/sec execute 50 sec latency 2701.546 ms 1 9011 0.76 MB/sec execute 51 sec latency 3701.854 ms 1 9011 0.74 MB/sec execute 52 sec latency 4702.095 ms 1 9011 0.73 MB/sec execute 53 sec latency 5702.349 ms 1 9011 0.72 MB/sec execute 54 sec latency 6702.606 ms 1 9011 0.70 MB/sec execute 55 sec latency 7702.775 ms 1 9011 0.69 MB/sec execute 56 sec latency 8702.965 ms 1 9011 0.68 MB/sec execute 57 sec latency 9703.129 ms 1 9011 0.67 MB/sec execute 58 sec latency 10703.243 ms Failover mds1 to oleg409-server mount facets: mds1 1 9011 0.65 MB/sec execute 59 sec latency 11703.496 ms 1 9011 0.64 MB/sec execute 60 sec latency 12703.636 ms Starting mds1: -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 9011 0.63 MB/sec execute 61 sec latency 13703.780 ms 1 9011 0.62 MB/sec execute 62 sec latency 14703.932 ms 1 9011 0.61 MB/sec execute 63 sec latency 15704.104 ms 1 9011 0.60 MB/sec execute 64 sec latency 16704.229 ms oleg409-server: oleg409-server.virtnet: executing set_default_debug -1 all 8 pdsh@oleg409-client: oleg409-server: ssh exited with exit code 1 Started lustre-MDT0000 1 9011 0.59 MB/sec execute 65 sec latency 17704.383 ms 1 9011 0.59 MB/sec execute 66 sec latency 18704.532 ms 1 9011 0.58 MB/sec execute 67 sec latency 19704.788 ms 1 9011 0.57 MB/sec execute 68 sec latency 20705.034 ms 1 9012 0.56 MB/sec execute 69 sec latency 21681.840 ms oleg409-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 9444 0.57 MB/sec execute 70 sec latency 41.819 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 9938 0.62 MB/sec execute 71 sec latency 12.638 ms 1 10592 0.70 MB/sec execute 72 sec latency 23.563 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 10930 0.71 MB/sec execute 73 sec latency 15.317 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed Jan 8 13:17:32 EST 2025 with return code 0 11193 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 11193 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished