== replay-dual test 26: dbench and tar with mds failover ========================================================== 05:35:46 (1744536946) Starting client oleg311-client.virtnet: -o user_xattr,flock 192.168.203.111@tcp:/lustre /mnt/lustre Started clients oleg311-client.virtnet: 192.168.203.111@tcp:/lustre on /mnt/lustre type lustre (rw,checksum,noencrypt,flock,lazystatfs,lruresize,nolock,statfs_project,nouser_fid2path,user_xattr,verbose) Started tar loop with pid 14944 Started dbench loop with 14945 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 Apr 13 05:35:47 EDT 2025 waiting for dbench pid 14976 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 1 181 7.32 MB/sec warmup 1 sec latency 33.646 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 3584 2205056 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 3072 3707904 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 3072 3707904 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 6144 7415808 1% /mnt/lustre 1 389 6.91 MB/sec warmup 2 sec latency 25.802 ms 1 644 7.02 MB/sec warmup 3 sec latency 30.066 ms 1 798 5.37 MB/sec warmup 4 sec latency 71.267 ms test_26 fail mds1 1 times Failing mds1 on oleg311-server Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 1076 4.59 MB/sec warmup 5 sec latency 26.984 ms 05:35:53 (1744536953) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 1076 3.82 MB/sec warmup 6 sec latency 1008.624 ms 1 1076 3.28 MB/sec warmup 7 sec latency 2008.842 ms 1 1076 2.87 MB/sec warmup 8 sec latency 3009.028 ms 1 1076 2.55 MB/sec warmup 9 sec latency 4009.229 ms 1 1076 2.29 MB/sec warmup 10 sec latency 5009.492 ms 1 1076 2.08 MB/sec warmup 11 sec latency 6009.717 ms 1 1076 1.91 MB/sec warmup 12 sec latency 7009.884 ms 1 1076 1.76 MB/sec warmup 13 sec latency 8010.059 ms 1 1076 1.64 MB/sec warmup 14 sec latency 9010.252 ms 1 1076 1.53 MB/sec warmup 15 sec latency 10010.442 ms Failover mds1 to oleg311-server mount facets: mds1 1 1076 1.43 MB/sec warmup 16 sec latency 11010.574 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 1076 1.35 MB/sec warmup 17 sec latency 12010.750 ms 1 1076 1.27 MB/sec warmup 18 sec latency 13010.895 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 Started lustre-MDT0000 05:36:06 (1744536966) targets are mounted 05:36:06 (1744536966) facet_failover done 1 1076 1.21 MB/sec warmup 19 sec latency 14011.061 ms 1 1076 0.00 MB/sec execute 1 sec latency 16011.353 ms 1 1076 0.00 MB/sec execute 2 sec latency 17011.539 ms 1 1076 0.00 MB/sec execute 3 sec latency 18011.782 ms 1 1076 0.00 MB/sec execute 4 sec latency 19011.986 ms 1 1076 0.00 MB/sec execute 5 sec latency 20012.192 ms 1 1147 0.01 MB/sec execute 6 sec latency 20681.759 ms oleg311-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 1378 0.44 MB/sec execute 7 sec latency 46.435 ms 1 1558 0.40 MB/sec execute 8 sec latency 58.216 ms 1 1727 0.37 MB/sec execute 9 sec latency 32.408 ms 1 2037 0.37 MB/sec execute 10 sec latency 35.000 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210688 4608 2204032 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 14336 3611648 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 39936 3573760 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 54272 7185408 1% /mnt/lustre 1 2356 0.45 MB/sec execute 11 sec latency 50.762 ms 1 2716 0.75 MB/sec execute 12 sec latency 36.221 ms 1 3176 0.86 MB/sec execute 13 sec latency 44.202 ms test_26 fail mds1 2 times 1 3541 1.10 MB/sec execute 14 sec latency 30.242 ms Failing mds1 on oleg311-server Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 3776 1.12 MB/sec execute 15 sec latency 245.049 ms 05:36:23 (1744536983) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 3776 1.05 MB/sec execute 16 sec latency 1245.240 ms 1 3776 0.99 MB/sec execute 17 sec latency 2245.504 ms 1 3776 0.94 MB/sec execute 18 sec latency 3245.755 ms 1 3776 0.89 MB/sec execute 19 sec latency 4246.068 ms 1 3776 0.84 MB/sec execute 20 sec latency 5246.332 ms 1 3776 0.80 MB/sec execute 21 sec latency 6246.551 ms 1 3776 0.77 MB/sec execute 22 sec latency 7246.812 ms 1 3776 0.73 MB/sec execute 23 sec latency 8247.173 ms 1 3776 0.70 MB/sec execute 24 sec latency 9247.427 ms 1 3776 0.67 MB/sec execute 25 sec latency 10247.707 ms Failover mds1 to oleg311-server mount facets: mds1 1 3776 0.65 MB/sec execute 26 sec latency 11247.958 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 3776 0.62 MB/sec execute 27 sec latency 12248.221 ms 1 3776 0.60 MB/sec execute 28 sec latency 13248.436 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 Started lustre-MDT0000 05:36:36 (1744536996) targets are mounted 05:36:36 (1744536996) facet_failover done 1 3776 0.58 MB/sec execute 29 sec latency 14248.674 ms 1 3776 0.56 MB/sec execute 30 sec latency 15248.926 ms 1 3776 0.54 MB/sec execute 31 sec latency 16249.156 ms 1 3776 0.53 MB/sec execute 32 sec latency 17249.396 ms 1 3776 0.51 MB/sec execute 33 sec latency 18249.700 ms 1 3776 0.50 MB/sec execute 34 sec latency 19249.890 ms 1 3776 0.48 MB/sec execute 35 sec latency 20250.089 ms 1 3851 0.47 MB/sec execute 36 sec latency 20846.441 ms oleg311-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 4102 0.46 MB/sec execute 37 sec latency 15.254 ms 1 4297 0.46 MB/sec execute 38 sec latency 89.070 ms 1 4448 0.46 MB/sec execute 39 sec latency 62.187 ms 1 4685 0.48 MB/sec execute 40 sec latency 37.092 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 6016 2202496 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 16384 3554304 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 45056 3504128 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 61440 7058432 1% /mnt/lustre 1 4967 0.54 MB/sec execute 41 sec latency 23.738 ms 1 5170 0.53 MB/sec execute 42 sec latency 45.621 ms 1 5340 0.52 MB/sec execute 43 sec latency 47.324 ms test_26 fail mds1 3 times Failing mds1 on oleg311-server 1 5532 0.51 MB/sec execute 44 sec latency 44.893 ms Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 5645 0.51 MB/sec execute 45 sec latency 503.997 ms 05:36:53 (1744537013) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 5645 0.50 MB/sec execute 46 sec latency 1504.159 ms 1 5645 0.49 MB/sec execute 47 sec latency 2504.379 ms 1 5645 0.48 MB/sec execute 48 sec latency 3504.589 ms 1 5645 0.47 MB/sec execute 49 sec latency 4504.811 ms 1 5645 0.46 MB/sec execute 50 sec latency 5505.043 ms 1 5645 0.45 MB/sec execute 51 sec latency 6505.299 ms 1 5645 0.44 MB/sec execute 52 sec latency 7505.517 ms 1 5645 0.43 MB/sec execute 53 sec latency 8505.669 ms 1 5645 0.42 MB/sec execute 54 sec latency 9505.824 ms 1 5645 0.41 MB/sec execute 55 sec latency 10505.989 ms Failover mds1 to oleg311-server mount facets: mds1 1 5645 0.41 MB/sec execute 56 sec latency 11506.117 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 5645 0.40 MB/sec execute 57 sec latency 12506.271 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 1 5645 0.39 MB/sec execute 58 sec latency 13506.375 ms Started lustre-MDT0000 05:37:06 (1744537026) targets are mounted 05:37:06 (1744537026) facet_failover done 1 5645 0.39 MB/sec execute 59 sec latency 14506.543 ms 1 5645 0.38 MB/sec execute 60 sec latency 15506.710 ms 1 5645 0.37 MB/sec execute 61 sec latency 16506.891 ms 1 5645 0.37 MB/sec execute 62 sec latency 17507.071 ms 1 5645 0.36 MB/sec execute 63 sec latency 18507.217 ms 1 5645 0.36 MB/sec execute 64 sec latency 19507.316 ms 1 5645 0.35 MB/sec execute 65 sec latency 20507.426 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 5845 0.36 MB/sec execute 66 sec latency 20619.967 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 6134 0.38 MB/sec execute 67 sec latency 46.426 ms 1 6480 0.44 MB/sec execute 68 sec latency 65.036 ms 1 6826 0.46 MB/sec execute 69 sec latency 55.313 ms 1 7173 0.50 MB/sec execute 70 sec latency 33.542 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 7296 2201216 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 17408 3440640 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 49152 3502080 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 66560 6942720 1% /mnt/lustre 1 7383 0.51 MB/sec execute 71 sec latency 21.789 ms 1 7531 0.50 MB/sec execute 72 sec latency 25.563 ms 1 7699 0.50 MB/sec execute 73 sec latency 25.018 ms test_26 fail mds1 4 times Failing mds1 on oleg311-server 1 7872 0.50 MB/sec execute 74 sec latency 122.997 ms Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 7916 0.49 MB/sec execute 75 sec latency 692.033 ms 05:37:22 (1744537042) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 7916 0.48 MB/sec execute 76 sec latency 1692.321 ms 1 7916 0.48 MB/sec execute 77 sec latency 2692.745 ms 1 7916 0.47 MB/sec execute 78 sec latency 3693.119 ms 1 7916 0.47 MB/sec execute 79 sec latency 4693.388 ms 1 7916 0.46 MB/sec execute 80 sec latency 5693.643 ms 1 7916 0.45 MB/sec execute 81 sec latency 6693.849 ms 1 7916 0.45 MB/sec execute 82 sec latency 7694.092 ms 1 7916 0.44 MB/sec execute 83 sec latency 8694.384 ms 1 7916 0.44 MB/sec execute 84 sec latency 9694.605 ms 1 7916 0.43 MB/sec execute 85 sec latency 10694.798 ms Failover mds1 to oleg311-server mount facets: mds1 1 7916 0.43 MB/sec execute 86 sec latency 11694.989 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 7916 0.42 MB/sec execute 87 sec latency 12695.122 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all 1 7916 0.42 MB/sec execute 88 sec latency 13695.371 ms pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 Started lustre-MDT0000 05:37:36 (1744537056) targets are mounted 05:37:36 (1744537056) facet_failover done 1 7916 0.41 MB/sec execute 89 sec latency 14695.611 ms 1 7916 0.41 MB/sec execute 90 sec latency 15695.866 ms 1 7916 0.40 MB/sec execute 91 sec latency 16696.082 ms 1 7916 0.40 MB/sec execute 92 sec latency 17696.303 ms 1 7916 0.40 MB/sec execute 93 sec latency 18696.529 ms 1 7916 0.39 MB/sec execute 94 sec latency 19696.709 ms 1 7916 0.39 MB/sec execute 95 sec latency 20696.954 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 8091 0.39 MB/sec execute 96 sec latency 20973.929 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8394 0.40 MB/sec execute 97 sec latency 31.511 ms 1 8740 0.42 MB/sec execute 98 sec latency 43.009 ms 1 8965 0.42 MB/sec execute 99 sec latency 32.555 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 8832 2199680 1% /mnt/lustre[MDT:0] 1 cleanup 100 sec lustre-OST0000_UUID 3771392 18432 3435520 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 50176 3414016 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 68608 6849536 1% /mnt/lustre 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1434 54.761 20973.915 Close 1070 2.018 7.177 Rename 59 17.723 31.137 Unlink 264 5.559 25.002 Qpathinfo 1351 3.306 38.321 Qfileinfo 229 0.554 4.742 Qfsinfo 214 0.623 3.233 Sfileinfo 116 188.345 20681.746 Find 487 1.423 16.191 WriteX 684 2.207 8.662 ReadX 2149 0.216 36.188 LockX 4 2.451 3.984 UnlockX 4 2.254 2.762 Flush 92 27.147 122.985 Throughput 0.420833 MB/sec 1 clients 1 procs max_latency=20973.929 ms stopping dbench on /mnt/lustre at Sun Apr 13 05:37:48 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished 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 Apr 13 05:37:49 EDT 2025 waiting for dbench pid 19201 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 test_26 fail mds1 5 times 1 181 7.32 MB/sec warmup 1 sec latency 39.613 ms Failing mds1 on oleg311-server Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 373 6.65 MB/sec warmup 2 sec latency 40.054 ms 05:37:52 (1744537072) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 373 4.43 MB/sec warmup 3 sec latency 1040.257 ms 1 373 3.33 MB/sec warmup 4 sec latency 2040.496 ms 1 373 2.66 MB/sec warmup 5 sec latency 3040.741 ms 1 373 2.22 MB/sec warmup 6 sec latency 4041.063 ms 1 373 1.90 MB/sec warmup 7 sec latency 5041.356 ms 1 373 1.66 MB/sec warmup 8 sec latency 6041.603 ms 1 373 1.48 MB/sec warmup 9 sec latency 7041.897 ms 1 373 1.33 MB/sec warmup 10 sec latency 8042.191 ms 1 373 1.21 MB/sec warmup 11 sec latency 9042.508 ms 1 373 1.11 MB/sec warmup 12 sec latency 10042.822 ms Failover mds1 to oleg311-server mount facets: mds1 1 373 1.02 MB/sec warmup 13 sec latency 11043.037 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 373 0.95 MB/sec warmup 14 sec latency 12043.204 ms 1 373 0.89 MB/sec warmup 15 sec latency 13043.383 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 Started lustre-MDT0000 05:38:05 (1744537085) targets are mounted 05:38:05 (1744537085) facet_failover done 1 373 0.83 MB/sec warmup 16 sec latency 14043.633 ms 1 373 0.78 MB/sec warmup 17 sec latency 15043.836 ms 1 373 0.74 MB/sec warmup 18 sec latency 16044.012 ms 1 373 0.70 MB/sec warmup 19 sec latency 17044.198 ms 1 373 0.00 MB/sec execute 1 sec latency 19044.567 ms 1 373 0.00 MB/sec execute 2 sec latency 20044.728 ms 1 373 0.00 MB/sec execute 3 sec latency 21044.853 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 591 1.78 MB/sec execute 4 sec latency 21414.401 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 765 1.61 MB/sec execute 5 sec latency 45.344 ms 1 990 1.43 MB/sec execute 6 sec latency 37.678 ms 1 1273 1.41 MB/sec execute 7 sec latency 25.770 ms 1 1500 1.59 MB/sec execute 8 sec latency 72.439 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 10112 2198400 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 38912 3398656 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 32768 3526656 1% /mnt/lustre[OST:1] filesystem_summary: 7542784 71680 6925312 2% /mnt/lustre 1 1770 1.44 MB/sec execute 9 sec latency 32.643 ms 1 2000 1.32 MB/sec execute 10 sec latency 27.837 ms 1 2304 1.31 MB/sec execute 11 sec latency 22.364 ms test_26 fail mds1 6 times Failing mds1 on oleg311-server Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 2567 1.30 MB/sec execute 12 sec latency 100.430 ms 05:38:22 (1744537102) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 2567 1.20 MB/sec execute 13 sec latency 1100.626 ms 1 2567 1.11 MB/sec execute 14 sec latency 2100.785 ms 1 2567 1.04 MB/sec execute 15 sec latency 3100.896 ms 1 2567 0.98 MB/sec execute 16 sec latency 4101.121 ms 1 2567 0.92 MB/sec execute 17 sec latency 5101.412 ms 1 2567 0.87 MB/sec execute 18 sec latency 6101.590 ms 1 2567 0.82 MB/sec execute 19 sec latency 7101.816 ms 1 2567 0.78 MB/sec execute 20 sec latency 8101.992 ms 1 2567 0.74 MB/sec execute 21 sec latency 9102.169 ms 1 2567 0.71 MB/sec execute 22 sec latency 10102.411 ms Failover mds1 to oleg311-server mount facets: mds1 1 2567 0.68 MB/sec execute 23 sec latency 11102.554 ms Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 2567 0.65 MB/sec execute 24 sec latency 12102.656 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 1 2567 0.62 MB/sec execute 25 sec latency 13102.760 ms Started lustre-MDT0000 05:38:34 (1744537114) targets are mounted 05:38:34 (1744537114) facet_failover done 1 2567 0.60 MB/sec execute 26 sec latency 14102.939 ms 1 2567 0.58 MB/sec execute 27 sec latency 15103.112 ms 1 2567 0.56 MB/sec execute 28 sec latency 16103.323 ms 1 2567 0.54 MB/sec execute 29 sec latency 17103.470 ms 1 2567 0.52 MB/sec execute 30 sec latency 18103.618 ms 1 2567 0.50 MB/sec execute 31 sec latency 19103.780 ms 1 2567 0.49 MB/sec execute 32 sec latency 20103.910 ms 1 2567 0.47 MB/sec execute 33 sec latency 21104.016 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 2935 0.59 MB/sec execute 34 sec latency 21330.535 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 3531 0.72 MB/sec execute 35 sec latency 37.803 ms 1 3852 0.73 MB/sec execute 36 sec latency 13.360 ms 1 4076 0.72 MB/sec execute 37 sec latency 15.316 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 2210560 11264 2197248 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3771392 44032 3462144 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3771392 36864 3457024 2% /mnt/lustre[OST:1] filesystem_summary: 7542784 80896 6919168 2% /mnt/lustre 1 4330 0.71 MB/sec execute 38 sec latency 73.661 ms 1 4557 0.71 MB/sec execute 39 sec latency 35.800 ms 1 4985 0.80 MB/sec execute 40 sec latency 14.280 ms test_26 fail mds1 7 times 1 5254 0.78 MB/sec execute 41 sec latency 46.720 ms Failing mds1 on oleg311-server Stopping /mnt/lustre-mds1 (opts:) on oleg311-server 1 5385 0.77 MB/sec execute 42 sec latency 470.089 ms 05:38:52 (1744537132) shut down facet: mds1 facet_host: oleg311-server facet_failover_host: oleg311-server 1 5385 0.75 MB/sec execute 43 sec latency 1470.317 ms 1 5385 0.73 MB/sec execute 44 sec latency 2470.525 ms 1 5385 0.71 MB/sec execute 45 sec latency 3470.696 ms 1 5385 0.70 MB/sec execute 46 sec latency 4470.871 ms 1 5385 0.68 MB/sec execute 47 sec latency 5470.994 ms 1 5385 0.67 MB/sec execute 48 sec latency 6471.153 ms 1 5385 0.66 MB/sec execute 49 sec latency 7471.300 ms 1 5385 0.64 MB/sec execute 50 sec latency 8471.439 ms 1 5385 0.63 MB/sec execute 51 sec latency 9471.602 ms 1 5385 0.62 MB/sec execute 52 sec latency 10471.747 ms Failover mds1 to oleg311-server mount facets: mds1 Starting mds1: -o localrecov lustre-mdt1/mdt1 /mnt/lustre-mds1 1 5385 0.61 MB/sec execute 53 sec latency 11471.870 ms 1 5385 0.60 MB/sec execute 54 sec latency 12472.005 ms oleg311-server: oleg311-server.virtnet: executing set_default_debug -1 all pdsh@oleg311-client: oleg311-server: ssh exited with exit code 1 Started lustre-MDT0000 05:39:04 (1744537144) targets are mounted 05:39:04 (1744537144) facet_failover done 1 5385 0.58 MB/sec execute 55 sec latency 13472.182 ms 1 5385 0.57 MB/sec execute 56 sec latency 14472.370 ms 1 5385 0.56 MB/sec execute 57 sec latency 15472.472 ms 1 5385 0.55 MB/sec execute 58 sec latency 16472.628 ms oleg311-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 5587 0.55 MB/sec execute 59 sec latency 16741.859 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5937 0.56 MB/sec execute 60 sec latency 36.487 ms 1 6432 0.62 MB/sec execute 61 sec latency 59.085 ms 1 6953 0.67 MB/sec execute 62 sec latency 42.306 ms 1 7374 0.72 MB/sec execute 63 sec latency 13.829 ms 1 7636 0.72 MB/sec execute 64 sec latency 13.003 ms 1 7902 0.71 MB/sec execute 65 sec latency 67.007 ms 1 8194 0.73 MB/sec execute 66 sec latency 38.750 ms 1 8590 0.76 MB/sec execute 67 sec latency 34.140 ms 1 8870 0.75 MB/sec execute 68 sec latency 53.962 ms 1 9131 0.75 MB/sec execute 69 sec latency 40.405 ms 1 9481 0.76 MB/sec execute 70 sec latency 43.314 ms 1 9981 0.80 MB/sec execute 71 sec latency 35.729 ms 1 10477 0.84 MB/sec execute 72 sec latency 38.330 ms 1 10898 0.89 MB/sec execute 73 sec latency 14.212 ms 1 11139 0.88 MB/sec execute 74 sec latency 14.808 ms 1 11386 0.87 MB/sec execute 75 sec latency 90.262 ms 1 11638 0.87 MB/sec execute 76 sec latency 42.021 ms 1 11941 0.87 MB/sec execute 77 sec latency 27.332 ms 1 12287 0.90 MB/sec execute 78 sec latency 37.967 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Sun Apr 13 05:39:28 EDT 2025 with return code 0 19201 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 19201 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished