== replay-dual test 26: dbench and tar with mds failover ========================================================== 13:46:39 (1747849599) Starting client oleg411-client.virtnet: -o user_xattr,flock 192.168.204.111@tcp:/lustre /mnt/lustre Started clients oleg411-client.virtnet: 192.168.204.111@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 17237 Started dbench loop with 17238 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 May 21 13:46:41 EDT 2025 waiting for dbench pid 17269 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 1 247 9.39 MB/sec warmup 1 sec latency 21.783 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 1928 1285760 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 1404 3605616 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 25976 3555640 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27380 7161256 1% /mnt/lustre 1 469 8.21 MB/sec warmup 2 sec latency 24.859 ms 1 738 7.10 MB/sec warmup 3 sec latency 49.652 ms 1 991 5.48 MB/sec warmup 4 sec latency 16.958 ms test_26 fail mds1 1 times 1 1277 4.63 MB/sec warmup 5 sec latency 19.506 ms Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 1576 4.35 MB/sec warmup 6 sec latency 145.483 ms 13:46:47 (1747849607) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 1576 3.73 MB/sec warmup 7 sec latency 1145.642 ms 1 1576 3.27 MB/sec warmup 8 sec latency 2145.795 ms 1 1576 2.90 MB/sec warmup 9 sec latency 3145.960 ms 1 1576 2.61 MB/sec warmup 10 sec latency 4146.130 ms 1 1576 2.38 MB/sec warmup 11 sec latency 5146.286 ms 1 1576 2.18 MB/sec warmup 12 sec latency 6146.426 ms 1 1576 2.01 MB/sec warmup 13 sec latency 7146.570 ms 1 1576 1.87 MB/sec warmup 14 sec latency 8146.731 ms 1 1576 1.74 MB/sec warmup 15 sec latency 9146.919 ms 1 1576 1.63 MB/sec warmup 16 sec latency 10147.183 ms Failover mds1 to oleg411-server mount facets: mds1 1 1576 1.54 MB/sec warmup 17 sec latency 11147.448 ms 1 1576 1.45 MB/sec warmup 18 sec latency 12147.631 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1576 1.38 MB/sec warmup 19 sec latency 13147.801 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:47:01 (1747849621) targets are mounted 13:47:01 (1747849621) facet_failover done 1 1576 0.00 MB/sec execute 1 sec latency 15148.116 ms 1 1576 0.00 MB/sec execute 2 sec latency 16148.250 ms 1 1576 0.00 MB/sec execute 3 sec latency 17148.361 ms 1 1616 0.01 MB/sec execute 4 sec latency 17902.041 ms oleg411-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 1834 0.04 MB/sec execute 5 sec latency 25.764 ms 1 2098 0.09 MB/sec execute 6 sec latency 24.956 ms 1 2348 0.25 MB/sec execute 7 sec latency 54.390 ms 1 2764 0.73 MB/sec execute 8 sec latency 16.739 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2380 1285308 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 8744 3591616 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 35204 3565724 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 43948 7157340 1% /mnt/lustre 1 3297 1.02 MB/sec execute 9 sec latency 16.718 ms 1 3707 1.26 MB/sec execute 10 sec latency 18.179 ms 1 3948 1.27 MB/sec execute 11 sec latency 16.599 ms 1 4214 1.17 MB/sec execute 12 sec latency 16.854 ms test_26 fail mds1 2 times Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 4480 1.13 MB/sec execute 13 sec latency 23.081 ms 13:47:15 (1747849635) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 4539 1.06 MB/sec execute 14 sec latency 780.739 ms 1 4539 0.99 MB/sec execute 15 sec latency 1780.909 ms 1 4539 0.92 MB/sec execute 16 sec latency 2781.059 ms 1 4539 0.87 MB/sec execute 17 sec latency 3781.215 ms 1 4539 0.82 MB/sec execute 18 sec latency 4781.363 ms 1 4539 0.78 MB/sec execute 19 sec latency 5781.567 ms 1 4539 0.74 MB/sec execute 20 sec latency 6781.700 ms 1 4539 0.70 MB/sec execute 21 sec latency 7781.861 ms 1 4539 0.67 MB/sec execute 22 sec latency 8782.028 ms 1 4539 0.64 MB/sec execute 23 sec latency 9782.216 ms Failover mds1 to oleg411-server mount facets: mds1 1 4539 0.62 MB/sec execute 24 sec latency 10782.349 ms 1 4539 0.59 MB/sec execute 25 sec latency 11782.521 ms 1 4539 0.57 MB/sec execute 26 sec latency 12782.651 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 4539 0.55 MB/sec execute 27 sec latency 13782.837 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:47:28 (1747849648) targets are mounted 13:47:28 (1747849648) facet_failover done 1 4539 0.53 MB/sec execute 28 sec latency 14783.047 ms 1 4539 0.51 MB/sec execute 29 sec latency 15783.244 ms 1 4539 0.49 MB/sec execute 30 sec latency 16783.485 ms 1 4539 0.48 MB/sec execute 31 sec latency 17783.702 ms 1 4539 0.46 MB/sec execute 32 sec latency 18783.832 ms 1 4539 0.45 MB/sec execute 33 sec latency 19783.934 ms oleg411-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 4772 0.47 MB/sec execute 34 sec latency 19989.405 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5118 0.55 MB/sec execute 35 sec latency 20.675 ms 1 5379 0.54 MB/sec execute 36 sec latency 15.821 ms 1 5695 0.53 MB/sec execute 37 sec latency 20.717 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3032 1284656 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 15968 3578964 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 41000 3555532 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 56968 7134496 1% /mnt/lustre 1 5988 0.55 MB/sec execute 38 sec latency 22.841 ms 1 6474 0.68 MB/sec execute 39 sec latency 17.332 ms 1 6801 0.69 MB/sec execute 40 sec latency 454.718 ms 1 7247 0.77 MB/sec execute 41 sec latency 13.134 ms test_26 fail mds1 3 times 1 7503 0.79 MB/sec execute 42 sec latency 17.272 ms Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 7638 0.77 MB/sec execute 43 sec latency 414.127 ms 13:47:44 (1747849664) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 7638 0.75 MB/sec execute 44 sec latency 1414.291 ms 1 7638 0.73 MB/sec execute 45 sec latency 2414.443 ms 1 7638 0.72 MB/sec execute 46 sec latency 3414.608 ms 1 7638 0.70 MB/sec execute 47 sec latency 4414.782 ms 1 7638 0.69 MB/sec execute 48 sec latency 5414.943 ms 1 7638 0.67 MB/sec execute 49 sec latency 6415.103 ms 1 7638 0.66 MB/sec execute 50 sec latency 7415.249 ms 1 7638 0.65 MB/sec execute 51 sec latency 8415.411 ms 1 7638 0.64 MB/sec execute 52 sec latency 9415.576 ms 1 7638 0.62 MB/sec execute 53 sec latency 10415.720 ms Failover mds1 to oleg411-server mount facets: mds1 1 7638 0.61 MB/sec execute 54 sec latency 11415.940 ms 1 7638 0.60 MB/sec execute 55 sec latency 12416.102 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7638 0.59 MB/sec execute 56 sec latency 13416.265 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all 1 7638 0.58 MB/sec execute 57 sec latency 14416.412 ms pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:47:58 (1747849678) targets are mounted 13:47:58 (1747849678) facet_failover done 1 7638 0.57 MB/sec execute 58 sec latency 15416.602 ms 1 7638 0.56 MB/sec execute 59 sec latency 16416.782 ms 1 7638 0.55 MB/sec execute 60 sec latency 17417.089 ms 1 7638 0.54 MB/sec execute 61 sec latency 18417.275 ms 1 7638 0.53 MB/sec execute 62 sec latency 19417.404 ms 1 7638 0.52 MB/sec execute 63 sec latency 20417.505 ms oleg411-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 7792 0.52 MB/sec execute 64 sec latency 20684.318 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8024 0.52 MB/sec execute 65 sec latency 24.508 ms 1 8298 0.53 MB/sec execute 66 sec latency 19.402 ms 1 8611 0.57 MB/sec execute 67 sec latency 30.705 ms 1 8864 0.56 MB/sec execute 68 sec latency 18.586 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3624 1284064 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 17676 3584704 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 42588 3558492 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 60264 7143196 1% /mnt/lustre 1 9129 0.56 MB/sec execute 69 sec latency 18.748 ms 1 9471 0.57 MB/sec execute 70 sec latency 21.285 ms 1 9852 0.62 MB/sec execute 71 sec latency 19.130 ms 1 10312 0.64 MB/sec execute 72 sec latency 27.799 ms test_26 fail mds1 4 times Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 10732 0.69 MB/sec execute 73 sec latency 16.860 ms 13:48:14 (1747849694) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 10735 0.69 MB/sec execute 74 sec latency 995.957 ms 1 10735 0.68 MB/sec execute 75 sec latency 1996.112 ms 1 10735 0.67 MB/sec execute 76 sec latency 2996.281 ms 1 10735 0.66 MB/sec execute 77 sec latency 3996.483 ms 1 10735 0.65 MB/sec execute 78 sec latency 4996.626 ms 1 10735 0.64 MB/sec execute 79 sec latency 5996.786 ms 1 10735 0.63 MB/sec execute 80 sec latency 6996.963 ms 1 10735 0.63 MB/sec execute 81 sec latency 7997.147 ms 1 10735 0.62 MB/sec execute 82 sec latency 8997.384 ms 1 10735 0.61 MB/sec execute 83 sec latency 9997.538 ms Failover mds1 to oleg411-server mount facets: mds1 1 10735 0.60 MB/sec execute 84 sec latency 10997.713 ms 1 10735 0.60 MB/sec execute 85 sec latency 11997.895 ms 1 10735 0.59 MB/sec execute 86 sec latency 12998.045 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 10735 0.58 MB/sec execute 87 sec latency 13998.190 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:48:29 (1747849709) targets are mounted 13:48:29 (1747849709) facet_failover done 1 10735 0.58 MB/sec execute 88 sec latency 14998.408 ms 1 10735 0.57 MB/sec execute 89 sec latency 15998.529 ms 1 10735 0.56 MB/sec execute 90 sec latency 16998.726 ms 1 10735 0.56 MB/sec execute 91 sec latency 17998.915 ms 1 10735 0.55 MB/sec execute 92 sec latency 18999.039 ms 1 10735 0.55 MB/sec execute 93 sec latency 19999.183 ms 1 10837 0.55 MB/sec execute 94 sec latency 20565.884 ms oleg411-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 11049 0.55 MB/sec execute 95 sec latency 16.764 ms 1 11232 0.54 MB/sec execute 96 sec latency 25.347 ms 1 11446 0.54 MB/sec execute 97 sec latency 34.876 ms 1 11678 0.55 MB/sec execute 98 sec latency 23.280 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4108 1283580 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 27272 3575296 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 43912 3552420 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 71184 7127716 1% /mnt/lustre 1 11930 0.55 MB/sec execute 99 sec latency 22.877 ms 1 cleanup 100 sec 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1819 30.586 19989.390 Close 1336 1.711 7.160 Rename 78 15.073 25.905 Unlink 370 4.674 25.653 Qpathinfo 1671 27.592 20684.299 Qfileinfo 288 0.473 3.032 Qfsinfo 306 0.531 2.376 Sfileinfo 150 9.222 15.447 Find 642 1.261 14.852 WriteX 902 2.204 8.531 ReadX 2871 0.182 47.529 LockX 6 1.641 1.894 UnlockX 6 1.636 1.864 Flush 129 16.239 454.704 Throughput 0.549047 MB/sec 1 clients 1 procs max_latency=20684.318 ms stopping dbench on /mnt/lustre at Wed May 21 13:48:41 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 Wed May 21 13:48:43 EDT 2025 waiting for dbench pid 21860 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 Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 215 8.36 MB/sec warmup 1 sec latency 84.989 ms 13:48:44 (1747849724) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 215 4.18 MB/sec warmup 2 sec latency 1085.163 ms 1 215 2.79 MB/sec warmup 3 sec latency 2085.387 ms 1 215 2.09 MB/sec warmup 4 sec latency 3085.571 ms 1 215 1.67 MB/sec warmup 5 sec latency 4085.689 ms 1 215 1.39 MB/sec warmup 6 sec latency 5085.837 ms 1 215 1.19 MB/sec warmup 7 sec latency 6086.003 ms 1 215 1.05 MB/sec warmup 8 sec latency 7086.169 ms 1 215 0.93 MB/sec warmup 9 sec latency 8086.377 ms 1 215 0.84 MB/sec warmup 10 sec latency 9086.492 ms 1 215 0.76 MB/sec warmup 11 sec latency 10086.643 ms Failover mds1 to oleg411-server mount facets: mds1 1 215 0.70 MB/sec warmup 12 sec latency 11086.781 ms 1 215 0.64 MB/sec warmup 13 sec latency 12086.931 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 215 0.60 MB/sec warmup 14 sec latency 13087.066 ms 1 215 0.56 MB/sec warmup 15 sec latency 14087.242 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:48:58 (1747849738) targets are mounted 13:48:58 (1747849738) facet_failover done 1 215 0.52 MB/sec warmup 16 sec latency 15087.399 ms 1 215 0.49 MB/sec warmup 17 sec latency 16087.720 ms 1 215 0.46 MB/sec warmup 18 sec latency 17087.860 ms 1 215 0.44 MB/sec warmup 19 sec latency 18088.049 ms 1 215 0.00 MB/sec execute 1 sec latency 20088.351 ms oleg411-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 1 434 3.45 MB/sec execute 2 sec latency 20182.483 ms 1 711 4.28 MB/sec execute 3 sec latency 25.476 ms 1 934 3.35 MB/sec execute 4 sec latency 18.375 ms 1 1181 2.93 MB/sec execute 5 sec latency 19.720 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4492 1283196 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 44788 3544824 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 8160 3574832 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 52948 7119656 1% /mnt/lustre 1 1512 2.95 MB/sec execute 6 sec latency 40.693 ms 1 1808 2.57 MB/sec execute 7 sec latency 19.527 ms 1 2046 2.28 MB/sec execute 8 sec latency 177.643 ms 1 2368 2.17 MB/sec execute 9 sec latency 28.489 ms test_26 fail mds1 6 times 1 2768 2.36 MB/sec execute 10 sec latency 17.581 ms Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 3189 2.35 MB/sec execute 11 sec latency 261.674 ms 13:49:14 (1747849754) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 3189 2.16 MB/sec execute 12 sec latency 1261.877 ms 1 3189 1.99 MB/sec execute 13 sec latency 2262.067 ms 1 3189 1.85 MB/sec execute 14 sec latency 3262.233 ms 1 3189 1.73 MB/sec execute 15 sec latency 4262.428 ms 1 3189 1.62 MB/sec execute 16 sec latency 5262.616 ms 1 3189 1.52 MB/sec execute 17 sec latency 6262.777 ms 1 3189 1.44 MB/sec execute 18 sec latency 7262.924 ms 1 3189 1.36 MB/sec execute 19 sec latency 8263.096 ms 1 3189 1.29 MB/sec execute 20 sec latency 9263.278 ms 1 3189 1.23 MB/sec execute 21 sec latency 10263.423 ms Failover mds1 to oleg411-server mount facets: mds1 1 3189 1.18 MB/sec execute 22 sec latency 11263.590 ms 1 3189 1.13 MB/sec execute 23 sec latency 12263.797 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 3189 1.08 MB/sec execute 24 sec latency 13263.945 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all 1 3189 1.04 MB/sec execute 25 sec latency 14264.084 ms pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:49:28 (1747849768) targets are mounted 13:49:28 (1747849768) facet_failover done 1 3189 1.00 MB/sec execute 26 sec latency 15264.252 ms 1 3189 0.96 MB/sec execute 27 sec latency 16264.460 ms 1 3189 0.92 MB/sec execute 28 sec latency 17264.732 ms 1 3189 0.89 MB/sec execute 29 sec latency 18264.969 ms 1 3189 0.86 MB/sec execute 30 sec latency 19265.162 ms 1 3202 0.84 MB/sec execute 31 sec latency 20228.906 ms oleg411-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 3640 0.95 MB/sec execute 32 sec latency 15.885 ms 1 3883 0.95 MB/sec execute 33 sec latency 21.594 ms 1 4096 0.93 MB/sec execute 34 sec latency 15.592 ms 1 4306 0.92 MB/sec execute 35 sec latency 54.645 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 3760 1283928 1% /mnt/lustre[MDT:0] lustre-OST0000_UUID 3833116 53316 3547244 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 15904 3580732 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 69220 7127976 1% /mnt/lustre 1 4538 0.90 MB/sec execute 36 sec latency 25.128 ms 1 4810 0.91 MB/sec execute 37 sec latency 18.903 ms 1 5135 0.97 MB/sec execute 38 sec latency 36.310 ms 1 5370 0.95 MB/sec execute 39 sec latency 19.095 ms test_26 fail mds1 7 times 1 5670 0.94 MB/sec execute 40 sec latency 24.225 ms Failing mds1 on oleg411-server Stopping /mnt/lustre-mds1 (opts:) on oleg411-server 1 5902 0.94 MB/sec execute 41 sec latency 354.558 ms 13:49:44 (1747849784) shut down facet: mds1 facet_host: oleg411-server facet_failover_host: oleg411-server 1 5902 0.92 MB/sec execute 42 sec latency 1354.706 ms 1 5902 0.90 MB/sec execute 43 sec latency 2354.859 ms 1 5902 0.88 MB/sec execute 44 sec latency 3355.020 ms 1 5902 0.86 MB/sec execute 45 sec latency 4355.195 ms 1 5902 0.84 MB/sec execute 46 sec latency 5355.372 ms 1 5902 0.82 MB/sec execute 47 sec latency 6355.544 ms 1 5902 0.80 MB/sec execute 48 sec latency 7355.683 ms 1 5902 0.79 MB/sec execute 49 sec latency 8355.864 ms 1 5902 0.77 MB/sec execute 50 sec latency 9356.036 ms 1 5902 0.76 MB/sec execute 51 sec latency 10356.259 ms Failover mds1 to oleg411-server mount facets: mds1 1 5902 0.74 MB/sec execute 52 sec latency 11356.408 ms 1 5902 0.73 MB/sec execute 53 sec latency 12356.538 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 5902 0.71 MB/sec execute 54 sec latency 13356.739 ms oleg411-server: oleg411-server.virtnet: executing set_default_debug -1 all 1 5902 0.70 MB/sec execute 55 sec latency 14356.987 ms pdsh@oleg411-client: oleg411-server: ssh exited with exit code 1 Started lustre-MDT0000 13:49:58 (1747849798) targets are mounted 13:49:58 (1747849798) facet_failover done 1 5902 0.69 MB/sec execute 56 sec latency 15357.212 ms 1 5902 0.68 MB/sec execute 57 sec latency 16357.405 ms 1 5902 0.67 MB/sec execute 58 sec latency 17357.560 ms 1 5902 0.65 MB/sec execute 59 sec latency 18357.726 ms 1 5902 0.64 MB/sec execute 60 sec latency 19357.861 ms 1 5929 0.63 MB/sec execute 61 sec latency 20199.472 ms oleg411-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 6317 0.69 MB/sec execute 62 sec latency 20.176 ms 1 6800 0.72 MB/sec execute 63 sec latency 25.032 ms 1 7226 0.77 MB/sec execute 64 sec latency 14.489 ms 1 7464 0.78 MB/sec execute 65 sec latency 15.636 ms 1 7690 0.77 MB/sec execute 66 sec latency 16.366 ms 1 7921 0.77 MB/sec execute 67 sec latency 48.961 ms 1 8170 0.78 MB/sec execute 68 sec latency 29.647 ms 1 8512 0.81 MB/sec execute 69 sec latency 17.889 ms 1 8740 0.80 MB/sec execute 70 sec latency 28.679 ms 1 8959 0.79 MB/sec execute 71 sec latency 30.195 ms 1 9262 0.79 MB/sec execute 72 sec latency 32.489 ms 1 9545 0.79 MB/sec execute 73 sec latency 28.659 ms 1 10016 0.86 MB/sec execute 74 sec latency 22.465 ms dbench killed by signal 15 stopping dbench on /mnt/lustre at Wed May 21 13:50:18 EDT 2025 with return code 0 21860 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 21860 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished