== replay-dual test 26: dbench and tar with mds failover ========================================================== 04:12:15 (1749543135) Starting client oleg313-client.virtnet: -o user_xattr,flock 192.168.203.113@tcp:/lustre /mnt/lustre Started clients oleg313-client.virtnet: 192.168.203.113@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 5089 Started dbench loop with 5090 striped dir -i0 -c2 -H fnv_1a_64 /mnt/lustre2/d26.replay-dual/run_dbench striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar 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 Tue Jun 10 04:12:16 EDT 2025 waiting for dbench pid 5131 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 1 262 9.92 MB/sec warmup 1 sec latency 23.487 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2292 1285396 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2100 1285588 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 26120 3555900 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 1536 3605484 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 27656 7161384 1% /mnt/lustre 1 501 8.73 MB/sec warmup 2 sec latency 22.431 ms 1 736 7.10 MB/sec warmup 3 sec latency 289.978 ms 1 992 5.48 MB/sec warmup 4 sec latency 18.614 ms test_26 fail mds1 1 times 1 1396 5.20 MB/sec warmup 5 sec latency 17.381 ms Failing mds1 on oleg313-server Stopping /mnt/lustre-mds1 (opts:) on oleg313-server 1 1603 4.36 MB/sec warmup 6 sec latency 308.270 ms 04:12:23 (1749543143) shut down facet: mds1 facet_host: oleg313-server facet_failover_host: oleg313-server 1 1603 3.74 MB/sec warmup 7 sec latency 1308.490 ms 1 1603 3.27 MB/sec warmup 8 sec latency 2308.703 ms 1 1603 2.91 MB/sec warmup 9 sec latency 3308.882 ms 1 1603 2.62 MB/sec warmup 10 sec latency 4309.079 ms 1 1603 2.38 MB/sec warmup 11 sec latency 5309.300 ms 1 1603 2.18 MB/sec warmup 12 sec latency 6309.478 ms 1 1603 2.01 MB/sec warmup 13 sec latency 7309.698 ms 1 1603 1.87 MB/sec warmup 14 sec latency 8309.867 ms 1 1603 1.74 MB/sec warmup 15 sec latency 9310.034 ms 1 1603 1.63 MB/sec warmup 16 sec latency 10310.219 ms Failover mds1 to oleg313-server mount facets: mds1 1 1603 1.54 MB/sec warmup 17 sec latency 11310.397 ms 1 1603 1.45 MB/sec warmup 18 sec latency 12310.559 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 1603 1.38 MB/sec warmup 19 sec latency 13310.663 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 Started lustre-MDT0000 04:12:36 (1749543156) targets are mounted 04:12:36 (1749543156) facet_failover done 1 1603 0.00 MB/sec execute 1 sec latency 15310.943 ms 1 1603 0.00 MB/sec execute 2 sec latency 16311.181 ms 1 1603 0.00 MB/sec execute 3 sec latency 17311.460 ms 1 1603 0.00 MB/sec execute 4 sec latency 18311.644 ms oleg313-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 1772 0.02 MB/sec execute 5 sec latency 18751.919 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2098 0.08 MB/sec execute 6 sec latency 21.342 ms 1 2347 0.25 MB/sec execute 7 sec latency 28.463 ms 1 2488 0.32 MB/sec execute 8 sec latency 29.424 ms 1 2876 0.67 MB/sec execute 9 sec latency 31.441 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2924 1284764 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2592 1285096 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 30088 3568444 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 5020 3594488 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 35108 7162932 1% /mnt/lustre 1 3204 0.81 MB/sec execute 10 sec latency 27.282 ms 1 3538 1.11 MB/sec execute 11 sec latency 27.613 ms 1 3797 1.13 MB/sec execute 12 sec latency 25.532 ms 1 3971 1.07 MB/sec execute 13 sec latency 23.913 ms test_26 fail mds2 2 times 1 4112 0.99 MB/sec execute 14 sec latency 22.931 ms Failing mds2 on oleg313-server Stopping /mnt/lustre-mds2 (opts:) on oleg313-server 1 4365 0.96 MB/sec execute 15 sec latency 43.601 ms 04:12:52 (1749543172) shut down facet: mds2 facet_host: oleg313-server facet_failover_host: oleg313-server 1 4564 0.93 MB/sec execute 16 sec latency 66.930 ms 1 4564 0.87 MB/sec execute 17 sec latency 1067.154 ms 1 4564 0.83 MB/sec execute 18 sec latency 2067.293 ms 1 4564 0.78 MB/sec execute 19 sec latency 3067.441 ms 1 4564 0.74 MB/sec execute 20 sec latency 4067.662 ms 1 4564 0.71 MB/sec execute 21 sec latency 5067.818 ms 1 4564 0.68 MB/sec execute 22 sec latency 6067.968 ms 1 4564 0.65 MB/sec execute 23 sec latency 7068.138 ms 1 4564 0.62 MB/sec execute 24 sec latency 8068.319 ms 1 4564 0.59 MB/sec execute 25 sec latency 9068.443 ms Failover mds2 to oleg313-server mount facets: mds2 1 4564 0.57 MB/sec execute 26 sec latency 10068.645 ms 1 4564 0.55 MB/sec execute 27 sec latency 11068.815 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4564 0.53 MB/sec execute 28 sec latency 12068.957 ms 1 4564 0.51 MB/sec execute 29 sec latency 13069.150 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 Started lustre-MDT0001 04:13:06 (1749543186) targets are mounted 04:13:06 (1749543186) facet_failover done 1 4564 0.50 MB/sec execute 30 sec latency 14069.320 ms 1 4564 0.48 MB/sec execute 31 sec latency 15069.496 ms 1 4564 0.46 MB/sec execute 32 sec latency 16069.736 ms 1 4564 0.45 MB/sec execute 33 sec latency 17069.936 ms 1 4564 0.44 MB/sec execute 34 sec latency 18070.151 ms oleg313-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 4818 0.46 MB/sec execute 35 sec latency 18198.577 ms 1 5075 0.53 MB/sec execute 36 sec latency 38.481 ms 1 5245 0.52 MB/sec execute 37 sec latency 29.771 ms 1 5489 0.51 MB/sec execute 38 sec latency 24.313 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4068 1283620 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2428 1285260 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 39108 3555788 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 11772 3580592 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 50880 7136380 1% /mnt/lustre 1 5771 0.51 MB/sec execute 39 sec latency 16.107 ms 1 6014 0.53 MB/sec execute 40 sec latency 21.988 ms 1 6431 0.61 MB/sec execute 41 sec latency 24.051 ms 1 6815 0.67 MB/sec execute 42 sec latency 30.385 ms test_26 fail mds1 3 times 1 7191 0.73 MB/sec execute 43 sec latency 19.818 ms Failing mds1 on oleg313-server Stopping /mnt/lustre-mds1 (opts:) on oleg313-server 1 7361 0.74 MB/sec execute 44 sec latency 50.833 ms 04:13:21 (1749543201) shut down facet: mds1 facet_host: oleg313-server facet_failover_host: oleg313-server 1 7535 0.73 MB/sec execute 45 sec latency 21.472 ms 1 7627 0.72 MB/sec execute 46 sec latency 315.017 ms 1 7627 0.70 MB/sec execute 47 sec latency 1315.220 ms 1 7627 0.69 MB/sec execute 48 sec latency 2315.545 ms 1 7627 0.67 MB/sec execute 49 sec latency 3315.864 ms 1 7627 0.66 MB/sec execute 50 sec latency 4316.171 ms 1 7627 0.65 MB/sec execute 51 sec latency 5316.544 ms 1 7627 0.64 MB/sec execute 52 sec latency 6316.776 ms 1 7627 0.62 MB/sec execute 53 sec latency 7316.969 ms 1 7627 0.61 MB/sec execute 54 sec latency 8317.334 ms 1 7627 0.60 MB/sec execute 55 sec latency 9317.546 ms Failover mds1 to oleg313-server mount facets: mds1 1 7627 0.59 MB/sec execute 56 sec latency 10317.768 ms 1 7627 0.58 MB/sec execute 57 sec latency 11318.004 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7627 0.57 MB/sec execute 58 sec latency 12318.159 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all 1 7627 0.56 MB/sec execute 59 sec latency 13318.396 ms pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 Started lustre-MDT0000 04:13:36 (1749543216) targets are mounted 04:13:36 (1749543216) facet_failover done 1 7627 0.55 MB/sec execute 60 sec latency 14318.738 ms 1 7627 0.54 MB/sec execute 61 sec latency 15319.031 ms 1 7627 0.53 MB/sec execute 62 sec latency 16319.344 ms 1 7627 0.52 MB/sec execute 63 sec latency 17319.519 ms 1 7627 0.52 MB/sec execute 64 sec latency 18319.664 ms 1 7627 0.51 MB/sec execute 65 sec latency 19319.773 ms oleg313-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 7844 0.51 MB/sec execute 66 sec latency 19582.376 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 8075 0.51 MB/sec execute 67 sec latency 21.719 ms 1 8308 0.52 MB/sec execute 68 sec latency 29.450 ms 1 8647 0.55 MB/sec execute 69 sec latency 19.818 ms 1 8819 0.55 MB/sec execute 70 sec latency 35.069 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 4512 1283176 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2544 1285144 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 40692 3552540 2% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 11840 3576036 1% /mnt/lustre[OST:1] filesystem_summary: 7666232 52532 7128576 1% /mnt/lustre 1 9065 0.54 MB/sec execute 71 sec latency 20.136 ms 1 9328 0.54 MB/sec execute 72 sec latency 18.076 ms 1 9593 0.56 MB/sec execute 73 sec latency 36.361 ms 1 10025 0.62 MB/sec execute 74 sec latency 23.567 ms test_26 fail mds2 4 times Failing mds2 on oleg313-server Stopping /mnt/lustre-mds2 (opts:) on oleg313-server 1 10478 0.63 MB/sec execute 75 sec latency 31.219 ms 1 10497 0.63 MB/sec execute 76 sec latency 968.034 ms 1 10497 0.62 MB/sec execute 77 sec latency 1968.430 ms 1 10497 0.61 MB/sec execute 78 sec latency 2968.719 ms 1 10497 0.60 MB/sec execute 79 sec latency 3969.003 ms 1 10497 0.59 MB/sec execute 80 sec latency 4969.368 ms 1 10497 0.59 MB/sec execute 81 sec latency 5969.605 ms 04:13:58 (1749543238) shut down facet: mds2 facet_host: oleg313-server facet_failover_host: oleg313-server 1 10497 0.58 MB/sec execute 82 sec latency 6969.879 ms 1 10497 0.57 MB/sec execute 83 sec latency 7970.175 ms 1 10497 0.57 MB/sec execute 84 sec latency 8970.492 ms 1 10497 0.56 MB/sec execute 85 sec latency 9970.763 ms 1 10497 0.55 MB/sec execute 86 sec latency 10971.047 ms 1 10497 0.55 MB/sec execute 87 sec latency 11971.428 ms 1 10497 0.54 MB/sec execute 88 sec latency 12971.684 ms 1 10497 0.53 MB/sec execute 89 sec latency 13971.960 ms 1 10497 0.53 MB/sec execute 90 sec latency 14972.242 ms 1 10497 0.52 MB/sec execute 91 sec latency 15972.579 ms Failover mds2 to oleg313-server mount facets: mds2 1 10497 0.52 MB/sec execute 92 sec latency 16972.746 ms 1 10497 0.51 MB/sec execute 93 sec latency 17972.977 ms 1 10497 0.51 MB/sec execute 94 sec latency 18973.204 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 10497 0.50 MB/sec execute 95 sec latency 19973.538 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 Started lustre-MDT0001 04:14:12 (1749543252) targets are mounted 04:14:12 (1749543252) facet_failover done 1 10497 0.50 MB/sec execute 96 sec latency 20973.773 ms 1 10497 0.49 MB/sec execute 97 sec latency 21973.955 ms 1 10497 0.49 MB/sec execute 98 sec latency 22974.283 ms 1 10497 0.48 MB/sec execute 99 sec latency 23974.566 ms 1 cleanup 100 sec oleg313-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 cleanup 101 sec 0 cleanup 101 sec Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 1481 40.769 25430.483 Close 1117 2.070 6.155 Rename 64 18.930 36.338 Unlink 280 5.745 16.727 Qpathinfo 1402 16.555 18751.907 Qfileinfo 259 0.550 2.953 Qfsinfo 248 1.107 10.288 Sfileinfo 116 10.278 22.251 Find 559 37.619 19582.364 WriteX 774 2.583 13.826 ReadX 2479 0.097 4.335 LockX 6 2.111 3.211 UnlockX 6 2.086 2.874 Flush 104 10.336 38.456 Throughput 0.480422 MB/sec 1 clients 1 procs max_latency=23974.566 ms stopping dbench on /mnt/lustre at Tue Jun 10 04:14:18 EDT 2025 with return code 0 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec striped dir -i0 -c2 -H fnv_1a_64 /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 Tue Jun 10 04:14:19 EDT 2025 waiting for dbench pid 9596 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 1 238 9.14 MB/sec warmup 1 sec latency 26.960 ms 1 493 8.60 MB/sec warmup 2 sec latency 22.832 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5176 1282512 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3260 1284428 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20036 3566732 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 35892 3540108 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 55928 7106840 1% /mnt/lustre 1 798 7.16 MB/sec warmup 3 sec latency 22.365 ms 1 980 5.47 MB/sec warmup 4 sec latency 192.085 ms 1 1255 4.62 MB/sec warmup 5 sec latency 294.985 ms 1 1625 4.36 MB/sec warmup 6 sec latency 21.124 ms test_26 fail mds1 5 times Failing mds1 on oleg313-server 1 1924 3.78 MB/sec warmup 7 sec latency 20.723 ms Stopping /mnt/lustre-mds1 (opts:) on oleg313-server 1 2000 3.31 MB/sec warmup 8 sec latency 665.391 ms 04:14:28 (1749543268) shut down facet: mds1 facet_host: oleg313-server facet_failover_host: oleg313-server 1 2000 2.94 MB/sec warmup 9 sec latency 1665.671 ms 1 2000 2.65 MB/sec warmup 10 sec latency 2665.980 ms 1 2000 2.41 MB/sec warmup 11 sec latency 3666.298 ms 1 2000 2.21 MB/sec warmup 12 sec latency 4666.562 ms 1 2000 2.04 MB/sec warmup 13 sec latency 5666.775 ms 1 2000 1.89 MB/sec warmup 14 sec latency 6667.055 ms 1 2000 1.77 MB/sec warmup 15 sec latency 7667.349 ms 1 2000 1.66 MB/sec warmup 16 sec latency 8667.593 ms 1 2000 1.56 MB/sec warmup 17 sec latency 9667.953 ms 1 2000 1.47 MB/sec warmup 18 sec latency 10668.341 ms Failover mds1 to oleg313-server mount facets: mds1 1 2000 1.39 MB/sec warmup 19 sec latency 11668.569 ms 1 2000 0.00 MB/sec execute 1 sec latency 13668.874 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 2000 0.00 MB/sec execute 2 sec latency 14669.064 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all 1 2000 0.00 MB/sec execute 3 sec latency 15669.454 ms pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 Started lustre-MDT0000 04:14:43 (1749543283) targets are mounted 04:14:43 (1749543283) facet_failover done 1 2000 0.00 MB/sec execute 4 sec latency 16669.792 ms 1 2000 0.00 MB/sec execute 5 sec latency 17670.046 ms 1 2000 0.00 MB/sec execute 6 sec latency 18670.302 ms 1 2000 0.00 MB/sec execute 7 sec latency 19670.453 ms oleg313-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0000-mdc-*.mds_server_uuid 1 2148 0.02 MB/sec execute 8 sec latency 20189.109 ms mdc.lustre-MDT0000-mdc-*.mds_server_uuid in FULL state after 0 sec 1 2449 0.18 MB/sec execute 9 sec latency 25.671 ms 1 2932 0.70 MB/sec execute 10 sec latency 27.417 ms 1 3529 1.08 MB/sec execute 11 sec latency 20.341 ms 1 3796 1.11 MB/sec execute 12 sec latency 24.765 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 5208 1282480 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 3196 1284492 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 20408 3569016 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 38220 3558180 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 58628 7127196 1% /mnt/lustre 1 3979 1.04 MB/sec execute 13 sec latency 32.230 ms 1 4211 0.98 MB/sec execute 14 sec latency 19.774 ms 1 4434 0.95 MB/sec execute 15 sec latency 34.783 ms 1 4589 0.94 MB/sec execute 16 sec latency 39.548 ms test_26 fail mds2 6 times Failing mds2 on oleg313-server 1 4787 0.92 MB/sec execute 17 sec latency 26.033 ms Stopping /mnt/lustre-mds2 (opts:) on oleg313-server 1 4999 1.04 MB/sec execute 18 sec latency 453.346 ms 1 4999 0.98 MB/sec execute 19 sec latency 1453.524 ms 1 4999 0.93 MB/sec execute 20 sec latency 2453.683 ms 1 4999 0.89 MB/sec execute 21 sec latency 3453.845 ms 1 4999 0.85 MB/sec execute 22 sec latency 4453.951 ms 1 4999 0.81 MB/sec execute 23 sec latency 5454.044 ms 04:15:03 (1749543303) shut down facet: mds2 facet_host: oleg313-server facet_failover_host: oleg313-server 1 4999 0.78 MB/sec execute 24 sec latency 6454.129 ms 1 4999 0.75 MB/sec execute 25 sec latency 7454.298 ms 1 4999 0.72 MB/sec execute 26 sec latency 8454.509 ms 1 4999 0.69 MB/sec execute 27 sec latency 9454.718 ms 1 4999 0.67 MB/sec execute 28 sec latency 10454.883 ms 1 4999 0.64 MB/sec execute 29 sec latency 11455.079 ms 1 4999 0.62 MB/sec execute 30 sec latency 12455.229 ms 1 4999 0.60 MB/sec execute 31 sec latency 13455.369 ms 1 4999 0.58 MB/sec execute 32 sec latency 14455.587 ms 1 4999 0.56 MB/sec execute 33 sec latency 15455.748 ms Failover mds2 to oleg313-server mount facets: mds2 1 4999 0.55 MB/sec execute 34 sec latency 16455.933 ms 1 4999 0.53 MB/sec execute 35 sec latency 17456.087 ms 1 4999 0.52 MB/sec execute 36 sec latency 18456.270 ms Start mds2: mount -t lustre -o localrecov /dev/mapper/mds2_flakey /mnt/lustre-mds2 1 4999 0.50 MB/sec execute 37 sec latency 19456.414 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 1 4999 0.49 MB/sec execute 38 sec latency 20456.570 ms Started lustre-MDT0001 04:15:18 (1749543318) targets are mounted 04:15:18 (1749543318) facet_failover done 1 4999 0.48 MB/sec execute 39 sec latency 21456.797 ms 1 4999 0.47 MB/sec execute 40 sec latency 22456.955 ms 1 4999 0.45 MB/sec execute 41 sec latency 23457.112 ms 1 4999 0.44 MB/sec execute 42 sec latency 24457.357 ms oleg313-client.virtnet: executing wait_import_state_mount (FULL|IDLE) mdc.lustre-MDT0001-mdc-*.mds_server_uuid 1 5190 0.44 MB/sec execute 43 sec latency 24654.581 ms mdc.lustre-MDT0001-mdc-*.mds_server_uuid in FULL state after 0 sec 1 5438 0.43 MB/sec execute 44 sec latency 18.386 ms 1 5710 0.43 MB/sec execute 45 sec latency 20.864 ms 1 5905 0.45 MB/sec execute 46 sec latency 25.998 ms 1 6144 0.46 MB/sec execute 47 sec latency 36.872 ms UUID 1K-blocks Used Available Use% Mounted on lustre-MDT0000_UUID 1414116 2892 1284796 1% /mnt/lustre[MDT:0] lustre-MDT0001_UUID 1414116 2396 1285292 1% /mnt/lustre[MDT:1] lustre-OST0000_UUID 3833116 15764 3590332 1% /mnt/lustre[OST:0] lustre-OST0001_UUID 3833116 37576 3568328 2% /mnt/lustre[OST:1] filesystem_summary: 7666232 53340 7158660 1% /mnt/lustre 1 6568 0.54 MB/sec execute 48 sec latency 26.308 ms 1 7100 0.63 MB/sec execute 49 sec latency 19.067 ms 1 7304 0.65 MB/sec execute 50 sec latency 22.293 ms test_26 fail mds1 7 times 1 7514 0.64 MB/sec execute 51 sec latency 19.230 ms striped dir -i0 -c2 -H crush /mnt/lustre/d26.replay-dual/run_tar Failing mds1 on oleg313-server Stopping /mnt/lustre-mds1 (opts:) on oleg313-server 1 7695 0.63 MB/sec execute 52 sec latency 105.881 ms 1 7695 0.62 MB/sec execute 53 sec latency 1106.065 ms 1 7695 0.61 MB/sec execute 54 sec latency 2106.252 ms 1 7695 0.59 MB/sec execute 55 sec latency 3106.516 ms 1 7695 0.58 MB/sec execute 56 sec latency 4106.800 ms 1 7695 0.57 MB/sec execute 57 sec latency 5107.116 ms 1 7695 0.56 MB/sec execute 58 sec latency 6107.273 ms 04:15:38 (1749543338) shut down facet: mds1 facet_host: oleg313-server facet_failover_host: oleg313-server 1 7695 0.55 MB/sec execute 59 sec latency 7107.501 ms 1 7695 0.55 MB/sec execute 60 sec latency 8107.738 ms 1 7695 0.54 MB/sec execute 61 sec latency 9107.942 ms 1 7695 0.53 MB/sec execute 62 sec latency 10108.174 ms 1 7695 0.52 MB/sec execute 63 sec latency 11108.396 ms 1 7695 0.51 MB/sec execute 64 sec latency 12108.597 ms 1 7695 0.50 MB/sec execute 65 sec latency 13108.766 ms 1 7695 0.50 MB/sec execute 66 sec latency 14108.905 ms 1 7695 0.49 MB/sec execute 67 sec latency 15109.092 ms 1 7695 0.48 MB/sec execute 68 sec latency 16109.297 ms Failover mds1 to oleg313-server mount facets: mds1 1 7695 0.47 MB/sec execute 69 sec latency 17109.513 ms 1 7695 0.47 MB/sec execute 70 sec latency 18109.740 ms 1 7695 0.46 MB/sec execute 71 sec latency 19109.981 ms Start mds1: mount -t lustre -o localrecov /dev/mapper/mds1_flakey /mnt/lustre-mds1 1 7695 0.45 MB/sec execute 72 sec latency 20110.133 ms oleg313-server: oleg313-server.virtnet: executing set_default_debug -1 all pdsh@oleg313-client: oleg313-server: ssh exited with exit code 1 Started lustre-MDT0000 04:15:52 (1749543352) targets are mounted 04:15:52 (1749543352) facet_failover done 1 7695 0.45 MB/sec execute 73 sec latency 21110.265 ms 1 7695 0.44 MB/sec execute 74 sec latency 22110.403 ms 1 7695 0.44 MB/sec execute 75 sec latency 23110.649 ms 1 7695 0.43 MB/sec execute 76 sec latency 24110.932 ms 1 7695 0.42 MB/sec execute 77 sec latency 25111.192 ms 1 7756 0.42 MB/sec execute 78 sec latency 25910.137 ms oleg313-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 8005 0.42 MB/sec execute 79 sec latency 20.612 ms 1 8174 0.43 MB/sec execute 80 sec latency 31.897 ms 1 8349 0.43 MB/sec execute 81 sec latency 25.840 ms 1 8573 0.46 MB/sec execute 82 sec latency 29.226 ms tar: Unexpected EOF in archive tar: Unexpected EOF in archive 1 8717 0.46 MB/sec execute 83 sec latency 23.772 ms tar: Error is not recoverable: exiting now dbench killed by signal 15 stopping dbench on /mnt/lustre at Tue Jun 10 04:16:03 EDT 2025 with return code 0 9596 pts/0 S+ 0:00 dbench -c client.txt 1 -D /mnt/lustre2/d26.replay-dual/run_dbench -t 100 killed dbench main pid 9596 clean dbench files on /mnt/lustre /mnt/lustre /mnt/lustre removed 'client.txt' /mnt/lustre dbench successfully finished