Description of problem: I was running I/O to three filesystems on my 6 node cluster over the weekend and hit this assertion failure: dlm: tarlow2: recover event 15 done dlm: tarlow2: process held requests dlm: tarlow2: processed 0 requests dlm: tarlow2: resend marked requests dlm: tarlow2: resent 0 requests dlm: tarlow2: recover event 15 finished dlm: tarlow1: granting lock on lockqueue dlm: lkb id 400a01d8 remid 0 flags 0 status 1 rqmode 3 grmode -1 nodeid 1 lqstate 3 lqflags 0 dlm: request rh_cmd 6 rh_lkid 3141032d remlkid 400a01d8 flags 0 status 0 rqmode 0 dlm: tarlow1: process_lockqueue_reply id 400a01d8 state 0 GFS: Assertion failed on line 247 of file /usr/src/cluster/gfs-kernel/src/gfs/inode.c GFS: assertion: "FALSE" GFS: time = 1090835334 GFS: fsid=morph-cluster:tarlow2.4: inode = 50980737/50980737 Kernel panic: GFS: Record message above and reboot. Here are the cmdlines that I was running: ./accordion -L flock -s 2097152 -e 1024 -w /mnt/tarlow0 -t -m 100000 -S 54321 accd1 accd2 accd3 accd4 accd5 accd6 accd7 accd8 accd9 accd10 & ./genesis -S 12345 -n 7500 -s 1048576 -L flock -d 700 -w /mnt/tarlow1 & ./genesis -S 12345 -n 7500 -s 1048576 -L flock -d 700 -w /mnt/tarlow2 &
The "granting lock on lockqueue", lkb printout, and "process_lockqueue_reply" are not a problem and probably not related to the assertion.
Updates with the proper version and component name.
hasn't been seen in over 5 months.