[Bug 204764] Filesystem deadlock, process in vodead state

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=204764

--- Comment #1 from daniel at blodan.se ---
I'm actually having the exact same problem, it started when we upgraded to 10.2
(we were running 10.1 before and it never happened there) and it happens about
once a month and after a reboot it's good for about another month.

It seems that its the periodic find that always gets stuck and after that alot
of other i/o procs get stuck

Here's the periodic find:
23293 100188 find             -                mi_switch+0xe1 sleepq_wait+0x3a
_sleep+0x287 vnode_create_vobject+0x100 ufs_lookup_ino+0xa0
VOP_CACHEDLOOKUP_APV+0xa1 vfs_cache_lookup+0xd6 VOP_LOOKUP_APV+0xa1
lookup+0x5a1 namei+0x4d4 kern_statat_vnhook+0xae sys_fstatat+0x2c
amd64_syscall+0x357 Xfast_syscall+0xfb

And here's a rsync call thats stuck:
83577 100644 rsync            -                mi_switch+0xe1 sleepq_wait+0x3a
_sleep+0x287 vnode_create_vobject+0x100 ufs_open+0x6d VOP_OPEN_APV+0xa1
vn_open_vnode+0x234 vn_open_cred+0x33e kern_openat+0x26f amd64_syscall+0x357
Xfast_syscall+0xfb

One difference in setup is that I'm running a mfi raid and not zfs

[root at backup-se ~]# mfiutil show volumes
mfi0 Volumes:
  Id     Size    Level   Stripe  State   Cache   Name
 mfid0 (   12T) RAID-5      64K OPTIMAL Disabled
 mfid1 (  931G) RAID-0      64K OPTIMAL Disabled


Filesystem      Size    Used   Avail Capacity  Mounted on
/dev/mfid1p2    898G    4.8G    821G     1%    /
/dev/mfid0p1     12T    8.9T    1.8T    83%    /backups
devfs           1.0K    1.0K      0B   100%    /dev
fdescfs         1.0K    1.0K      0B   100%    /dev/fd

-- 
You are receiving this mail because:
You are the assignee for the bug.