Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 29 Aug 2013 17:03:44 +0200
From:      Andreas Longwitz <longwitz@incore.de>
To:        freebsd-fs@freebsd.org
Subject:   fsync: giving up on dirty on partitions with gjournal or soft updates
Message-ID:  <521F62D0.8000400@incore.de>

next in thread | raw e-mail | index | archive | help
Hello, I run Freebsd 8.4-Stable r253040 completed with adapted r244795,
r244925 and r245286 from head.
On my servers with gjournaled partitions I sometimes see messages like this:

 <kern.crit> serv02 kernel: fsync: giving up on dirty
 <kern.crit> serv02 kernel: 0xffffff0002d313b0: tag devfs, type VCHR
 <kern.crit> serv02 kernel: usecount 1, writecount 0, refcount 35 i
             mountedhere 0xffffff0002bcd400
 <kern.crit> serv02 kernel: flags ()
 <kern.crit> serv02 kernel: v_object 0xffffff0002d22ca8 ref 0 pages 520
 <kern.crit> serv02 kernel: lock type devfs: EXCL by thread
             0xffffff0002956470 (pid 9)
 <kern.crit> serv02 kernel: dev mirror/gmsv02p10.journal
 <kern.crit> serv02 kernel: GEOM_JOURNAL: Cannot suspend file system
             /home (error=35).

pid 9 is the process g_journal switcher and mount gives for /home:
  /dev/mirror/gmsv02p10.journal on /home (ufs, asynchronous, local,
  noatime, gjournal)

I am aware of on old statement of pjd:
 it's harmless, it just means journal switch will be done a bit later.

Ok, but now I have the same messages on a server running soft updates
instead of gjournal during a backup with "dump -L" started by amanda:

amandalog:
sendbackup: Spawning "/sbin/dump dump 0ubLshf 64 1048576 0 -
     /dev/amrd0s1f" in pipeline
sendbackup: 116: strange(?): mksnap_ffs: Cannot create snapshot
     /home/.snap/dump_snapshot: Resource temporarily unavailable
sendbackup: critical (fatal): error [dump (82637) /sbin/dump returned 1]

messages:
 <kern.crit> dsspbx2 kernel: fsync: giving up on dirty
 <kern.crit> dsspbx2 kernel: 0xc5ae4b84: tag devfs, type VCHR
 <kern.crit> dsspbx2 kernel: usecount 1, writecount 0, refcount 123
             mountedhere 0xc5a34d00
 <kern.crit> dsspbx2 kernel: flags ()
 <kern.crit> dsspbx2 kernel: v_object 0xc5aeca18 ref 0 pages 834
 <kern.crit> dsspbx2 kernel: lock type devfs: EXCL by thread 0xc5a4c8a0
             (pid 82639)
 <kern.crit> dsspbx2 kernel: dev amrd0s1f
 <auth.notice> dsspbx2 sendbackup[82634]: error [dump (82637) /sbin/dump
              returned 1]

pid 82639 is the process mksnap_ffs and mount gives for /home:
   /dev/amrd0s1f on /home (ufs, local, noatime, soft-updates)

Last year in this list Kirk wrote (for V9)
  "Note that soft updates without journaling do not show this issue".

I like to modify this statement a little bit (for V8)
  "soft updates do show this is issue, but not so often as gjournal".

-- 
Andreas Longwitz




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?521F62D0.8000400>