ZFS: Almost a minute of dirty buffers?
Zaphod Beeblebrox
zbeeble at gmail.com
Tue Mar 19 20:45:42 UTC 2013
During a recent protracted power outage at home, it came time to shutdown
my ZFS fileserver. This doesn't happen often --- it's a reliable performer.
The kicker is that _after_ the buffers have been sync'd for UFS
(root/var/usr on UFS), ZFS spends some time shutting down --- or that's
what I believe since the disk usage lights on the ZFS drives are going
crazy.
... and ZFS takes nearly a minute of very active disk to shutdown ?!!?
Are these dirty buffers? What is it doing? This period of disk blinking
seems to be related to uptime (ie: longer uptime, longer blinking on
shutdown).
For the curious, my ZFS config is:
[1:1:301]root at virtual:~> zpool status
pool: vr2
state: ONLINE
scan: resilvered 30.8M in 0h2m with 0 errors on Tue Feb 26 20:41:45 2013
config:
NAME STATE READ WRITE CKSUM
vr2 ONLINE 0 0 0
raidz1-0 ONLINE 0 0 0
label/vr2-d0 ONLINE 0 0 0
label/vr2-d1 ONLINE 0 0 0
label/vr2-d2a ONLINE 0 0 0
label/vr2-d3a ONLINE 0 0 0
label/vr2-d4 ONLINE 0 0 0
label/vr2-d5 ONLINE 0 0 0
label/vr2-d6 ONLINE 0 0 0
label/vr2-d7c ONLINE 0 0 0
label/vr2-d8 ONLINE 0 0 0
raidz1-1 ONLINE 0 0 0
gpt/vr2-e0 ONLINE 0 0 0
gpt/vr2-e1 ONLINE 0 0 0
gpt/vr2-e2 ONLINE 0 0 0
gpt/vr2-e3 ONLINE 0 0 0
gpt/vr2-e4 ONLINE 0 0 0
gpt/vr2-e5 ONLINE 0 0 0
gpt/vr2-e6 ONLINE 0 0 0
gpt/vr2-e7 ONLINE 0 0 0
errors: No known data errors
I know that the two vdevs are not the same size (9 disks and 8 disks), but
I noticed this behavior when there was only one vdev in this array, too.
Most of the ZFS usage is via NFS, SMB or iSCSI.
More information about the freebsd-fs
mailing list