> What do you see from:
> sysctl kstat.zfs.misc.zio_trim
>
> You should be seeing none zero unsupported and zero failed. If this is
> not the case its likely hast isnt setting bio_error to ENOTSUP.
Again, unfortunately, the systems are now running with trim diisabled
so these statsitcs have all be
- Original Message -
From: "Pete French"
If the device on the secondary node does not supports DELETE, but the
device on the primary does, HAST will report to ZFS that DELETE
succeeded (although it failed on the secondary), and ZFS will not
disable TRIM. Pete, isn't this your case?
> You should also see them in "local errors" statistics from `hastctl
> list' output.
Unfortunately I think those couters were reset when the machine
panicd - they are all showing as zero.
-pete.
___
freebsd-stable@freebsd.org mailing list
http://lists.
> You showed only "Remote request failed" errors from your logs. Do you
> have "Local request failed" errors too?
Yes, I have both - heres a fragment of the log:
Oct 9 11:06:47 serpentine-active hastd[1502]: [serp0] (primary) Remote request
failed (Operation not supported): DELETE(8594203648, 2
On Fri, Oct 11, 2013 at 01:42:39PM +0300, Mikolaj Golub wrote:
> You showed only "Remote request failed" errors from your logs. Do you
> have "Local request failed" errors too?
You should also see them in "local errors" statistics from `hastctl
list' output.
--
Mikolaj Golub
___
On Fri, Oct 11, 2013 at 11:27:36AM +0100, Pete French wrote:
> > If the device on the secondary node does not supports DELETE, but the
> > device on the primary does, HAST will report to ZFS that DELETE
> > succeeded (although it failed on the secondary), and ZFS will not
> > disable TRIM. Pete, is
> If the device on the secondary node does not supports DELETE, but the
> device on the primary does, HAST will report to ZFS that DELETE
> succeeded (although it failed on the secondary), and ZFS will not
> disable TRIM. Pete, isn't this your case?
Afraid not, both machines are running normal "sp
On Wed, Oct 09, 2013 at 03:47:29PM +0100, Steven Hartland wrote:
> ZFS will try to send DELETE requests to the underlying storage to
> support TRIM. If that fails then it will disable TRIM support for
> that vdev.
>
> My guess would be you're just seeing hast being a bit verbose
> when these init
ssage -
From: "Pete French"
To:
Sent: Wednesday, October 09, 2013 3:25 PM
Subject: hast and zfs trim possibly causing some problems in 9.2
I just had a machine fall over on my for the first time in ages - one
of a pair of machine we have running hast with zfs on top. I havent
g
I just had a machine fall over on my for the first time in ages - one
of a pair of machine we have running hast with zfs on top. I havent
got any concrete evidence of what made it die as yet, but I
did notice the logifles filling up with thoursands of lines like this
just prior to the crash:
serpe
10 matches
Mail list logo
