You might also crank up the priority on your resilver, particularly if it
is getting tripped all of the time:
http://broken.net/uncategorized/zfs-performance-tuning-for-scrubs-and-resilvers/
-nld
On Tue, Jun 9, 2015 at 1:31 PM, Dave Pooser dave...@pooserville.com wrote:
This is probably a
still be ok with seagate drives; we were only using the
self-check predictive failure flag, as opposed to anything more
complicated.
good luck
-nld
On Tue, Mar 31, 2015 at 5:08 AM, Matej Zerovnik ma...@zunaj.si wrote:
On 27. 03. 2015 16:13, Narayan Desai wrote:
Having been on the receiving end
Having been on the receiving end of similar advice, it is a frustrating
situation to be in, since you have (and will likely continue to have) the
hardware in production, without much option for replacement.
When we had systems like this, we had a lot of success being aggressive in
swapping out
I'm pretty sure these are just the SAS controller containing about getting
messages it couldn't decode. (in this case, encapsulated SMART command
responses from the drives). AFAIK there is no way to suppress them.
-nld
On Tue, Jan 20, 2015 at 7:15 AM, Stephan Budach stephan.bud...@jvm.de
wrote:
On Thu, Oct 23, 2014 at 10:36 PM, Michael Rasmussen m...@miras.org wrote:
On Fri, 24 Oct 2014 12:08:14 +1100
David Bomba turbo...@gmail.com wrote:
Correct, they are 40Gb/s cards.
I have heard same stories of problems with 40Gb/s cards on Linux and
FreeBSD. What it boils down to is that at
is a link to the switch
i got.
http://www.mellanox.com/related-docs/prod_ib_switch_systems/SX6012.pdf
*Matt Mabis*
--
*From:* Matthew Lagoe matthew.la...@subrigo.net
*Sent:* Monday, September 29, 2014 11:12 AM
*To:* 'Narayan Desai'; Matthew Mabis
*Cc:* omnios
Are you using iSER, or iSCSI over IPoIB? Have you checked your fabrics for
errors (not that those should cause the system to panic).
Also, what kind of infiniband gear are you using?
-nld
On Thu, May 15, 2014 at 4:07 AM, Rune Tipsmark r...@steait.net wrote:
My server panics on high write
We're running a mixed system with connectX 1 and 2, and IB only cards work
great with the hermon driver. We haven't had any luck with CX3, but hear
that it is possible. Performance has been quite good, and we haven't needed
to worry about it so far (knock on wood)
I did a bunch of digging to
We've seen problems like this when we have a SATA drive in a SAS expander
that is going out to lunch. Are there any drives showing errors in iostat
-En? or any drive timeout messages in the ring buffer?
-nld
On Tue, Jan 21, 2014 at 3:04 AM, Tobias Oetiker t...@oetiker.ch wrote:
Hi,
we are
, at 7:21 AM, Narayan Desai narayan.de...@gmail.com
wrote:
We've seen problems like this when we have a SATA drive in a SAS
expander that is going out to lunch. Are there any drives showing errors in
iostat -En? or any drive timeout messages in the ring buffer?
Generally speaking -- you use
and other errors that show up in iostat -En output. We remove
them proactively at that point, and get pretty regular failures on a
testing rig afterward.
-nld
On Tue, Dec 10, 2013 at 8:32 PM, Paul B. Henson hen...@acm.org wrote:
From: Narayan Desai [mailto:narayan.de...@gmail.com]
Sent
On a related note, is there a driver in the pipeline for the new LSI 12gb
HBAs?
-nld
On Mon, Oct 14, 2013 at 5:07 PM, Matthew Mabis mma...@vmware.com wrote:
I have been using a LSI 1068E card for a very long time (Multiple years)
with solaris foundations Pre-Omni... SOLID as a ROCK!
This is caused by the system attempting to use fastboot on default reboot.
We've disabled that and things seem to work properly; the following
commands do the trick. (the first changes reboot not to use fastboot, the
second causes the system to do a full reboot upon panic)
-nld
# svccfg -s
. Prtconf -vp might be helpful. Presumably this is the
result of one or more devices not doing the right thing for quiesce().
- Garrett
On Oct 7, 2013, at 4:34 AM, Narayan Desai narayan.de...@gmail.com
wrote:
This is caused by the system attempting to use fastboot on default
reboot. We've
Intel gigabit (igb)
Someone suggested that this might be some sort of ACPI problem at one
point. Does that seem reasonable?
-nld
On Mon, Oct 7, 2013 at 9:13 PM, Garrett D'Amore
garrett.dam...@dey-sys.comwrote:
On Oct 7, 2013, at 6:08 PM, Narayan Desai narayan.de...@gmail.com wrote:
So
Depending on the availability of the guest-side drivers, it should be a lot
faster to use virtio, both for disk and net.
Does anyone know if virtio support ships now in OmniOS? I know there have
been some drivers floating around for a while now, but haven't tried them.
-nld
On Fri, Sep 13,
600GB 10k SAS drives in
raid10) reading from disks in a different box.
-ashley
On Fri, Sep 13, 2013 at 3:50 PM, Narayan Desai narayan.de...@gmail.com
wrote:
Depending on the availability of the guest-side drivers, it should be
a lot
faster to use virtio, both for disk and net
As far as we've been able to tell, zfs replace is a one way street; once
you start the replace, there doesn't seem to be a way to cancel it until it
is completed.
Also, resilvers appear to start from scratch any time anything about the
pool changes. Do you have a drive that is flapping offline
:25 PM, Narayan Desai wrote:
It looks like someone has managed to get things working on OI:
http://syoyo.wordpress.com/category/infiniband/
Just fyi, there don't seem to be many people running IB with omniOS or OI,
in general. We are, but aren't getting the performance we get with the same
19 matches
Mail list logo