FWIW, I just disabled prefetch, and my dedup + zfs recv seems to be
running visibly faster (somewhere around 3-5x faster).
echo zfs_prefetch_disable/W0t1 | mdb -kw
Anyone else see a result like this?
I'm using the "read" bandwidth from the sending pool from "zpool
iostat -x 5" to estimate transf
On Dec 24, 2009, at 5:34 PM, Freddie Cash wrote:
Mattias Pantzare wrote:
That would leave us with three options;
1) Deal with it and accept performance as it is.
2) Find a way to speed things up further for this
workload
3) Stop trying to use ZFS for this workload
Option 4 is to re-do your p
> Mattias Pantzare wrote:
> That would leave us with three options;
>
> 1) Deal with it and accept performance as it is.
> 2) Find a way to speed things up further for this
> workload
> 3) Stop trying to use ZFS for this workload
Option 4 is to re-do your pool, using fewer disks per raidz2 vdev,
guys! it's alll good.
We don't need to argue about whether or not EFI is or isn't platform
independentwhat would be nice, is if someone can explain the best way to
create a zpool in freebsd that i can import into solaris so i can move my
data.
I've still got a week or two before i have t
On Fri, Dec 25, 2009 at 9:24 AM, BM wrote:
> EFI is a label, that differs from the VTOC mainly by supporting larger
> than 2GB disks (exceptions are SCSI and SSD drives)
I mean, TB. :-)
--
Kind regards, BM
Things, that are stupid at the beginning, rarely ends up wisely.
On Fri, Dec 25, 2009 at 6:27 AM, Mattias Pantzare wrote:
> On a PC EFI is very OS specific as most OS on that platform does not
> support EFI.
What you mean by "most OS on PC does not support EFI" and what is "PC
platform" anyway? There is some crappy i386 hardware that does not
supports EFI boot
On 24 Dec 2009, at 21:27, Mattias Pantzare wrote:
An EFI label isn't "OS specific formatting"!
It is. Not all OS will read an EFI label.
You misunderstood the concept of OS specific, I feel. EFI is indeed
OS
independent; however, that doesn't necesssarily imply that all OSs
can read
EFI
>>> An EFI label isn't "OS specific formatting"!
>>
>> It is. Not all OS will read an EFI label.
>
> You misunderstood the concept of OS specific, I feel. EFI is indeed OS
> independent; however, that doesn't necesssarily imply that all OSs can read
> EFI disks. My Commodore 128D could boot CP/M bu
I'm running into a issue where there seems to be a high number of read iops
hitting disks and physical free memory is fluctuating between 200MB -> 450MB
out of 16GB total. We have the l2arc configured on a 32GB Intel X25-E ssd and
slog on another32GB X25-E ssd.
According to our tester, Oracle
-BEGIN PGP SIGNED MESSAGE-
Hash: RIPEMD160
Hi Richard,
Richard Elling wrote:
> How about posting the data somewhere we can see it?
As stated in an earlier posting it should be accessible at:
http://init.science.uva.nl/~jeroen/solaris11_iozone_nfs2zfs
Happy holidays!
~Jeroen
- --
Jero
[revisiting the OP]
On Dec 23, 2009, at 8:27 AM, Auke Folkerts wrote:
Hello,
We have performed several tests to measure the performance
using SSD drives for the ZIL.
Tests are performed using a X4540 "Thor" with a zpool consisting of
3 14-disk RaidZ2 vdevs. This fileserver is connected to a
On Dec 24, 2009, at 12:44 AM, Jeroen Roodhart wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: RIPEMD160
Mattias Pantzare wrote:
The ZIL is _not_ optional as the log is in UFS.
Right, thanks (also to Richard and Daniel) for the explanation. I was
afraid this was to good to be true, nice to s
On Dec 24, 2009, at 3:15 AM, Colin Raven wrote:
Does anyone know if a zfs "pool configuration calculator" (for want
of a better term) exists?
I wrote a tool which does this for homogenous disks. An example of
the output is at:
http://blogs.sun.com/relling/entry/sample_raidoptimizer_o
On 24 Dec 2009, at 10:33, Mattias Pantzare wrote:
On Thu, Dec 24, 2009 at 04:36, Ian Collins wrote:
An EFI label isn't "OS specific formatting"!
It is. Not all OS will read an EFI label.
You misunderstood the concept of OS specific, I feel. EFI is indeed OS
independent; however, that
There is a calculator at Corporate Strategies:
http://ctistrategy.com/resources/sun-7000-calculator/
Note that if the ctistrategy site is unavailable for some reason, you can also
just download the free 7000 series virtual appliance which will run happily in
VMWare or VirtualBox.
--
This mess
Does anyone know if a zfs "pool configuration calculator" (for want of a
better term) exists?
Reason for the question:
We're looking at building a configuration which has some hard limits (case
size for one). It's a collaborative project, and not everyone resides in the
same place (or timezone ev
On Thu, Dec 24, 2009 at 04:36, Ian Collins wrote:
> Mattias Pantzare wrote:
I'm not sure how to go about it. Basically, how should i format my
drives in FreeBSD, create a ZPOOL which can be imported into
OpenSolaris.
>>>
>>> I'm not sure about BSD, but Solaris ZFS works w
-BEGIN PGP SIGNED MESSAGE-
Hash: RIPEMD160
Jeroen Roodhart wrote:
>> Questions: 1. Client wsize?
>
> We usually set these to 342768 but this was tested with CenOS
> defaults: 8192 (were doing this over NFSv3)
Is stand corrected here. Looking at proc/mounts I see we are in fact
using diff
-BEGIN PGP SIGNED MESSAGE-
Hash: RIPEMD160
Mattias Pantzare wrote:
>
> The ZIL is _not_ optional as the log is in UFS.
Right, thanks (also to Richard and Daniel) for the explanation. I was
afraid this was to good to be true, nice to see it stated this clearly
though.
That would leave us
19 matches
Mail list logo
