Hi,
i think, the local ZFS filesystem with raidz on the 7210 is not the
problem (when there are fast HDs), but you can test it with e.g.
bonnie++ (downloadable at sunfreeware.com), also NFS should not be the
problem because iscsi is also very slow(isn´t it?).
some other ideas are:
Network
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
If I remember correctly, ESX always uses synchronous writes over NFS. If
so, adding a dedicated log device (such as a DDRdrive) might help you
out here. You should be able to test it by disabling the ZIL for a short
while and see if performance
Hi,
In a setup similar to yours I changed from a single 15 disks raidz2 to 7 mirros
of 2 disks each. The change in performance was stellar. The key point in
serving things for VMware is that it always issue synchronous writes, wheter on
iscsi or NFS. When you have tens of VM the resulting
On 8/27/2010 12:25 AM, Michael Dodwell wrote:
Lao,
I had a look at the HAStoragePlus etc and from what i understand that's to
mirror local storage across 2 nodes for services to be able to access 'DRBD
style'.
not true, HAS+ use shred storage.
in this case since ZFS is not clustered FS so
For quite some time I'm bitten by the fact that on my laptop (currently
running self-built snv_147) zpool status rpool and format disagree about
the device name of the root disk:
r...@masaya 14 zpool status rpool
pool: rpool
state: ONLINE
status: The pool is formatted using an older on-disk
hi
may be boot a livecd then export and import the zpool?
regards
On 8/27/2010 8:27 AM, Rainer Orth wrote:
For quite some time I'm bitten by the fact that on my laptop (currently
running self-built snv_147) zpool status rpool and format disagree about
the device name of the root disk:
On Fri, 27 Aug 2010, Rainer Orth wrote:
zpool status thinks rpool is on c1t0d0s3, while format (and the kernel)
correctly believe it's c11t0d0(s3) instead.
Any suggestions?
Try removing the symlinks or using 'devfsadm -C' as suggested here:
LaoTsao 老曹 laot...@gmail.com writes:
may be boot a livecd then export and import the zpool?
I've already tried all sorts of contortions to regenerate
/etc/path_to_inst to no avail. This is simply a case of `should not
happen'.
Rainer
--
Saso is correct - ESX/i always uses F_SYNC for all writes and that is for sure
your performance killer. Do a snoop | grep sync and you'll see the sync write
calls from VMWare. We use DDRdrives in our production VMWare storage and they
are excellent for solving this problem. Our cluster supports
On Fri, August 27, 2010 08:46, Eff Norwood wrote:
Saso is correct - ESX/i always uses F_SYNC for all writes and that is for
sure your performance killer. Do a snoop | grep sync and you'll see the
sync write calls from VMWare. We use DDRdrives in our production VMWare
storage and they are
David asked me what I meant by filled up. If you make the unwise decision to
use an SSD as your ZIL, at some point days to weeks after you install it, all
of the pages will be allocated and you will suddenly find the device to be
slower than a conventional disk drive. This is due to the way
Mark J Musante mark.musa...@oracle.com writes:
On Fri, 27 Aug 2010, Rainer Orth wrote:
zpool status thinks rpool is on c1t0d0s3, while format (and the kernel)
correctly believe it's c11t0d0(s3) instead.
Any suggestions?
Try removing the symlinks or using 'devfsadm -C' as suggested here:
On Aug 27, 2010, at 1:04 AM, Mark markwo...@yahoo.com wrote:
We are using a 7210, 44 disks I believe, 11 stripes of RAIDz sets. When I
installed I selected the best bang for the buck on the speed vs capacity
chart.
We run about 30 VM's on it, across 3 ESX 4 servers. Right now, its all
Rainer,
devfsadm -C alone didn't make a difference, but clearing out /dev/*dsk
and running devfsadm -Cv did help.
I am glad it helped; but removing anything from /dev/*dsk is a kludge
that cannot be accepted/condoned/supported.
Regards... Sean.
Sean,
I am glad it helped; but removing anything from /dev/*dsk is a kludge that
cannot be accepted/condoned/supported.
no doubt about this: two parts of the kernel (zfs vs. devfs?) disagreeing
about devices mustn't happen.
Rainer
--
On Fri, Aug 27, 2010 at 05:51:38AM -0700, David Magda wrote:
On Fri, August 27, 2010 08:46, Eff Norwood wrote:
Saso is correct - ESX/i always uses F_SYNC for all writes and that is for
sure your performance killer. Do a snoop | grep sync and you'll see the
sync write calls from VMWare. We
On Thu, 26 Aug 2010, George Wilson wrote:
David Magda wrote:
On Wed, August 25, 2010 23:00, Neil Perrin wrote:
Does a scrub go through the slog and/or L2ARC devices, or only the
primary storage components?
A scrub will go through slogs and primary storage devices. The L2ARC device
is
Hi,
sometimes ago Jeff Bonwick provides source code and x86-binary for a tool to
recover detached disks.
Refs at http://www.opensolaris.org/jive/thread.jspa?messageID=229969 or
http://opensolaris.org/jive/thread.jspa?messageID=303895#303895
Does someone have an binary for sparc at hand? I
I have been running some large VirtualBox guest images on OpenSolaris (b134) -
and have on three occasions had my zpool develop unrecoverable errors. The
corruption developed in the VirtualBox disk image files. These are large files
with intense activity- so better chance of seeing errors I
Hi Rainer,
I'm no device expert but we see this problem when firmware updates or
other device/controller changes change the device ID associated with
the devices in the pool.
In general, ZFS can handle controller/device changes if the driver
generates or fabricates device IDs. You can view
Hi Cindy,
I'll investigate more next week since I'm in a hurry to leave, but one
point now:
I'm no device expert but we see this problem when firmware updates or
other device/controller changes change the device ID associated with
the devices in the pool.
This is the internal disk in a
On Fri, Aug 27 at 6:16, Eff Norwood wrote:
David asked me what I meant by filled up. If you make the unwise
decision to use an SSD as your ZIL, at some point days to weeks
after you install it, all of the pages will be allocated and you
will suddenly find the device to be slower than a
Hey thanks for the replies everyone.
Saddly most of those options will not work, since we are using a SUN Unified
Storage 7210, the only option is to buy the SUN SSD's for it, which is about
$15k USD for a pair. We also don't have the ability to shut off ZIL or any of
the other options that
markwo...@yahoo.com said:
So the question is with a proper ZIL SSD from SUN, and a RAID10... would I be
able to support all the VM's or would it still be pushing the limits a 44
disk pool?
If it weren't a closed 7000-series appliance, I'd suggest running the
zilstat script. It should make it
On Fri, Aug 27, 2010 at 11:57:17AM -0700, Marion Hakanson wrote:
markwo...@yahoo.com said:
So the question is with a proper ZIL SSD from SUN, and a RAID10... would I
be
able to support all the VM's or would it still be pushing the limits a 44
disk pool?
If it weren't a closed
It does, its on a pair of large APC's.
Right now we're using NFS for our ESX Servers. The only iSCSI LUN's I have are
mounted inside a couple Windows VM's. I'd have to migrate all our VM's to
iSCSI, which I'm willing to do if it would help and not cause other issues.
So far the 7210
On Fri, Aug 27, 2010 at 12:46:42PM -0700, Mark wrote:
It does, its on a pair of large APC's.
Right now we're using NFS for our ESX Servers. The only iSCSI LUN's
I have are mounted inside a couple Windows VM's. I'd have to
migrate all our VM's to iSCSI, which I'm willing to do if it would
Wouldn't it be possible to saturate the SSD ZIL with enough backlogged sync
writes?
What I mean is, doesn't the ZIL eventually need to make it to the pool, and if
the pool as a whole (spinning disks) can't keep up with 30+ vm's of write
requests, couldn't you fill up the ZIL that way?
--
On Aug 27, 2010, at 2:32 PM, Mark wrote:
Saddly most of those options will not work, since we are using a SUN Unified
Storage 7210, the only option is to buy the SUN SSD's for it, which is about
$15k USD for a pair. We also don't have the ability to shut off ZIL or any
of the other
On Fri, Aug 27, 2010 at 01:22:15PM -0700, John wrote:
Wouldn't it be possible to saturate the SSD ZIL with enough
backlogged sync writes?
What I mean is, doesn't the ZIL eventually need to make it to the
pool, and if the pool as a whole (spinning disks) can't keep up with
30+ vm's of write
No. From what I've seen, ZFS will periodically flush writes from the
ZIL to disk. You may run into a read starvation situation where ZFS is
so busy flushing to disk that you won't get reads. If you have VMs where
developers expect low latency interactivity, they get unhappy. Trust me. :)
Hi Mark;
I have installed several 7000 series systems, some running 100's of VM's.
I can help try to help you but to find where exactly the problem is I may
need more information.
I can understand that you have no ZIL's. So most probably you are using the
7110 with 250 GB drives.
All 7000
By all means please try it to validate it yourself and post your results from
hour one, day one and week one. In a ZIL use case, although the data set is
small it is always writing a small ever changing (from the SSDs perspective)
data set. The SSD does not know to release previously written
On Fri, Aug 27, 2010 at 03:51:39PM -0700, Eff Norwood wrote:
By all means please try it to validate it yourself and post your
results from hour one, day one and week one. In a ZIL use case,
although the data set is small it is always writing a small ever
changing (from the SSDs perspective)
Hi,
When I set readonly=on on a dataset then no new files are allowed to be
created.
However writes to already opened files are allowed.
This is rather counter intuitive - if I set a filesystem as read-only I
would expect it not to allow any modifications to it.
I think it shouldn't behave
On 08/28/10 11:13 AM, Robert Milkowski wrote:
Hi,
When I set readonly=on on a dataset then no new files are allowed to
be created.
However writes to already opened files are allowed.
This is rather counter intuitive - if I set a filesystem as read-only
I would expect it not to allow any
On 08/28/10 12:05 PM, Ian Collins wrote:
On 08/28/10 11:13 AM, Robert Milkowski wrote:
Hi,
When I set readonly=on on a dataset then no new files are allowed to
be created.
However writes to already opened files are allowed.
This is rather counter intuitive - if I set a filesystem as
On Sat, Aug 28, 2010 at 12:05:53PM +1200, Ian Collins wrote:
Think of this from the perspective of an application. How would
write failure be reported? open(2) returns EACCES if the file can
not be written but there isn't a corresponding return from write(2).
Any open file descriptors would
From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss-
boun...@opensolaris.org] On Behalf Of Ian Collins
However writes to already opened files are allowed.
Think of this from the perspective of an application. How would write
failure be reported?
Both very good points. But I
Hello All,
I'm sure this has been discussed previously but I haven't been able to find an
answer to this. I've added another raidz1 vdev to an existing storage pool and
the increased available storage isn't reflected in the 'zfs list' output. Why
is this?
The system in question is runnning
On 08/28/10 12:45 PM, Edward Ned Harvey wrote:
Another specific example ...
Suppose you zfs send from a primary server to a backup server. You want
the filesystems to be readonly on the backup fileserver, in order to receive
incrementals. If you make a mistake, and start writing to the backup
From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss-
boun...@opensolaris.org] On Behalf Of Ian Collins
so it should behave in the same way as an unmount in
the presence of open files.
+1
You can unmount lazy, or force, or by default, the unmount fails in the
presence of open
Hi,
Is it possible to do zfs get -??? quota filesystem ?
Thanks.
Fred
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
From: Ian Collins [mailto:i...@ianshome.com]
On 08/28/10 12:45 PM, Edward Ned Harvey wrote:
Another specific example ...
Suppose you zfs send from a primary server to a backup server. You
want
the filesystems to be readonly on the backup fileserver, in order to
receive
This just popped up:
In terms of how native ZFS for Linux is being handled by [KQ
Infotec], they are releasing their ported ZFS code under the Common
Development Distribution License and will not be attempting to go
for mainline integration. Instead, this company will just be
releasing
I get the answer: -p.
-Original Message-
From: Fred Liu
Sent: 星期六, 八月 28, 2010 9:00
To: zfs-discuss@opensolaris.org
Subject: get quota showed in precision of byte?
Hi,
Is it possible to do zfs get -??? quota filesystem ?
Thanks.
Fred
Hi,
Thanks for posting information about this port here. Just to add few points:
* Currently we are planning to do a closed beta for this port, which is
based on b121, we will be doing a proper release around end of this year,
which will be based on latest build b141. If you are interested in
On Sat, Aug 28, 2010 at 7:54 AM, Darin Perusich
darin.perus...@cognigencorp.com wrote:
Hello All,
I'm sure this has been discussed previously but I haven't been able to find an
answer to this. I've added another raidz1 vdev to an existing storage pool and
the increased available storage isn't
I can think of two rather ghetto ways to go.
1. write data then set the read-only property. If you need to make updates
cycle back to rw, write data, set read only.
2. Write data, snapshot the fs, expose the snapshot instead of the r/w file
system. Your mileage may vary depending on the
49 matches
Mail list logo