On 14 Jun 2012, at 23:15, Timothy Coalson tsc...@mst.edu wrote:
The client is using async writes, that include commits. Sync writes do not
need commits.
Are you saying nfs commit operations sent by the client aren't always
reported by that script?
They are not reported in your case because
One of the glories of Solaris is that it is so very observable. Then
there are the many excellent blog posts, wiki entries, and books - some
or which are authored by contributors to this very thread - explaining
how Solaris works. But these virtues are also a snare to some, and it is
not
On 08/06/2011 14:35, Marty Scholes wrote:
Are some of the reads sequential? Sequential reads
don't go to L2ARC.
That'll be it. I assume the L2ARC is just taking
metadata. In situations
such as mine, I would quite like the option of
routing sequential read
data to the L2ARC also.
The good
Ok here's the thing ...
A customer has some big tier 1 storage, and has presented 24 LUNs (from
four RAID6 groups) to an OI148 box which is acting as a kind of iSCSI/FC
bridge (using some of the cool features of ZFS along the way). The OI
box currently has 32GB configured for the ARC, and 4x
On 07/06/2011 20:34, Marty Scholes wrote:
I'll throw out some (possibly bad) ideas.
Thanks for taking the time.
Is ARC satisfying the caching needs? 32 GB for ARC should almost cover the
40GB of total reads, suggesting that the L2ARC doesn't add any value for this
test.
Are the SSD
On 07/06/2011 22:57, LaoTsao wrote:
You have un balance setup
Fc 4gbps vs 10gbps nic
It's actually 2x 4Gbps (using MPXIO) vs 1x 10Gbps.
After 10b/8b encoding it is even worse, but this not yet impact your benchmark
yet
Sent from my iPad
Hung-Sheng Tsao ( LaoTsao) Ph.D
On Jun 7, 2011, at
Big subject!
You haven't said what your 32 threads are doing, or how you gave them
the same priority, or what scheduler class they are running in.
However, you only have 24 VCPUs, and (I assume) 32 active threads, so
Solaris will try to share resources evenly, and yes, it will preempt one
On 24/12/2010 18:21, Richard Elling wrote:
Latency is what matters most. While there is a loose relationship
between IOPS
and latency, you really want low latency. For 15krpm drives, the
average latency
is 2ms for zero seeks. A decent SSD will beat that by an order of
magnitude.
And the
Great question. In good enough computing, beauty is in the eye of the
beholder. My home NAS appliance uses IDE and SATA drives withoutba dedicated ZIL
http://dtrace.org/blogs/ahl/2010/11/15/zil-analysis-from-chris-george/
if HDDs and commodity SSDs continue to be target ZIL devices, ZFS could
Sent from my iPhone (which had a lousy user interface which makes it all too
easy for a clumsy oaf like me to touch Send before I'm done)...
On 23 Dec 2010, at 11:07, Phil Harman phil.har...@gmail.com wrote:
Great question. In good enough computing, beauty is in the eye of the
beholder. My
On 23 Dec 2010, at 11:53, Stephan Budach stephan.bud...@jvm.de wrote:
Am 23.12.10 12:18, schrieb Phil Harman:
Sent from my iPhone (which had a lousy user interface which makes it all too
easy for a clumsy oaf like me to touch Send before I'm done)...
On 23 Dec 2010, at 11:07, Phil Harman
On 21/12/2010 21:53, Jeff Bacon wrote:
So, to Phil's email - read()/write() on a ZFS-backed vnode somehow
completely bypass the page cache and depend only on the ARC? How the
heck does that happen - I thought all files were represented as vm
objects?
For most other filesystems (and
On 21/12/2010 05:44, Richard Elling wrote:
On Dec 20, 2010, at 7:31 AM, Phil Harman phil.har...@gmail.com
mailto:phil.har...@gmail.com wrote:
On 20/12/2010 13:59, Richard Elling wrote:
On Dec 20, 2010, at 2:42 AM, Phil Harman phil.har...@gmail.com
mailto:phil.har...@gmail.com wrote:
Why does
On 21/12/2010 13:05, Deano wrote:
On Dec 20, 2010, at 7:31 AM, Phil Harman phil.har...@gmail.com
mailto:phil.har...@gmail.com wrote:
If you only have a few slow drives, you don't have performance.
Like trying to win the Indianapolis 500 with a tricycle...
Actually, I didn't say
Hi Jeff,
ZFS support for mmap() was something of an afterthought. The current
Solaris virtual memory infrastructure didn't have the features or
performance required, which is why ZFS ended up with the ARC.
Yes, you've got it. When we mmap() a ZFS file, there are two main caches
involved:
Why does resilvering take so long in raidz anyway?
Because it's broken. There were some changes a while back that made it more
broken.
There has been a lot of discussion, anecdotes and some data on this list.
The resilver doesn't do a single pass of the drives, but uses a smarter
temporal
On 20/12/2010 11:03, Deano wrote:
Hi,
Which brings up an interesting question...
IF it were fixed in for example illumos or freebsd is there a plan for how
to handle possible incompatible zfs implementations?
Currently the basic version numbering only works as it implies only one
stream of
On 20/12/2010 11:29, Lanky Doodle wrote:
I believe Oracle is aware of the problem, but most of
the core ZFS team has left. And of course, a fix for
Oracle Solaris no longer means a fix for the rest of
us.
OK, that is a bit concerning then. As good as ZFS may be, i'm not sure I want
to committ
On 20/12/2010 13:59, Richard Elling wrote:
On Dec 20, 2010, at 2:42 AM, Phil Harman phil.har...@gmail.com
mailto:phil.har...@gmail.com wrote:
Why does resilvering take so long in raidz anyway?
Because it's broken. There were some changes a while back that made
it more broken.
broken
+1
When I did my stuff (with a major bank) two years ago, my reasoning was that we
(Sun, remember them?) had made huge capital out of the always consistent on
disk claim, and that we could be expected to stand by and honour that promise.
But because this was a big bank, I felt that due
Actually, I did this very thing a couple of years ago with M9000s and EMC DMX4s
... with the exception of the same host requirement you have (i.e. the thing
that requires the GUID change).
If you want to import the pool back into the host where the cloned pool is also
imported, it's not just
What more info could you provide? Quite a lot more, actually, like: how many
streams of SQL and copy are you running? how are the filesystems/zvols
configured (recordsize, etc)? some CPU, VM and network stats would also be nice.
Based on the nexenta iostats you've provided (a tiny window on
On 20/10/2010 14:48, Darren J Moffat wrote:
On 20/10/2010 14:03, Edward Ned Harvey wrote:
In a discussion a few weeks back, it was mentioned that the Best
Practices
Guide says something like Don't put more than ___ disks into a single
vdev. At first, I challenged this idea, because I see no
Ian,
It would help to have some config detail (e.g. what options are you using?
zpool status output; property lists for specific filesystems and zvols; etc)
Some basic Solaris stats can be very helpful too (e.g. peak flow samples of
vmstat 1, mpstst 1, iostat -xnz 1, etc)
It would also be
As I have mentioned already, it would be useful to know more about the
config, how the tests are being done, and to see some basic system
performance stats.
On 15/10/2010 15:58, Ian D wrote:
As I have mentioned already, we have the same performance issues whether we
READ or we WRITE to the
www.solarisinternals.com has always been a community. It never was hosted by
Sun, and it's not hosted by Oracle. True, many of the contributors were Sun
employees, but not so many remain at Oracle. If it's out if date, I suspect
that's because the original contributors are too busy doing other
I saw this the other day when doing an initial auto sync from one Nexenta
3.0.3 node to another (using the ZFS/SSH method). I later tried it again with a
fresh destination pool and the read traffic was minimal. Sadly I didn't have an
opportunity to do and investigation, but it doesn't fit my
On 10 Aug 2010, at 08:49, Ian Collins i...@ianshome.com wrote:
On 08/10/10 06:21 PM, Terry Hull wrote:
I am wanting to build a server with 16 - 1TB drives with 2 – 8 dri
ve RAID Z2 arrays striped together. However, I would like the capa
bility of adding additional stripes of 2TB drives in the
On 10 Aug 2010, at 10:22, Ian Collins i...@ianshome.com wrote:
On 08/10/10 09:12 PM, Andrew Gabriel wrote:
Phil Harman wrote:
On 10 Aug 2010, at 08:49, Ian Collins i...@ianshome.com wrote:
On 08/10/10 06:21 PM, Terry Hull wrote:
I am wanting to build a server with 16 - 1TB drives with 2 – 8
That's because NFS adds synchronous writes to the mix (e.g. the client needs to
know certain transactions made it to nonvolatile storage in case the server
restarts etc). The simplest safe solution, although not cheap, is to add an SSD
log device to the pool.
On 23 Jul 2010, at 08:11, Sigbjorn
On 23 Jul 2010, at 09:18, Andrew Gabriel andrew.gabr...@oracle.com wrote:
Thomas Burgess wrote:
On Fri, Jul 23, 2010 at 3:11 AM, Sigbjorn Lie sigbj...@nixtra.com
mailto:sigbj...@nixtra.com wrote:
Hi,
I've been searching around on the Internet to fine some help with
this, but
Sent from my iPhone
On 23 Jul 2010, at 09:42, tomwaters tomwat...@chadmail.com wrote:
I agree, I get apalling NFS speeds compared to CIFS/Samba..ie. CIFS/Samba of
95-105MB and NFS of 5-20MB.
Not the thread hijack, but I assume a SSD ZIL will similarly improve an iSCSI
target...as I am
On 23/07/2010 10:02, Sigbjorn Lie wrote:
On Fri, July 23, 2010 10:42, tomwaters wrote:
I agree, I get apalling NFS speeds compared to CIFS/Samba..ie. CIFS/Samba of
95-105MB and NFS of
5-20MB.
Not the thread hijack, but I assume a SSD ZIL will similarly improve an iSCSI
target...as I am
On 10 Jun 2010, at 19:20, Bob Friesenhahn
bfrie...@simple.dallas.tx.us wrote:
On Thu, 10 Jun 2010, casper@sun.com wrote:
Swap is perhaps the wrong name; it is really virtual memory;
virtual
memory consists of real memory and swap on disk. In Solaris, a page
either exists on the
That screen shot looks very much like Nexenta 3.0 with a different
branding. Elsewhere, The Register confirms it's OpenSolaris.
On 29 Apr 2010, at 07:35, Thommy M. Malmström thommy.m.malmst...@gmail.co
m wrote:
What operating system does it run?
--
This message posted from opensolaris.org
I see at least two differences:
1. duration 30s vs 100s (so not SAME)
2. your manual test doesn't empty the cache
Of course, it is the latter that makes all the difference.
Hope this helps,
Phil
Sent from my iPhone
On 2 Mar 2010, at 08:38, Abdullah Al-Dahlawi dahl...@ieee.org wrote:
On 19/02/2010 21:57, Ragnar Sundblad wrote:
On 18 feb 2010, at 13.55, Phil Harman wrote:
Whilst the latest bug fixes put the world to rights again with respect to
correctness, it may be that some of our performance workaround are still unsafe
(i.e. if my iSCSI client assumes all writes
client assumes all writes are
synchronised to nonvolatile storage, I'd better be pretty sure of the
failure modes before I work around that).
Right now, it seems like an SSD Logzilla is needed if you want
correctness and performance.
Phil Harman
Harman Holistix - focusing on the detail
Can ASM match ZFS for checksum and self healing? The reason I ask is
that the x45x0 uses inexpensive (less reluable) SATA drives. Even the
J4xxx paper you cite uses SAS for production data (only using SATA for
Oracle Flash, although I gave my concerns about that too).
The thing is, ZFS and
Richard Elling wrote:
Tristan Ball wrote:
Also - Am I right in thinking that if a 4K write is made to a
filesystem block with a recordsize of 8K, then the original block
is read (assuming it's not in the ARC), before the new block is
written elsewhere (the copy, from copy on write)? This
YMMV. At a recent LOSUG meeting we were told of a case where rsync was
faster than an incremental zfs send/recv. But I think that was for a
mail server with many tiny files (i.e. changed blocks are very easy to
find in files with very few blocks).
However, I don't see why further ZFS
Hi Banks,
Some basic stats might shed some light, e.g. vmstat 5, mpstat 5,
iostat -xnz 5, prstat -Lmc 5 ... all running from just before you
start the tests until things are normal again.
Memory starvation is certainly a possibility. The ARC can be greedy
and slow to release memory under
What version of Solaris / OpenSolaris are you using? Older versions use
mmap(2) for reads in cp(1). Sadly, mmap(2) does not jive well with ZFS.
To be sure, you could check how your cp(1) is implemented using truss(1)
(i.e. does it do mmap/write or read/write?)
aside
I find it interesting
of this list.
On 14 Nov 2009, at 17:58, Miles Nordin car...@ivy.net wrote:
ph == Phil Harman phil.har...@gmail.com writes:
The format of the stream is committed. You will be able to
receive your streams on future versions of ZFS.
What Erik said is stronger than the man page in an important
On 12 Nov 2009, at 19:54, David Dyer-Bennet d...@dd-b.net wrote:
On Thu, November 12, 2009 13:36, Edward Ned Harvey wrote:
I built a fileserver on solaris 10u6 (10/08) intending to back it
up to
another server via zfs send | ssh othermachine 'zfs receive'
However, the new server is too new
Ok, since we're doing weird, here's my experience ...
MacOS X 10.5, amd64 snv_82, ZFS via NFS v3, iTunes 7-ish
One ZFS filesystem with about 8000 mp3 files.
One empty iTunes library.
Drag and drop about 250 directories (containing the 800 files) into
iTunes from NFS mounted volume.
Select
ZFS doesn't mix well with mmap(2). This is because ZFS uses the ARC
instead of the Solaris page cache. But mmap() uses the latter. So if
anyone maps a file, ZFS has to keep the two caches in sync.
cp(1) uses mmap(2). When you use cp(1) it brings pages of the files it
copies into the
Joerg Schilling wrote:
Phil Harman phil.har...@sun.com wrote:
ZFS doesn't mix well with mmap(2). This is because ZFS uses the ARC
instead of the Solaris page cache. But mmap() uses the latter. So if
anyone maps a file, ZFS has to keep the two caches in sync.
cp(1) uses mmap(2). When
Bob Friesenhahn wrote:
On Sat, 4 Jul 2009, Phil Harman wrote:
If you reboot, your cpio(1) tests will probably go fast again, until
someone uses mmap(2) on the files again. I think tar(1) uses read(2),
but from my iPod I can't be sure. It would be interesting to see how
tar(1) performs
Gary Mills wrote:
On Sat, Jul 04, 2009 at 08:48:33AM +0100, Phil Harman wrote:
ZFS doesn't mix well with mmap(2). This is because ZFS uses the ARC
instead of the Solaris page cache. But mmap() uses the latter. So if
anyone maps a file, ZFS has to keep the two caches in sync.
That's
Bob Friesenhahn wrote:
On Sat, 4 Jul 2009, Phil Harman wrote:
However, this is only part of the problem. The fundamental issue is
that ZFS has its own ARC apart from the Solaris page cache, so
whenever mmap() is used, all I/O to that file has to make sure that
the two caches are in sync
Bob Friesenhahn wrote:
On Sat, 4 Jul 2009, Phil Harman wrote:
However, it seems that memory mapping is not responsible for the
problem I am seeing here. Memory mapping may make the problem seem
worse, but it is clearly not the cause.
mmap(2) is what brings ZFS files into the page cache. I
On 10 Sep 2007, at 16:41, Brian H. Nelson wrote:
Stephen Usher wrote:
Brian H. Nelson:
I'm sure it would be interesting for those on the list if you could
outline the gotchas so that the rest of us don't have to re-invent
the
wheel... or at least not fall down the pitfalls.
Also, here's
53 matches
Mail list logo