> > > Did you do those "dd" tests with small block sizes (like 1byte:
> > > bs=1), like somebody on one of those lists suggests, too? Then
> > > we could see, if there is a high latency that ruins
> > > everything...
> >
> > FYI, PostgreSQL does 8kB I/O by default. This can only be changed
> > by
On Wed, Jan 18, 2006 at 05:11:15PM -0800, Brooks Davis wrote:
> On Wed, Jan 18, 2006 at 06:58:47PM -0600, Jim C. Nasby wrote:
> > On Sat, Jan 14, 2006 at 06:42:02AM -0800, Arne Woerner wrote:
> > > Did you do those "dd" tests with small block sizes (like 1byte:
> > > bs=1), like somebody on one of
On Wed, Jan 18, 2006 at 06:58:47PM -0600, Jim C. Nasby wrote:
> On Sat, Jan 14, 2006 at 06:42:02AM -0800, Arne Woerner wrote:
> > Did you do those "dd" tests with small block sizes (like 1byte:
> > bs=1), like somebody on one of those lists suggests, too? Then we
> > could see, if there is a high l
On Sat, Jan 14, 2006 at 06:42:02AM -0800, Arne Woerner wrote:
> Did you do those "dd" tests with small block sizes (like 1byte:
> bs=1), like somebody on one of those lists suggests, too? Then we
> could see, if there is a high latency that ruins everything...
FYI, PostgreSQL does 8kB I/O by defau
Or sit on ur fingers before u send CR
Slawek Zak <[EMAIL PROTECTED]> wrote: Hi,
I went back one step and moved the db back to the disks. It seems that
an unrelated update to the database at around the same time I migrated
to filer, made it slow down to a crawl. After some tweaking by the
develop
Hi,
I went back one step and moved the db back to the disks. It seems that
an unrelated update to the database at around the same time I migrated
to filer, made it slow down to a crawl. After some tweaking by the
developers and moving back to filer, performance is fine again.
Lesson learned: Alwa
On 1/14/06, Arne Woerner <[EMAIL PROTECTED]> wrote:
> --- Ivan Voras <[EMAIL PROTECTED]> wrote:
> > Arne Woerner wrote:
> > > But why does switching from local disc
> > > to NFS makes the PostgreSQL performance
> > > so bad?
> >
> > A wild guess/try: does file locking work
> > properly with NFS and
On 1/14/06, Andreas Feid <[EMAIL PROTECTED]> wrote:
> Are you sure the filer is fine?
> I would guess so from your description, might be worth getting the latest
> version of perfstat from NOW and run it.
I'm sure. It doesn't do anything special. The throughput it sees from
the dbserver is in the
Arne Woerner wrote:
--- Slawek Zak <[EMAIL PROTECTED]> wrote:
On 1/13/06, Arne Woerner <[EMAIL PROTECTED]> wrote:
40MB/s. CPU load negligible. I don't have
an exact number, as this machine has other
processes running. But overall, the system
load didn't exceed 5%.
Looks good...
I
--- Ivan Voras <[EMAIL PROTECTED]> wrote:
> Arne Woerner wrote:
> > But why does switching from local disc
> > to NFS makes the PostgreSQL performance
> > so bad?
>
> A wild guess/try: does file locking work
> properly with NFS and the filer?
>
I would recommend the following test in order to answ
Arne Woerner wrote:
But why does switching from local disc to NFS makes the PostgreSQL
performance so bad?
A wild guess/try: does file locking work properly with NFS and the filer?
___
freebsd-performance@freebsd.org mailing list
http://lists.freebsd
--- Slawek Zak <[EMAIL PROTECTED]> wrote:
> On 1/13/06, Arne Woerner <[EMAIL PROTECTED]> wrote:
> 40MB/s. CPU load negligible. I don't have
> an exact number, as this machine has other
> processes running. But overall, the system
> load didn't exceed 5%.
>
Looks good...
> I saturated fast ethernet
On 1/13/06, Arne Woerner <[EMAIL PROTECTED]> wrote:
> Hiho!
>
> --- Slawek Zak <[EMAIL PROTECTED]> wrote:
> > A couple of days ago I've moved our
> > production database from local disks
> > to NetAPP filer serving NFS. Performance
> > for this server dropped by factor of 10
> > if not more.
> >
>
On 1/13/06, Claus Guttesen <[EMAIL PROTECTED]> wrote:
> > A couple of days ago I've moved our production database from local
> > disks to NetAPP filer serving NFS. Performance for this server dropped
> > by factor of 10 if not more. From a happy 10% load, the server hit the
> > ceiling and sees loa
> A couple of days ago I've moved our production database from local
> disks to NetAPP filer serving NFS. Performance for this server dropped
> by factor of 10 if not more. From a happy 10% load, the server hit the
> ceiling and sees load of 100% all the time with runqueue above 30. The
>
> I can p
On Fri, Jan 13, 2006 at 01:10:48PM -0800, Arne Woerner wrote:
> Hiho!
>
> --- Slawek Zak <[EMAIL PROTECTED]> wrote:
> > A couple of days ago I've moved our
> > production database from local disks
> > to NetAPP filer serving NFS. Performance
> > for this server dropped by factor of 10
> > if not m
Hiho!
--- Slawek Zak <[EMAIL PROTECTED]> wrote:
> A couple of days ago I've moved our
> production database from local disks
> to NetAPP filer serving NFS. Performance
> for this server dropped by factor of 10
> if not more.
>
I would like to suggest some tests (I do not have a clear idea,
why you
Hello everyone,
A couple of days ago I've moved our production database from local
disks to NetAPP filer serving NFS. Performance for this server dropped
by factor of 10 if not more. From a happy 10% load, the server hit the
ceiling and sees load of 100% all the time with runqueue above 30. The
se
18 matches
Mail list logo