Benjamin Krajmalnik wrote:
> > -Original Message-
> > From: Bruce Momjian [mailto:br...@momjian.us]
> > Sent: Monday, June 28, 2010 3:45 PM
> > To: Benjamin Krajmalnik
> > Cc: Rajesh Kumar Mallah; Kevin Grittner; pgsql-
> > performa...@postgresql.org
ian.us]
> Sent: Monday, June 28, 2010 3:45 PM
> To: Benjamin Krajmalnik
> Cc: Rajesh Kumar Mallah; Kevin Grittner; pgsql-
> performa...@postgresql.org
> Subject: Re: [PERFORM] cpu bound postgresql setup.
>
> Benjamin Krajmalnik wrote:
> > Rajesh,
> >
> > I ha
Benjamin Krajmalnik wrote:
> Rajesh,
>
> I had a similar situation a few weeks ago whereby performance all of a
> sudden decreased.
> The one tunable which resolved the problem in my case was increasing the
> number of checkpoint segments.
> After increasing them, everything went back to its norma
Rajesh Kumar Mallah wrote:
> Kevin Grittner wrote:
>>> max_connections = 300
>>
>> As I've previously mentioned, I would use a connection pool, in
>> which case this wouldn't need to be that high.
>
> We do use connection pooling provided to mod_perl server
> via Apache::DBI::Cache. If i reduc
Excerpts from Rajesh Kumar Mallah's message of jue jun 24 13:25:32 -0400 2010:
> What prompted me to post to list is that the server transitioned from
> being IO bound to CPU bound and 90% of syscalls being
> lseek(XXX, 0, SEEK_END) = YYY
It could be useful to find out what file is being seek
age-
> From: pgsql-performance-ow...@postgresql.org
[mailto:pgsql-performance-
> ow...@postgresql.org] On Behalf Of Rajesh Kumar Mallah
> Sent: Thursday, June 24, 2010 11:27 AM
> To: Kevin Grittner
> Cc: pgsql-performance@postgresql.org
> Subject: Re: [PERFORM] cpu bound postgresql
>i do not remember well but there is a system view that (i think)
>guides at what stage the marginal returns of increasing it
>starts disappearing , i had set it a few years back.
Sorry the above comment was regarding setting shared_buffers
not effective_cache_size.
On Thu, Jun 24, 2010 at 10:5
On Thu, Jun 24, 2010 at 8:57 PM, Kevin Grittner
wrote:
> I'm not clear whether you still have a problem, or whether the
> changes you mention solved your issues. I'll comment on potential
> issues that leap out at me.
It shall require more observation to know if the "problem" is solved.
my "pro
I'm not clear whether you still have a problem, or whether the
changes you mention solved your issues. I'll comment on potential
issues that leap out at me.
Rajesh Kumar Mallah wrote:
> 3. we use xfs and our controller has BBU , we changed barriers=1
> to barriers=0 as i learnt that having b
Dear List,
1. It was found that too many stray queries were getting generated
from rouge users and bots
we controlled using some manual methods.
2. We have made application changes and some significant changes have been done.
3. we use xfs and our controller has BBU , we changed barriers=1
Your response somehow landed in the subject line, apparently
truncated. I'll extract that to the message body and reply to what
made it through.
Rajesh Kumar Mallah wrote:
> Firstly many thanks for responding. I am concerned because the
> load averages have increased and users complaining of
Rajesh Kumar Mallah wrote:
> PasteBin for the vmstat output
> http://pastebin.com/mpHCW9gt
>
> On Wed, Jun 23, 2010 at 8:22 PM, Rajesh Kumar Mallah
> wrote:
>> Dear List ,
>>
>> I observe that my postgresql (ver 8.4.2) dedicated server has
>> turned cpu bound and there is a high load average in
PasteBin for the vmstat output
http://pastebin.com/mpHCW9gt
On Wed, Jun 23, 2010 at 8:22 PM, Rajesh Kumar Mallah
wrote:
> Dear List ,
>
> I observe that my postgresql (ver 8.4.2) dedicated server has turned cpu
> bound and there is a high load average in the server > 50 usually.
> The server has
13 matches
Mail list logo
