From: "Ralph Mason" <ralph.mason@telogis.com>
To: "'Jeff Davis'" <pgsql@j-davis.com>,
	"'Joshua D. Drake'" <jd@commandprompt.com>
Cc: "'CAJ CAJ'" <pguser@gmail.com>, pgsql-performance@postgresql.org
References: <5132236932388612597@unknownmsgid>	
	<467669b30705091726j31fce52fp2f49649be675d811@mail.gmail.com>	
	<4642677F.80209@commandprompt.com>
	<1178757739.24902.78.camel@dogma.v10.wvs>
In-Reply-To: <1178757739.24902.78.camel@dogma.v10.wvs>
Subject: Re: Performance Woes
Date: Thu, 10 May 2007 13:45:28 +1200
Message-ID: <014501c792a4$e8407a20$b8c16e60$@mason@telogis.com>
MIME-Version: 1.0
Content-Type: text/plain;
	charset="windows-1250"
Content-Transfer-Encoding: quoted-printable
Thread-Index: AceSnMa6mAj6HNPTTiO9vpOXkq9gPgAB0wuw
Content-Language: en-gb

>To me, that means that his machine is allowing the new FD to be =
created,
>but then can't really support that many so it gives an error.

files-max is 297834
ulimit is 1000000

(doesn't make sense but there you go)

What I don=92t really understand is with max_files_per_process at 800 we =
don't
get the problem, but with 1000 we do.

$lsof | wc -l=20
14944


$cat /proc/sys/fs/file-nr=20
12240   0       297834


>Ralph, how many connections do you have open at once? It seems like the
>machine perhaps just can't handle that many FDs in all of those
>processes at once.

There are only 30 connections - of those probably only 10 are really =
active.
It doesn't seem like we should be stressing this machine/


>That is a lot of tables. Maybe a different OS will handle it better?
>Maybe there's some way that you can use fewer connections and then the
>OS could still handle it?

It would be less but then you can't maintain the db b/c of the constant
vacuuming needed :-(  I think the linux folks would get up in arms if =
you
told them they couldn't handle that many open files ;-)

Thanks,
Ralph

--=20
Internal Virus Database is out-of-date.
Checked by AVG Free Edition.
Version: 7.5.432 / Virus Database: 268.15.9/573 - Release Date: =
05/12/2006
16:07
=20