pg.ddx.io  pgsql-performance@postgresql.org mailing list archive  
help / color / mirror / Atom feed
From: Alex Turner <armtuk@gmail.com>
To: Greg Stark <gsstark@mit.edu>
Cc: Merlin Moncure <merlin.moncure@rcsonline.com>
Cc: pgsql-performance@postgresql.org
Subject: Re: which dual-CPU hardware/OS is fastest for PostgreSQL?
Date: Wed, 12 Jan 2005 11:57:47 -0500
Message-ID: <33c6269f050112085763aff4a6@mail.gmail.com> (raw)
In-Reply-To: <87zmzg0ycq.fsf@stark.xeocode.com>
References: <6EE64EF3AB31D5448D0007DD34EEB3412A75A3@Herge.rcsinc.local>
	<87zmzg0ycq.fsf@stark.xeocode.com>

Infact the cache hit ratio that Oracle suggests is the minimum good
value is 95%.  Anything below that is bad news.  The reason is pretty
obvious - RAM transfer speed is around 3.2G/sec these days, whilst
even the best array isn't going to give more than 400MB/sec, and
that's not even starting to talk about seek time.  anything below 90%
is not going to keep even the best disc hardware saturated.  I know
that our dataset is 99% cached, and therefore better CPUs/better RAM
has a huge impact on overall performance.

Alex Turner
NetEconomist

On 11 Jan 2005 10:39:01 -0500, Greg Stark <gsstark@mit.edu> wrote:
> 
> "Merlin Moncure" <merlin.moncure@rcsonline.com> writes:
> 
> > heh, our apps do tend to be CPU bound.  Generally, I think the extra CPU
> > horsepower is worth the investment until you get to the really high end
> > cpus.
> 
> I find that while most applications I work with shouldn't be cpu intensive
> they do seem end up being cpu bound quite frequently. What happens is that 90%
> of the workload has a working set that fits in RAM. So the system ends up
> being bound by the memory bus speed. That appears exactly the same as
> cpu-bound, though I'm unclear whether increasing the cpu clock will help.
> 
> It's quite possible to have this situation at the same time as other queries
> are i/o bound. It's quite common to have 95% of your workload be frequently
> executed fast queries on commonly accessed data and 5% be bigger data
> warehouse style queries that need to do large sequential reads.
> 
> Incidentally, the same was true for Oracle on Solaris. If we found excessive
> cpu use typically meant some frequently executed query was using a sequential
> scan on a small table. Small enough to fit in RAM but large enough to consume
> lots of cycles reading it.
> 
> --
> greg
> 
>



view thread (36+ messages)  latest in thread

Message-ID: <33c6269f050112085763aff4a6@mail.gmail.com>
Permalink:  ../33c6269f050112085763aff4a6@mail.gmail.com/
Also on:    postgresql.org/message-id/33c6269f050112085763aff4a6@mail.gmail.com

 · 

reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Reply to all the recipients using the --to and --cc options:
  reply via email

  To: pgsql-performance@postgresql.org
  Cc: armtuk@gmail.com, gsstark@mit.edu, merlin.moncure@rcsonline.com
  Subject: Re: which dual-CPU hardware/OS is fastest for PostgreSQL?
  In-Reply-To: <33c6269f050112085763aff4a6@mail.gmail.com>

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox