Re: Performance question

On Mon, 14 Jun 1999, David S. Madole wrote:

> Duane Wessels wrote:
>
> > Your maximum request rate will depend mostly on how full you let the
> > disks become. If you use 90% of the filesystems, then you'll probably
> > be down in the 25/sec range. If you use much less, like 25%, then
> > you can take probably 50/sec.
>
> Based on my experience, your performance ought to be much more than
> this. I have, according to most of what is said, a very low-performance
> squid setup and I easily handle 25 req/sec on each of my boxes:
>
> FreeBSD 3.2 currently, 2.2.7 until recently
> Pentium II 266 / 384M RAM
> 2 x 12.6MB Quantum Fireball ***IDE***
>
> My demand peaks at about 25 req/sec, so I don't know the max, but at
> that level squid spends only about 30% of it's time in disk wait.
>
> I have two cache directories of 4GB each on each drive, 16GB total,
> which I keep 91% full at all times.

I think Duane meant keeping _disks_ more than 90% full. Do you mean cache
directories (2*4GB < 0.9*12GB)? There is a big difference.

> Hope this helps - I guess it just points out that real results can
> vary a lot from benchmarks and from one site to another.

They can. But as far as I can see, your example does not illustrate this
possibility as you do not know your performance limits (not that there is
anything wrong with that).

Getting 25 req/sec out of Squid is relatively simple. Getting 100-150
req/sec is hard, and the success will depend on the hardware and amount of
tuning.

$0.02,

Alex.
Received on Mon Jun 14 1999 - 19:12:49 MDT