Re: [squid-users] benchmark test

From: Bgs himself <bgs@dont-contact.us>
Date: Tue, 19 Feb 2002 10:50:18 +0100 (MET)

On Tue, 19 Feb 2002, Joe Cooper wrote:

 Hi !

Thanks for your reply. This is the kind of info I'm looking for :)

> Why not perform your own tests? Polygraph is free for the downloading.

Accidentally I don't have the resources now to perform these tests. Own
test would be best as I can try every hw and tweak, but one of the reasons
I have to plan in advance is that we are short of hw right now, but have
to start some work soon.

> Of course...maybe you're talking about website accelerator performance,
> in which case all these numbers go out the window. Squid is much faster
> from a RAM only workload, so your high numbers for those last two boxes
> get to be more realistic.

In the first step I'll need an accelerator and I'm putting more energy in
estimating accelerator performances.

Reading your mail a couple of questions came to my mind:

 - I saw tests about squid/disk numbers. Increase from 1d->2d was a real
 improvement. 2d->3d gave also noticable performance increase. From the on
 I saw very little difference. Isn't it better to have two servers with 2
 disk than having one with 8 disks (about the same price or even
 cheaper) ?

 - When running multiple squids on one box, which gives better
   performance:
   - 3 squids in: "frontend" -> 2 local parents setup
   - 2 squids and software tcp round-robin traffic distribution ?

 The first seems more failproof, the second a bit faster. Or is it only a
 wild guess?

I'm encountering more and more questions and I'm still far from making
estimates :/

Bye
Bgs
Received on Tue Feb 19 2002 - 03:00:14 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:06:26 MST