Re: Slowness of Squid without any apparent reason

On Wednesday 30 October 96, at 15 h 16, the keyboard of Stephane
Bortzmeyer <bortzmeyer@pasteur.fr> wrote:

> This has not yet improved :-( I just noticed that, during night or even
> lunch, the cache has a normal speed (less than a second of delay). So,

I forgot to say that, to try if the machine was bounded somewhere, I
tested the disk system (cp /cache/log /dev/null) and the network system
(rcp /cache/log other:/dev/null) and both performed fine, yielding
expected performance and showing the machine was not constrained by SCSI
I/O or FDDI (the "monitor" or "*stat" counters were multiplied by three).

Stephane Bortzmeyer Institut Pasteur
bortzmeyer@pasteur.fr Service d'Informatique Scientifique
                              Paris, France
+33 01 40 61 34 62

http://web.cnam.fr/personnes/bortzmeyer/home_page.dom
Received on Wed Oct 30 1996 - 06:39:24 MST