On Wed, 27 May 1998, Markus Storm wrote:
> On Tue, 26 May 1998, Mark Dabrowski wrote:
>
> > As you can see when the disk operations / second go above 100 (12th
> > column), the CPU idle time goes 100% (last column), which basically means
> > squid freezes...
> >
> > Correct me if I'm wrong, but that means our SCSI controller (Adaptec 2940
> > Ultra) / disk is maxing out at 100 operations / second...
>
> Not sure about that one, but decent controllers do 2000 ops or so ....
> Given an average seek time of 10 ms per access (remember it's mostly
> non-clustered, single random accesses), you're maxing out the disk.
>
> Try adding more disks.
Will it help? I don't think so.
As far as I know, Squid does sequential disk IO.
So when Squid decides to read a file, everything else has to wait. Then
you are waisting the additional disk IO bandwidt comming from the
multiple disk drives.
/Morten %-)
---------------------------------------------------------------
Morten.Guldager.Jensen@uni-c.dk UNI-C Denmark. +45 3587 8935
---------------------------------------------------------------
Windows 95: n.
32-bit extensions and a graphical shell for a 16-bit patch to
an 8-bit operating system originally coded for a 4-bit
microprocessor, written by a 2-bit company that can't stand
for 1 bit of competition.
Received on Wed May 27 1998 - 01:50:11 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:40:21 MST