RE: [squid-users] price/performance

From: HUNT_STEVE <[email protected]>
Date: Tue, 13 Nov 2001 10:05:42 -0800

According to these test results, Squid does worse than almost every other
caching product on the market, including Microsoft's. This is in terms of
both raw performance and cost comparison (hardware/software). Am I reading
the test results wrong? Why is Squid such a poor performer?

> -----Original Message-----
> From: Vivek Sadananda Pai [mailto:vivek@imimic.com]
> Sent: Tuesday, November 13, 2001 6:23 AM
> To: squid-users@squid-cache.org
> Subject: Re: [squid-users] price/performance
>
>
> To add to that last point...
>
> A summary of the hardware details of the entries can be found at
> http://www.measurement-factory.com/results/public/cacheoff/N03
> /report.by-meas.html#Sec:Config
>
> If you click on the names of the entries, that brings up the
> more detailed hardware/software configuration info. That
> should give you a better idea of the actual performance of
> the system for some amount of hardware, rather than the list
> prices the vendors provide.
>
> Note that one of the Squid entries was non-commercial, so it
> does have no cost added for software/support/packaging, etc -
> it's just a pure hardware cost number. This entry was from the
> Squid folks themselves (as opposed to a disinterested party
> entering it).
>
> -Vivek
>
> Andre van Zyl wrote:
> >
> > The costs shown are not for the software only. These
> figures are the total
> > cost of the entire "solution" entered, and so include costs
> for the server
> > hardware, switches and/or routers, as well as the software
> and OS. See
> > section 8: Product configurations to see the exact
> breakdown of each entry.
> >
> > AD.
> >
> > > -----Original Message-----
> > > From: Kareem Mahgoub [mailto:kashraf@thewayout.net]
> > > Sent: Tuesday, November 13, 2001 9:45 AM
> > > To: Vivek Sadananda Pai; squid-users@squid-cache.org
> > > Subject: Re: [squid-users] price/performance
> > >
> > >
> > > Just wondering
> > > Is this an advertisement for Microsoft?!:)
> > > theoretically squid must be the higher one as price = 0 $
> > > so Hit rate / Price = infinity
> > > thanks
> > > ----- Original Message -----
> > > From: "Vivek Sadananda Pai" <vivek@imimic.com>
> > > To: <squid-users@squid-cache.org>
> > > Sent: Tuesday, November 13, 2001 12:51 AM
> > > Subject: [squid-users] price/performance
> > >
> > >
> > > > Disclaimer: I work for a caching company
> > > >
> > > > Someone was asking about price/performance. Here are the
> > > price/performance
> > > > links for the last cacheoff. The Squid entries are in black.
> > > >
> > > > price/performance by cache hits
> > > >
> > > http://www.measurement-factory.com/results/public/cacheoff/N03/aut
> > > o/all/hit.
> > > rate_price.ratio.html
> > > >
> > > > price/performance by hits+misses
> > > >
> > > http://www.measurement-factory.com/results/public/cacheoff/N03/aut
> > > o/all/rep.
> > > rate_price.ratio.html
> > > >
> > > > The last polygraph results for CacheFlow are at
> > > > http://polygraph.ircache.net/Results/dcomm-1.cacheflow/
> > > > However, I'd be surprised if CacheFlow can still get
> > > > anyone to pay those prices :-)
> > > >
> > > > -Vivek
> > > >
> > >
> > >
>
Received on Tue Nov 13 2001 - 11:05:45 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:04:10 MST