Koji,
i benchmarked using JMeter a open source tool for generating Http Requests.
Since this was a controlled benchmark, i guess it would be considered
synthetic.
Thanks,
--Kapil
----- Original Message -----
From: "Koji Hino"
To:
Cc: ;
Sent: Sunday, March 07, 2004 3:22 PM
Subject: Re: [squid-users] Evaluating SQUID as a Reverse Proxy for a large
web site


> Hi,
>
> How you "benchmark" Apache and Squid?
>
> I mean:
>
> * Real environment benchmark, i.e. compare between followings with real
> customers
> - Get static contents from your busy (due to dynamic contents
> generation) Apache server
> - Get static contents from Squid, and get dynamic contents from your
> Apache server through Squid
>
> OR
>
> * Synthetic benchmark such as:
> - Get limited number (say several hundreds) of static contents, from
> your Apache server, or from your Squid server, with benchmarking
> HTTP client(s)
>
> I think those two benchmarks are completely different things.
>
> Best regards,
>
> ================================================== ==================
> Koji HINO(HINO is my family name)
> NEC Laboratories America, Inc.
>
> From: "kapil khanna"
> Date: Sun, 7 Mar 2004 13:13:43 -0600
>
> :> Henrik,
> :> I am using Apache as my web server. I decreased the dish cache size to

1 MB
> :> and re-ran my tests. This time i got all TCP_MEM_HITS for the images

and
> :> static files. However my benchmark results were not better. The web

server
> :> still scaled much better.
> :> My guess is that SQUID cannot handle concurrency too well. How do i get
> :> SQUID to increase the no of processes or threads? Is my only option to

have
> :> many SQUID servers on different ports on a host with lot of RAM,

running in
> :> front of a load balancer to handle concurrency?
> :> Thanks,
> :> --Kapil
> :> ----- Original Message -----
> :> From: "Henrik Nordstrom"
> :> To: "kapil khanna"
> :> Cc:
> :> Sent: Sunday, March 07, 2004 3:28 AM
> :> Subject: Re: [squid-users] Evaluating SQUID as a Reverse Proxy for a

large
> :> web site
> :>
> :>
> :> > On Sat, 6 Mar 2004, kapil khanna wrote:
> :> >
> :> > > I have been evaluating SQUID to deploy in front of a large web site

to
> :> cache
> :> > > all static content (Images, JS Files, CSS Files, HTML files etc...)

for
> :> the
> :> > > web site. I used JMeter as a load testing tool to evaluate the
> :> scalability
> :> > > of SQUID. This is my current config:-
> :> > > cache_mem - 256MB
> :> > > disk cache - 10MB.
> :> > > I purposely have a very low disk cache so that i can get most out

of
> :> > > in-memory caching of static content. I also set content expiry (if

not
> :> set)
> :> > > for images, JSP files etc to
> :> > > 14400 80% 43200
> :> >
> :> > You probably should run without any disk cache at all in this
> :> > configuration. If not Squid will not actually be able to use all that
> :> > cache_mem..
> :> >
> :> > > Why is that the Web application scales better than SQUID? The one

thing
> :> > > that stands out is that SQUID is running as one process one thread,
> :> > > whereas the web site is multithreaded.
> :> >
> :> > What kind of web server are you using?
> :> >
> :> > The benefits of using a cache infront of the web server is mostly

seen if
> :> > the web server can not handle very many concurrent connections. The

cache
> :> > then helps both by offloading the static content any by reusing the

same
> :> > persistent connections for multiple clients.
> :> >
> :> > Regards
> :> > Henrik
> :> >
> :> >
> :>
>