Hi , From new user

Alex Rousskov rousskov at measurement-factory.com
Wed Jul 24 15:08:55 UTC 2013


On 07/24/2013 01:55 AM, John Joseph wrote:

> I recently heard aboyt web-polygraph when I was trying to search for
> how to test squid server.

> I need to test my squid cache installation, I found out from google I
> could do it using web-polygraph, now I downloaded the latest stable
> release and tried to install on ubuntu 64 bit, I was able to run the
> configure command, but my make command failed. Did a search and found
> out that web-polygraph works fine with freeBSD, I plan to try it on
> the Free BSD

Polygraph runs OK on FreeBSD although most of the development (and use)
happens on Linux these days. If you come across a build problem, try
googling the error message for an existing solution and report new
problems at https://bugs.launchpad.net/polygraph


> Now I am searching for some document on how to start testing using
> web-polygraph (basics) , I would like to know do I need to install
> this on the squid server or can I have it my client Free BSD and and
> check it on the server from the client

Ideally, you should use at least three boxes to test a proxy: a client
drone (running Polygraph robots), a DUT box (running your proxy), and a
server drone (running Polygraph servers). If you are short on resources,
you can cut corners at the expense of the quality of your test results.
In the extreme case, everything can run on the same box.


> The docs at "http://www.web-polygraph.org/docs/userman/start.html" I
> am referring now, is there any simple howtodo guide?

http://www.web-polygraph.org/docs/userman/simple.html is the next step.
After that, the learning curve becomes steeper as you have to research
standard workloads such as PolyMix-4 (documented but rather complex)
and/or develop your own workloads (using documented PGL types and other
Polygraph concepts as building blocks). Reading old cache-off reports
(and studying standard workloads) may help you understand the overall
methodology better as well.


Good luck,

Alex.




More information about the Users mailing list