It is not exactly an Nginx question then :)<br><br>Something cheap-ish and simple-ish is to create your own scripts to hit your sites in a way that you know will or will not trigger cache hits and expensive queries.<br><br>
Chuck in some Apache Bench hits and judge the timings yourself...<br><br><div class="gmail_quote">2009/6/28 Ilan Berkner <span dir="ltr"><<a href="mailto:iberkner@gmail.com">iberkner@gmail.com</a>></span><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div>Just to clarify, I'm not specifically looking for how Nginx performs, but rather how our site performs, being that its a dynamic, php site and relatively quiet during the summer time (i.e. a good time to test) so I'm looking for a tool recommendation to simulate load as well as how to best process that information.</div>
<div> </div>
<div>Thank you for the advise, I'll take a look at some of the tool recommendations.</div><div><div></div><div class="h5">
<div> </div>
<div><br><br> </div>
<div class="gmail_quote">On Sat, Jun 27, 2009 at 9:50 AM, zepolen <span dir="ltr"><<a href="mailto:zepolen@gmail.com" target="_blank">zepolen@gmail.com</a>></span> wrote:<br>
<blockquote style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;" class="gmail_quote">On Fri, Jun 26, 2009 at 5:06 PM, Ilan Berkner<<a href="mailto:iberkner@gmail.com" target="_blank">iberkner@gmail.com</a>> wrote:<br>
> I haven't done stress testing in a long time... so I'm not sure what the<br>> best tools are, specifically for our nginx site<br><br>Rarely will nginx itself be the bottleneck. For example:<br><br>ab testing serving a single image will probably show anywhere from<br>
10,000 - 20,000 req/s, that is because is because after the first<br>access, it will be in ram and can be served fast and efficiently from<br>there on. However in a real production environment, where you might be<br>serving thousands of _different_ files - when the os file cache (in<br>
ram) fills up, those 10,000req/s will become about 300req/s, and in a<br>worst case scenario (where every request is an os cache miss), it<br>becomes entirely disk seek bound (which is why SSD hard disk are great<br>for this sort of job).<br>
<br></blockquote></div><br>
</div></div></blockquote></div><br>