Server Benchmarking Tools
h2load - HTTP/2 benchmarking tool
weighttp - lighty labs How to install weighttp in Ubuntu? | SkyRocknRoll ’s Blog
Load Testing with Apache JMeter
Measuring Web Application Performance
http://www.opensourcetesting.org/performance.php A comperhensive list of open source performance test tools. http://www.softwareqatest.com/qatweb1.html#LOAD List of load and performance test tools
http://sourceforge.net/projects/httperf/ http://www.freephpbenchmark.com/ http://www.pylot.org/ http://fwptt.sourceforge.net/ This interesting tool lets you record browsing actions, and then simulate and repeat them. http://htt.sourceforge.net/ HTTP Test Tool
http://www.pureftpd.org/project/phpbench http://unbeknownst.net/?tag=benchmark http://www.phpclasses.org/browse/package/27.html
Apache JMeter
Sources: http://jakarta.apache.org/jmeter/ http://blog.olenepal.org/index.php/archives/300
http://php-mag.net/itr/online_artikel/psecom,id,546,nodeid,114.html http://www.codediesel.com/php/benchmarking-php-code/ http://www.free-webhosts.com/php-benchmark-script.php
Siege for Apache
Siege is stress test and benchmark utility. It can stress a single URL with a user defined number of simulated users or it can read many URLs into memory and stress them simultaneously. The script is still very actively developed.
It looks like apachebench over-reports responsiveness when serving static HTML or minimal PHP scripts. The Siege is more accurate in reporting static HTML and PHP responsiveness. In all technicality they are the same, Siege just doesn’t require apache-tools.
yum -y install siege
Sources: http://www.joedog.org/index/siege-home http://paul-m-jones.com/?p=421 http://vps.net/forum/showthread.php?t=400 http://articles.techrepublic.com.com/5100-10878_11-5171727.html http://www.sitepoint.com/blogs/2007/05/07/besiege-your-web-application-load-testing-over-http/
httperf
A tool for measuring web server performance.
Sources: http://www.xenoclast.org/doc/benchmark/HTTP-benchmarking-HOWTO/ http://www.xenoclast.org/autobench/ http://sourceforge.net/projects/httperf/ http://httperf.comlore.com/ http://agiletesting.blogspot.com/2005/04/http-performance-testing-with-httperf.html
Apache Flood
Sources: http://httpd.apache.org/test/flood/
Optimize PHP code for speed
http://www.phpbench.com/ How to code PHP to be faster - PHP functions compared by speed.
About Latency
There must be a latency of ~10ms per every 1000 km of distance
Latency is constrained by the speed of light. Hence, 20ms RTT is equivalent to ~3000km, or a 1860 mile radius for light traveling in vacuum. We can’t do any better without changing the laws of physics. Our data packets travel through fiber, which slows us down by a factor of ~1.52, which translates to 2027 km, or a 1260 mile radius. What is remarkable is that we are already within a small constant factor of the theoretical limit.