Preface
Full-page load time measured using pingdom is below anticipation on the highly enhanced page (Pagespeed score 97/100).

Next trial-and-error step ended up being to test using different os/webserver combinations. A family member old Home windows 2003 IIS box offered the static page almost 4 occasions faster (.30s) than two different Apple boxes running Mac OS X build-in Apache (1.15s). Where Rackspace/Akamai CDN using Nginx loads the entire page ins08 seconds or reduced.

Question
Is anybody conscious of some released test results or benchmark that compares the entire web site load time of different os/web server combinations?

Needs:

  • using static content,
  • not measured on localhost,
  • preferrably splitting: start - connect, connect - first byte &lifier first byte - last byte phases for every hit,
  • in which the web servers are running on (almost) identical hardware,
  • in internet systems which are in comparable distance between testing client and serving host,
  • without calculating caching or DNS performance,
  • under no load (most webservers have low load not at their maximum like the majority of available benchmarks test)

Searching for an evaluation that attempts to deliver least output occasions of static content inside a real life internet atmosphere where os/webserver combo may be the variable.

I would recommend to see this decent article about benchmark results: http://nbonvin.wordpress.com/2011/03/14/apache-vs-nginx-vs-varnish-vs-gwan/

Appears G-WAN may be the pure champion. I heard many major high-traffic sites switching for this already (since - generally - may serve content two times faster then Nginx. Essentially enables a delay on hardware upgrades).