Running Debian Squeeze on a server with 16GB of RAM. Server handles web server, mail server, DB server but I am currently busy setting it up so its almost not in use, so far only this test site has been put in place until its final configuration. so far I have followed a lot of your tutorials and ended up with: MYSQL – tuned nginx + php5-fpm – tuned, using on_demand process manager + sockets not TCP/IP + APC + WP object caching to APC APC + fast_cgi caching to tmpfs so to admire my work I tried running an ab test from another server: and it ends with: apr_socket_recv: Connection reset by peer (104) so I googled that error, then checked my error logs on the tuned server and found LOADS of these: So what’s the story here? Clearly ab should be served from the fastcgi_cache so what is failing me here? I have attempted to tune networking parameters via sysctl: During my first test, the page was not in cache so when I first ran the ab test I saw a huge CPU spike but when I tried the test again, no cpu spike since the requests were being server from the fastcgi_cache. Also if I stop php5_fpm and open the page in a browser, I'm getting the cached version so the cache works just fine.
I've been making progress: ab -k -n 25000 -c 500 http://pacura.ru/ . . . oncurrency Level: 500 Time taken for tests: 40.164 seconds Complete requests: 25000 Failed requests: 0 Write errors: 0 Keep-Alive requests: 0 Total transferred: 1065375000 bytes HTML transferred: 1051000000 bytes Requests per second: 622.44 [#/sec] (mean) Time per request: 803.286 [ms] (mean) Time per request: 1.607 [ms] (mean, across all concurrent requests) Transfer rate: 25903.74 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 0 2.4 0 86 Processing: 6 795 725.5 590 3741 Waiting: 6 794 725.5 589 3740 Total: 6 795 726.0 590 3741 Percentage of the requests served within a certain time (ms) 50% 590 66% 874 75% 1137 80% 1293 90% 1700 95% 2396 98% 2918 99% 3232 100% 3741 (longest request)
