up vote 1 down vote favorite
share [g+] share [fb]

I've got a webserver running Ubuntu 10.04 Server edition (on rackspace cloud), running nginx and jetty. It's under quite a bit of load (60-70 requests/sec or so successful). Nginx is proxying requests to jetty, but it seems that the connection times out all the time:

2011/05/19 16:43:17 [error] 17798#0: *652139 connect() failed (110: Connection timed out) while connecting to upstream

Even worse, this seems to happen to every connection on the machine: incoming connections to nginx, nginx to (localhost) jetty, even incoming ssh connections occasionally time out.

What are the network parameters that need to be tuned on a heavily used ubuntu server?

link|improve this question
Are you seeing any corresponding errors in your syslog? Take a look at /var/log/messages and dmesg | tail – devicenull May 22 '11 at 4:05
Also, what do free -m, top, and dstat have to say about the machine---combined they would let you know what part of the system is overloaded (disk, network card, CPU, memory, or not the server at all)? – James Cape Sep 28 '11 at 23:24
feedback

migrated from stackoverflow.com May 21 '11 at 21:31

This question came from our site for professional and enthusiast programmers.

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
or
required, but never shown
discard