Nginx + fair load balancer patch looping
alex at purefiction.net
Fri Feb 29 12:39:24 MSK 2008
An Nginx instance suddenly started spewing the following to its error
log at a rate of about 1GB/minute, and using a bit more CPU than
2008/02/29 10:33:47 [error] 16875#0: *126309461 upstream prematurely
closed connection while reading response header from upstream [...]
Aside from the excessive logging, everything else seemed normal. Our
next_upstream setting is:
proxy_next_upstream error invalid_header;
Restarting Nginx fixed the problem.
Could this be the fair load balancer going hairwire?
More information about the nginx