Nginx + fair load balancer patch looping

[Joshua Sierles]

On Feb 29, 2008, at 11:39 AM, Alexander Staubo wrote:

> 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
> usual:
>
>  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?
>
> Alexander.
>

At Engine Yard we are seeing this happen as well, usually when a  
backend goes down or a 'clock skew' message is logged. It gets logged  
hundreds of thousands of times for each request.

Joshua Sierles
Engine Yard