Weird issue between backend and upstream (0 bytes)

[Guzmán Brasó]

Hi Maxim! Thanks for taking time to check it out...

So the 499 seen by the php-fpm nginx here It's not that main nginx closed
the connection but that fastcgi closed the connection?

All the time thought was nothing to do with the backend... there's no php
warning or error on the php-fpm side when this happens, will try to enable
debug mode in php-fpm and swim around the logs....

Thanks!



> 2012/08/03 13:56:17 [debug] 1519#0: *221 finalize http upstream request:
499



On Thu, Aug 9, 2012 at 11:15 AM, Maxim Dounin <mdounin at mdounin.ru> wrote:

> Hello!
>
> On Thu, Aug 09, 2012 at 10:24:51AM -0300, Guzmán Brasó wrote:
>
> > Just made myself of a dump from the backend perspective and analized with
> > wireshark to see what were on those bytes, I was pretty sure those bytes
> > were some error from the app with the key to fix it.... but no, those
> 15776
> > bytes are always 15776 but the first 15776 of every request, so every
> > request is different.
> >
> > According to tcpdump everything flows OK and after one common ack from
> > upstream while backend sends data, upstream inmediatly  sends the FIN
> flag
> > and inmediatly after that a group of RST arrive.
>
> This might be a result of several first packets (e.g. initial
> buffer size) being sent before app crashes somewhere at the end of
> response generation.  Have you tried to look what happens from
> the app's point of view?
>
> [...]
>
> Maxim Dounin
>
> _______________________________________________
> nginx mailing list
> nginx at nginx.org
> http://mailman.nginx.org/mailman/listinfo/nginx
>



-- 
Guzmán Brasó Núñez
Senior Perl Developer / Sysadmin
Web: http://guzman.braso.info
Mobile: +598 98 674020
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.nginx.org/pipermail/nginx/attachments/20120809/07d8e249/attachment.html>