I have no idea why backend is sick

[Hugo Cisneiros (Eitch)]

On Wed, Jul 18, 2012 at 8:55 PM, Abraham Cruz Sustaita
<abraham.sustaita at buscacorp.com> wrote:
> I have 8 servers, 7 of them are working as they supposed to be working.
> However, I have app02, and it is not working. The first problem I noticed
> was it was reporting errors even when I change the error reporting to off.
> The second problem, and the one that is give me troubles, is that after I
> reboot the server, it is not working. I have this in the log:
>
> varnishlog | grep app02
>     0 Backend_health - app02 Still healthy 4--X-R- 3 3 5 0.000488 0.000000
> HTTP/1.1 301 Moved Permanently
[...]
>     0 Backend_health - app02 Went sick 4--X-R- 2 3 5 0.000722 0.000000
> HTTP/1.1 301 Moved Permanently
[...]
>     0 Backend_health - app02 Still sick 4--X-R- 0 3 5 0.000503 0.000000
> HTTP/1.1 301 Moved Permanently
>
> But the problem is that the server is working ok. If I do wget app02 from
> varnish, it returns what it is supposed to return! But varnish says that it
> went sick... Is there anyway I can trace this?

As Shibashish said in the thread, the two requests (varnish and wget)
aren't the same, since Varnish does not specify the Host header and
your wget does.

Probably, your Apache configuration isn't catching Varnish's request
because it's not in the correspondent VirtualHost, and it's using the
default configuration. To simulate your varnish's probe, you have to
do:

wget -O /dev/null -S http://app02.domain.com/health-check.html

*without* hosts or anything. It must return HTTP 200. Take a look at
Apache's global configuration and see if it's redirecting. Use wget to
help identify the redirects.

-- 
[]'s
Hugo
www.devin.com.br