Re: [squid-users] 504 Timeout of large dynamically generated files - delay pool problem?

On Sat, 14 Jun 2003 15:19:47 +0200, Henrik wrote:
>Hmm.. delay pools should not make a difference here..
>
>Are you sure you have not changed any of the timeouts? Especially the
>read_timeout option.

Hello Henrik,

We had the read_timeout at 5minutes for a while but set it back to
15minutes (which is 10 minutes longer than the job takes to finish).
Also from what I understood of read_timeout from the conf file, if
that had been the issue, then a specific timeout error would have been
logged whereas we only get:
Fri Jun 13 12:20:15 2003 300028 192.168.5.4 TCP_MISS/504 1396 POST
http://external.web.server/A_44000.cfm/QueryFacility.xlc? -
in the access.log file and nothing in the cache.log.

The timeouts that are uncommented in my conf file are:
    connect_timeout 60 seconds
    read_timeout 15 minutes
The only other "interesting" things I just saw are:
    quick_abort_min 8 KB
    quick_abort_max 8 KB
    half_closed_clients off

Is there anything else I can do to test/check? Monday I am having the
user try it again but with a delay_pool that is wide open (i.e.
defined but defined as large as the aggregate pipe). Other than that,
I am not sure what to try/test next.

thanks,

Adam
Received on Sat Jun 14 2003 - 16:22:57 MDT