Re: Issues with releases of 3.2 after squid-3.2.0.14-20120117-r11491

On 02/08/2012 05:14 AM, alex sharaz wrote:

> I then downloaded the latest patch release 3.2.0.15......11508 and
> installed it on the test server. With this release, again everything
> seemed ok and a browser connecting to squid would get the 1st page. Any
> further attempts would result in a seriously long delay before anything
> appeared in the browser. A netstat -a would show a connection from the
> client to squid access.log would show nothing and then eventually (sorry
> I've XML'ized the logs) something of the form shown below.
>
> <squid_rec source_ip="150.237.129.18" client_ip="-"
> cache="150.237.85.197" time="1328683548.416"
> real_cache="150.237.85.197"><source_ip>150.237.129.18</source_ip><client_ip>-</client_ip><user_login>-</user_login><user_ident>-</user_ident><user_name>-</user_name><date_time>08/Feb/2012:06:45:48
> +0000</date_time><request_method>GET</request_method><url>http://www.mozilla.org/img/covehead/divider-notch.jpg</url><protocol>HTTP/1.1</protocol><status_code>0</status_code><reply_size>0</reply_size><request_status>NONE_ABORTED:HIER_NONE</request_status><response_time>22881</response_time></squid_rec>
>
>
>
> The only thing that's changed is the release of squid used.
>
> FWIW I've re-enabled ipv6 on the box and removed the --disable-ipv6
> option from the configure to no avail.
>
> Bit stuck as to what to look at next, any suggestions?

If you can reproduce the "seriously long delay" problem with just a few
requests, then I recommend enabling full debugging (debug options
ALL,9), starting Squid from scratch, submitting those requests, and
filing a bug report with the resulting cache.log. If you identify the
URL that has experienced the delay, it would help others to find the
troubling transaction in the logs.

You could analyze the log yourself as well, of course. It is often easy
to spot the place where the delay happens, especially if you use the
scripts to trace isolated transactions. What to do next depends on where
the identified delay source.

HTH,

Alex.
Received on Thu Feb 09 2012 - 01:48:50 MST