Re: [squid-users] caching failed tcp connects to destination ips

From: Eliezer Croitoru <eliezer_at_ngtech.co.il>
Date: Thu, 25 Jul 2013 10:06:14 +0300

On 07/25/2013 09:52 AM, Dieter Bloms wrote:
> Hi,
>
> we use ipv4 and ipv6 tcp protocol for our outgoing interface.
> The most sides are accessable via ipv6, if a AAAA Record is available,
> so ipv6 works great in most cases.
>
> Some sides like http://www.hsp-steuer.de/ announce ipv6 records, but are
> not accessable via ipv6.
>
> Is it possible that squid notice this fail so that future request will
> go to ipv4 directly and the user doesn't have to wait for the long
> tcp timeout every time ?
> Maybe with a timestamp, so that it will be refreshed after x hours.
>
>
It depends on what the client wants\needs.
most likely ipv4 is the same as ipv6 with couple things that are not the
same in the network level.
The dns should point to the same resources and allow browsers and
proxies to decide if they will use ipv4 or ipv6.
Then squid can decide on the right choice which was tested by chrome.
Chrome tested first "syn" faster then use the fastest network address.

A couple hours ipcache is not a good choice since the internet is a
dynamic system.

have you seen ipcache and dns cache yet?

Eliezer
Received on Thu Jul 25 2013 - 07:06:28 MDT

This archive was generated by hypermail 2.2.0 : Thu Jul 25 2013 - 12:00:10 MDT