[squid-users] Squid 2.7 behaviour when run as caching reverse proxy when origin web site down

Hello everyone,

I tried searching MARC for an answer to my question, but gave up after about an hour of reading unrelated threads.

I have an intranet application that depends upon graphics generated by an external web site, the results of which depend upon GET request query parameters.

I would like to use Squid in two capacities:
1. To cache the graphics so as to reduce the load on the external web site, as well as improve the performance of the intranet application, and
2. To allow the intranet application to survive (hopefully) temporary service interruptions experienced by either our data centre or the external web site.

To this end, I have set up Squid as a reverse proxy for the external web site. This satisfies #1.

I have examined the HTTP response headers returned with the graphic resources, and they include a Cache-Control header as follows:

Cache-Control: max-age=7200

I've read Mark Nottingham's blog about the stale-when-validation and stale-if-error options. In the absence of these Cache-Control options, what do I have to do (if anything) to have Squid serve the cached (and possibly stale) content if there are errors connecting to the origin web site? The graphics for any given set of GET request query parameters are static, so the graphics that are generated for any given request can essentially be reused indefinitely.

Thanks.

Sean Dockery
Senior Software Test Developer

QuIC Financial Technologies Inc.
Suite 225, 3553 - 31 St. NW
Calgary, AB Canada
T2L 2K7

t +1 403 210 8282
m +1 403 966 0631
f +1 403 210 8299
e sean.dockery_at_quic.com
www.quic.com
----------------------------
To view our disclaimer please visit http://www.quic.com/emailnotice.aspx

ver. QuIC 0707
Received on Fri Aug 06 2010 - 23:24:19 MDT