[squid-users] intermittent TCP_MISS on file specified in refresh_pattern

We are running Squid 3.1 on Debian Squeeze. We are using squid as a
reverse proxy/cache for a Django backend.

The cache is working well, but there is one file that keeps getting
by. It has a "?" in its URL, which is needed because it has a license
key parameter in it. I put a refresh pattern to try to catch it, but
it is not cached in a consistent manner. It returns a HIT maybe 50%
of the time, sometimes requests seconds apart will show different
results.

Here is the refresh pattern that I was hoping would catch it, this is
above any other patterns (this is a static file, and we want squid to
cache it for at least an hour):

refresh_pattern -i http://foo.bar/static/floatbox/options.js? 60
100% 60 override-expire override-lastmod

Here are some logs showing the weird caching:

62.189.22.21 [31/Oct/2012:06:15:29 -0700] "GET
http://foo.bar/static/floatbox/options.js? HTTP/1.1" 200
TCP_MEM_HIT:NONE
208.101.141.24 [31/Oct/2012:06:15:55 -0700] "GET
http://foo.bar/static/floatbox/options.js? HTTP/1.1" 200
TCP_MISS:FIRST_UP_PARENT

I was hoping it was a staleness issue, and setting the override-expire
and lastmod options would help enforce the min/max in the refresh
pattern. I'm sure I have missed something.

Thanks in advance for any help.

- Michael Penetcost
Received on Wed Oct 31 2012 - 15:47:03 MDT