Re: [squid-users] looking for testers: google maps/earth/youtube caching

From: Adrian Chadd <adrian@dont-contact.us>
Date: Tue, 27 Nov 2007 22:26:11 +0900

On Tue, Nov 27, 2007, Andreas Pettersson wrote:
> I've done some testing with Google Maps using the following rewriting
> regex and it seems to work just fine. Lot's of HITs.
>
> if (m/http:\/\/kh[0-3]?\.google\.com[\.a-z]*\/(.*?) /) {
> print "http://keyhole-srv.google.com.SQUIDINTERNAL/" . $1 . "\n";

Good. What about google earth? Similar hit rates?

Have you followed the Wiki instructions and removed the cache deny QUERY;
replacing it with the relevant refresh patterns in the right place?

> However with YouTube I have some trouble. This is the rewriter I use:

Leave YouTube for now; lets just make sure Google Maps and Earth are
doing the right thing. YouTube is still a bit tricky and I'm still
trying to figure out whats going on.

> 2007/11/27 13:18:07| storeurlStart:
> 'http://74.125.10.100/get_video?video_id=hDJ7IRS4krA&origin=nyc-v23.nyc.youtube.com'
> 2007/11/27 13:18:07| storeurlStart: sending
> 'http://74.125.10.100/get_video?video_id=hDJ7IRS4krA&origin=nyc-v23.nyc.youtube.com
> 127.0.0.1/localhost - GET - myip=127.0.0.1 myport=8081' to the helper
> 2007/11/27 13:18:08| storeurlHandleRead:
> {http://video-srv.youtube.com.SQUIDINTERNAL/get_video?video_id=hDJ7IRS4krA}

Good.

> Subsequent fetches (squidclient and wget) using the exact same URL are
> TCP_HITs.
> But. If I for example change the origin part of the URL (v23 to v24):
>
> 2007/11/27 13:24:05| storeurlStart:
> 'http://74.125.10.100/get_video?video_id=hDJ7IRS4krA&origin=nyc-v24.nyc.youtube.com'
> 2007/11/27 13:24:05| storeurlStart: sending
> 'http://74.125.10.100/get_video?video_id=hDJ7IRS4krA&origin=nyc-v24.nyc.youtube.com
> 127.0.0.1/localhost - GET - myip=127.0.0.1 myport=8081' to the helper
> 2007/11/27 13:24:05| storeurlHandleRead:
> {http://video-srv.youtube.com.SQUIDINTERNAL/get_video?video_id=hDJ7IRS4krA}

> As you see, the resulting storeURL is the same as before, but the
> request is now a TCP_SWAPFAIL_MISS.
> Shouldn't this be a HIT as well? Something I've missed?

Its possible that I've broken something; can you please check cache.log to see
if its logged any errors?

Adrian
Received on Tue Nov 27 2007 - 06:21:13 MST

This archive was generated by hypermail pre-2.1.9 : Sat Dec 01 2007 - 12:00:02 MST