Re: Proxying PHP Pages

From: John Dilley <jad@dont-contact.us>
Date: Tue, 15 Dec 1998 17:30:39 -0800

>AFAIK, Squid will only follow refresh_patterns if the object can be
>cached; i.e., has a validator (practically speaking, a Last-Modified). I
>could be wrong, but in my experience it does the right thing.

Good news.

>> The impact of max is then to cause IMS requests for not-modified
>> documents more often than necessary. While these requests are small
>> in bandwidth they contribute directly to user latency. Given the
>> observed modification patterns a larger max would make sense.
>
>Bingo. See below re: Squij work.

The Squij work looks interesting. How do you tell which hits
were for stale objects? Does it use a single cache log, or logs from
multiple servers, unified to detect modifications? In our experience
it's been very hard to identify modifications by looking at logs (Squid
or otherwise). You can not detect multiple modifications between hits,
so that causes you to underestimate modifications. On the other hand,
if a document is kicked out of cache the log will show a 200 and it's
hard to determine if it was a modification or a capacity miss ...

>> - The Alex protocol is based upon the assumption that a document
>> modified recently will be more likely to be modified soon than a
>> document modified a long time ago. This is based upon a lot of prior
>> work (decades of it in fact - pre web if you can remember back that
>> far! :-), and seems to behave quite well, in other words it matches
>> human behavior patterns. The percent factor says how old you'll let
>> the document get before checking to see if it's been modified. 200%
>> says let it get to be twice its age before checking - but this seems
>> kind of long to me. Instead, I think the percent parameter should be
>> smaller (20%, 50%), and increase max to prevent needless IMS
>> requests. The Squid default for max is, I believe, 3 weeks; but
>> documents won't get more than 20% of their age in the cache without
>> refreshing. This exhibits geometric scaling in network traffic,
>> which is pretty attractive.
>
>Interesting. Do you have any references for this?

A reference for Alex is Cate's paper, "Alex - A Global File
System" in Proceedings of USENIX File System Workshop May 1992 (pp 1-12)
and briefly in Gwertzman and Seltzer's USENIX paper "World-Wide Web
Cache Consistency" http://www.eecs.harvard.edu/~vino/web/usenix.196/.
Also Krishnamurthy and Wills USITS paper on Piggyback Cache Invalidation
at http://www.research.att.com/~bala/papers/pcv-usits97.ps.gz. Regards,

     -- jad --
  John Dilley <jad@hpl.hp.com>
Received on Tue Dec 15 1998 - 18:24:21 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:43:39 MST