回复:Re: what means Cache-off?

From: <maer727@dont-contact.us>
Date: Wed, 10 Apr 2002 15:43:58 +0800 (CST)

Thanks, Joe pal!

Where can I find paper from the Hewlett Packard as you mentioned?

Best regards,
George, Ma

----- 原文 -----
From: Joe Cooper
To: maer727@sohu.com
Cc: squid-dev@squid-cache.org
Subject: Re: what means Cache-off?
Sent: Wed Apr 10 14:08:36 CST 2002

> I have no idea. Alex mentioned in his reply on this topic a couple of
> options. And it wouldn't be difficult to script something in perl that
> will read an access log and fetch every object fetched during the day.
> Probably 5-10 minutes if you just want to test hit ratio (and don't care
> about latency or throughput issues).
>
> That said, Polygraph can provide a quite realistic workload without
> relying on the quirks of the real internet--polymix-4 has no flaws as
> far as I can see for realistically reproducing the workload a production
> cache would see. Have you read the paper from the Hewlett Packard folks
> who first implemented the heap-based policies? They've already done a
> pretty solid bunch of research into the impact of the various policies.
> How the policies perform is mostly a known quantity.
>
> maer727@sohu.com wrote:
> > Thanks, Joe pal!
> >
> > Your reply has clarified my doubts. I still have a question. If I want to use
> > historical log-files to test the performance of my cache, which do you think
> > is the best tool for I to use? My aim to test the LRU, GDSF and LFUDA algorithms
> > ( The hit rate of them.)
> >
> > Best regards,
> > George, Ma
>
> --
> Joe Cooper <joe@swelltech.com>
> http://www.swelltech.com
> Web Caching Appliances and Support
>
Received on Wed Apr 10 2002 - 01:44:06 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:15:01 MST