Re: Race condition in storeClose()

From: Adrian Chadd <adrian@dont-contact.us>
Date: Tue, 28 Nov 2000 23:38:38 +0800

On Tue, Nov 28, 2000, Joe Cooper wrote:

> Funny you should mention this. For experimentation sake, Moez has
> written a module to his Abyss web server to serve cache hits from the
> same object store Squid is using...and pass misses through to a running
> Squid. Call it a prototype for some future 'fast path' dual server
> approach (the fast path being the hits only server which answers hits
> quickly).
>
> So...proof of concept has been achieved. When he and I get back from
> our respective vacations we're going to see if we can debuggify it, and
> do some experimenting.

.. and you'll find that hits become served much faster? :-)

> Though it may be best to simply implement faster http client side code
> in Squid. We'll have to see, but obviously this objective took less
> time than rewriting the http layer and the hits-path from scratch.

Yup. I was planning something similar after my current work project
gives me back some hours to test the SMP friendlyness of reiserfs_raw.
Now that its done .. :)

Adrian

-- 
Adrian Chadd			"God: Damn! I left pot everywhere!
<adrian@creative.net.au>	  Now I'll have to create Republicans!"
				    - Bill Hicks
Received on Tue Nov 28 2000 - 08:38:44 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:13:00 MST