RE: small patch for async writes

On Tue, 15 Mar 2005, Steven Wilton wrote:

> Thanks, I see now. I'll keep an eye on bug 671. If you're happy with the
> patch, I'd be willing to do further testing on some of our systems.

I have not tested the patches much beyond compiling yet.

> This is the initial conclusion that I had come to, but the squid FAQ seems
> to indicate that diskd is the fastest option.

All it intends to indicate is that diskd is significantly faster than
using plain old ufs.

> This is probably because it is specifically mentioned in the FAQ
> (section 22), and section 22.2 (
> http://www.squid-cache.org/Doc/FAQ/FAQ.html#toc22.2 ) indicates that it
> is the highest performance option available. Is it worth mentioning
> that under linux, aufs may give equal or faster performance?

Regards
Henrik
Received on Tue Mar 15 2005 - 01:35:15 MST