Subject: Re: Preparing callout(9) for a HZ-less kernel
To: None <tech-kern@netbsd.org>
From: Andrew Doran <ad@netbsd.org>
List: tech-kern
Date: 10/19/2007 01:31:32
On Thu, Oct 18, 2007 at 09:44:35PM +0200, Joerg Sonnenberger wrote:

> Initial benchmarks from rmind@ have shown a small regression for the
> MySQL benchmark, but I hope the move to dynamic timers will ultimately
> justify this.

How much is a small regression? :-) Can you get averages with rdtsc from
callout_schedule/callout_stop?

Andrew