Date: Tue, 2 Dec 1997 14:03:27 -0800 (PST) From: Sean Eric Fagan <sef@kithrup.com> To: current@freebsd.org Cc: davidg@freebsd.org, phk@critter.freebsd.dk Subject: Re: cvs commit: src/sys/kern vfs_aio.c Message-ID: <199712022203.OAA04574@kithrup.com> In-Reply-To: <3286.881094892.kithrup.freebsd.current@critter.freebsd.dk> References: Your message of "Tue, 02 Dec 1997 11:42:21 PST." <199712021942.LAA16742@kithrup.com>
next in thread | previous in thread | raw e-mail | index | archive | help
In article <3286.881094892.kithrup.freebsd.current@critter.freebsd.dk> you write: >the difference between you and me on this is that I have measured the >actual difference, you are writing on the back of an envelope. and then: >>If it adds up to 0.1% of an average system call time, I would be >>highly surprised. >I do have numbers. Overall improvement after this change: 0.01 % Gosh. Looks like my statement that any improvement was minimal was *right*. Could it be that I actually *looked* at things before I came up with that number? (As an aside, I would have guessed 0.01% improvement, maybe a bit less... but I decided to be charitable and assume you'd actually come up with something more substantial than my "back of an envelope" -- yet correct -- measurements and evaluation came up with.) >Well, why don't you look at that, and leave me to do what I have in my >pipeline, OK ? Because you broke things. Because you ignored my complaint about it. Because I am not the only one who is unhappy with this change. Because anything else in your pipeline may break even more code. Because you seem to feel that one hundredth of one hundredth of a performance improvement is worth a massive, intrusive, ill-conceived change. Since you've now reported a result, I now suggest and request that the changes be backed out -- one ten-thousandth of an improvement is not worth this particular set of changes.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199712022203.OAA04574>