lkml.org 
[lkml]   [1999]   [Apr]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: nice policy in Linux
[w/o regard to the original subject]

On 5 Apr 1999, Kai Henningsen wrote:
> Changes like that aren't worth the work you put in, *unless* those are the
> 1-2% your program takes too long to meet some sort of deadline. *And* you
> have already given up on larger improvements.

hmm. 1-2% can be a huge difference over time. being that we aim to run
servers for years between downtime, this is a very significant figure. in
varying environments and over time an object could could be the base of a
time slew. if the original figure is modified by such a percentage over
time then the impact can certainly be "worthy".

consider a server that pumps out 4million hits a day. what's one percent of
that worth? perhaps you're benching. another 40K hits is a fair addition.
at 2%, 80K is quite significant.

now take a dozen tweeks at 1-2% of benefit. every little bit helps.

640K out to be enough for anyone. oh, another few k isn't a big
deal...don't bother about being efficient.

we(i) use linux because it's built to higher standards. i very much enjoy
tweeking code for a tiny bit of performance and/or efficiency gain.

:)

-d
--
This is Linux Country. On a quiet night, you can hear Windows NT reboot!
Do you remember how to -think- ? Do you remember how to experiment? Linux
__ is an operating system that brings back the fun and adventure in computing.
\/ for linux-kernel: please read linux/Documentation/* before posting problems


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:51    [W:0.028 / U:1.876 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site