19 messages in org.freebsd.freebsd-mobileRe: Extreme filesystem sloth| From | Sent On | Attachments |
|---|---|---|
| Harry Putnam | Nov 27, 2001 10:16 pm | |
| Daniel O'Connor | Nov 27, 2001 10:28 pm | |
| Robert Blacquière | Nov 27, 2001 10:42 pm | |
| Harry Putnam | Nov 27, 2001 10:52 pm | |
| Brian T.Schellenberger | Nov 27, 2001 11:12 pm | |
| Greg Lehey | Nov 27, 2001 11:32 pm | |
| Alfred Perlstein | Nov 27, 2001 11:34 pm | |
| Daniel O'Connor | Nov 28, 2001 12:03 am | |
| Harry Putnam | Nov 28, 2001 2:21 am | |
| Daniel O'Connor | Nov 28, 2001 5:15 am | |
| Jeremiah Gowdy | Nov 28, 2001 6:53 am | |
| Chris Faulhaber | Nov 28, 2001 6:55 am | |
| Chad R. Larson | Nov 28, 2001 2:42 pm | |
| Chad R. Larson | Nov 28, 2001 9:27 pm | |
| John Utz | Nov 29, 2001 1:08 pm | |
| Scott Lambert | Nov 29, 2001 1:09 pm | |
| G.E. Rafe | Nov 29, 2001 1:59 pm | |
| Torfinn Ingolfsen | Nov 29, 2001 2:00 pm | |
| Daniel O'Connor | Nov 29, 2001 3:54 pm |
| Subject: | Re: Extreme filesystem sloth | |
|---|---|---|
| From: | Daniel O'Connor (doco...@gsoft.com.au) | |
| Date: | Nov 28, 2001 5:15:07 am | |
| List: | org.freebsd.freebsd-mobile | |
On 28-Nov-2001 Harry Putnam wrote:
For comparison later on after I've been able to make the changes here is a reprint of the time on Freebsd and now duplicate manuever on the same machine but under Linux (Redhat 7.1)
On FreeBSD 4.3
du -sh mail_test 94M mail_test
rm -rf mail_test real 7m13.484s user 0m0.117s sys 0m3.080s
I don't happen to have 94meg of mail files handy, but.. [chowder 23:42] /tmp > du -s foo 18904 foo [chowder 23:42] /tmp > /usr/bin/time rm -rf foo 0.22 real 0.00 user 0.17 sys
I have write caching and softupdates on though. (That directory has 3893 messages in it).
time rm -rf Mail real 0m1.892s user 0m0.110s sys 0m1.818s
Roughly 600 % faster on linux, and that is on the same box (PentiumII 233mhz).
I've got to hit the road now but making the configs will give me something todo in the Motels... he he.
Well, let's say it's a linear relationship.. 94 / 18.9 = 4.9735
0.22 * 4.9735 = 1.09 seconds.
For data this small the results are probably meaningless anyway.
--- Daniel O'Connor software and network engineer for Genesis Software - http://www.gsoft.com.au "The nice thing about standards is that there are so many of them to choose from." -- Andrew Tanenbaum
To Unsubscribe: send mail to majo...@FreeBSD.org with "unsubscribe freebsd-mobile" in the body of the message