Re: copy-on-write optimized faults

1999-10-30 Thread Jonathan M. Bresler
> From: "Jonathan M. Bresler" <[EMAIL PROTECTED]> [snip] > 7:39PM up 29 mins, 1 user, load averages: 0.24, 0.32, 0.31 > Aspen:[209] uname -a > FreeBSD Aspen.Bresler.ORG 3.0-CURRENT FreeBSD 3.0-CURRENT #3: Sun Jan > 17 08:06:24 EST 1999 [EMAIL PROTECTED]:/usr/src/sys/compile/ASPEN > i386 > A

Re: copy-on-write optimized faults

1999-10-30 Thread Jonathan M. Bresler
i gets lots of "copy-on-write optimized faults". bu tthis may be a corner case. just rebooted my box. its used for ppp with nat aliasing and is in the middle of a cvsup follwed by 'cvs update -PAd'. the box is fairly weak40MB in a AMD 5x86-133MHz. Aspen:[208] uptime 7:39PM up 29 mins,

Re: copy-on-write optimized faults

1999-10-30 Thread Jesper Skriver
On Sat, Oct 30, 1999 at 06:54:07PM +0200, Leif Neland wrote: > > > > I would appreciate it if people running -current would run a "vmstat -s" > > and tell me if they see a NON-ZERO value for copy-on-write optimized > > faults. About six months ago, I implemented a simpler and more general > > o

Re: copy-on-write optimized faults

1999-10-29 Thread Brian Fundakowski Feldman
On Fri, 29 Oct 1999, Alan Cox wrote: > Thanks to Bernd and everyone else who has responded. Unless someone > reports a case where the old "optimization" gets applied more often > than 1 in ten million copy-on-write faults, I'm going to remove > the old code in a few days. At this frequency, the

Re: copy-on-write optimized faults

1999-10-29 Thread Alan Cox
On Sat, Oct 30, 1999 at 12:47:40AM +0200, Bernd Walter wrote: > > 307625181 copy-on-write faults >26 copy-on-write optimized faults Thanks to Bernd and everyone else who has responded. Unless someone reports a case where the old "optimization" gets applied more often than 1 in ten millio

RE: copy-on-write optimized faults

1999-10-29 Thread Alexander N. Kabaev
vmstat -s reports these numbers on my computer: 3649151 copy-on-write faults 1 copy-on-write optimized faults On 29-Oct-99 Alan Cox wrote: > I would appreciate it if people running -current would run a "vmstat -s" > and tell me if they see a NON-ZERO value for copy-on-write optimized >

Re: copy-on-write optimized faults

1999-10-29 Thread Bernd Walter
On Fri, Oct 29, 1999 at 02:47:43PM -0500, Alan Cox wrote: > I would appreciate it if people running -current would run a "vmstat -s" > and tell me if they see a NON-ZERO value for copy-on-write optimized > faults. About six months ago, I implemented a simpler and more general > optimization at an

Re: copy-on-write optimized faults

1999-10-29 Thread Ollivier Robert
According to Alan Cox: > I would appreciate it if people running -current would run a "vmstat -s" > and tell me if they see a NON-ZERO value for copy-on-write optimized FreeBSD keltia.freenix.fr 4.0-CURRENT FreeBSD 4.0-CURRENT #74: Thu Sep 9 00:20:51 CEST 1999 [EMAIL PROTECTED]:/src/src/sys

Re: copy-on-write optimized faults

1999-10-29 Thread Alan Cox
On Fri, Oct 29, 1999 at 09:51:55PM +0200, Jesper Skriver wrote: > > Those "about six months" can you be more specific ? > Sorry for being imprecise. It was May 16th. > $ uname -a > FreeBSD pebbles.tele.dk 4.0-CURRENT FreeBSD 4.0-CURRENT #2: Thu Apr 22 11:52:50 CEST >1999 > [EMAIL PROTECTED]:

Re: copy-on-write optimized faults

1999-10-29 Thread Jesper Skriver
On Fri, Oct 29, 1999 at 02:47:43PM -0500, Alan Cox wrote: > I would appreciate it if people running -current would run a "vmstat -s" > and tell me if they see a NON-ZERO value for copy-on-write optimized > faults. About six months ago, I implemented a simpler and more general > optimization at an