On Mon, Feb 8, 2010 at 9:48 AM, Mark Kettenis mark.kette...@xs4all.nl
wrote:
For one thing, I'd like to see some real benchmarks. Does using a
larger buffer really speed up cp? You claim moving a head between
reads and writes takes time, but so does moving it between reads. And
modern
On Sun, Feb 7, 2010 at 6:11 PM, Theo de Raadt dera...@cvs.openbsd.org
wrote:
I think adding big chunks of sysctl code to such specific applications
is very un-unix.
If choosing a buffer size is going to be a common operation, it should
be an API called to ask what the buffer size should be.
On Mon, Feb 8, 2010 at 9:48 AM, Mark Kettenis mark.kette...@xs4all.nl
wrote:
So how do we move forward?
For one thing, I'd like to see some real benchmarks. Does using a
larger buffer really speed up cp? You claim moving a head between
reads and writes takes time, but so does moving it
2010/2/7 Ted Unangst ted.unan...@gmail.com:
But using sysctl is insane. That is not portable.
Why does cp need to be portable? Who's porting OpenBSD cp to other
systems?
Good question.
--
antonvm
Why does cp need to be portable? Who's porting OpenBSD cp to other systems?
Will the same diff be added to every io generating program in /bin?
They all generate io, of course.
On Sun, Feb 7, 2010 at 2:09 PM, Theo de Raadt dera...@cvs.openbsd.org
wrote:
Why does cp need to be portable? Who's porting OpenBSD cp to other
systems?
Will the same diff be added to every io generating program in /bin?
They all generate io, of course.
I was planning on something similar
On Mon, Feb 8, 2010 at 12:11 AM, Theo de Raadt dera...@cvs.openbsd.org
wrote:
On Sun, Feb 7, 2010 at 2:09 PM, Theo de Raadt dera...@cvs.openbsd.org
wrote:
Why does cp need to be portable? B Who's porting OpenBSD cp to other
systems?
Will the same diff be added to every io generating program in
On Sun, Feb 7, 2010 at 6:11 PM, Theo de Raadt dera...@cvs.openbsd.org
wrote:
And in mv, for the cross-device case? I see others that do fast
reads, like sum. diff? cmp? grep? How many others? If cp(1)
is such a common operation (I bet it isn't), how soon before other
programs doing
On Sun, Feb 7, 2010 at 6:11 PM, Theo de Raadt dera...@cvs.openbsd.org wro=
te:
And in mv, for the cross-device case? =A0I see others that do fast
reads, like sum. =A0diff? =A0cmp? =A0grep? =A0How many others? =A0If cp(1=
)
is such a common operation (I bet it isn't), how soon before other
2010/2/8 Theo de Raadt dera...@cvs.openbsd.org:
For those of you who asked why cp needs to be portable, come on.
You've got it all wrong. If cp isn't written in a portable fashion,
then what is the point of doing anything else in a portable fashion.
This is good and reasonable answer. So I
On Fri, Feb 05, 2010 at 09:24:30PM -0500, Ted Unangst wrote:
Though for a program like cp, this may qualify as a big diff. :)
Continuing in my make IO suck less phase, cp would be a lot more
efficient if it didn't bounce the disk heads around so much. Instead of
using a tiny 64k buffer,
On 6 February 2010 c. 17:53:09 Otto Moerbeek wrote:
On Sat, Feb 06, 2010 at 09:14:53AM -0500, Ted Unangst wrote:
On Sat, Feb 6, 2010 at 8:44 AM, Mark Kettenis
mark.kette...@xs4all.nl wrote:
Continuing in my make IO suck less phase, cp would be a lot
more efficient if it didn't bounce
Whenever I find myself wishing for such knobs, I simply install FreeBSD.
2010/2/6 Vadim Zhukov persg...@gmail.com:
On 6 February 2010 c. 17:53:09 Otto Moerbeek wrote:
On Sat, Feb 06, 2010 at 09:14:53AM -0500, Ted Unangst wrote:
On Sat, Feb 6, 2010 at 8:44 AM, Mark Kettenis
On Sat, Feb 06, 2010 at 12:58:21PM -0500, Ted Unangst wrote:
On Sat, Feb 6, 2010 at 9:53 AM, Otto Moerbeek o...@drijf.net wrote:
The buffer cache should ne smart enough to optmize read and writes in
such large chunks so that the seeking gets reduced. The problem with
How? cp reads 64k.
On 6 February 2010 11:37, Claus Assmann ca+openbsd_t...@esmtp.org wrote:
Putting that kind of optimization into programs that read/write
large amount of data seems like the wrong way to go. It belongs in
a central place.
(That's just a comment from a clueless bystander...)
It belongs in
Now I look at the diff and see that the memory used is reasonably
small. But still, if multiple copies of your cp are run together on a
machine where available physical mem is low I might end up with a
machine swapping. That is certainly not going to speed up cp.
If multiple copies of
On Sat, Feb 6, 2010 at 1:35 PM, Otto Moerbeek o...@drijf.net wrote:
Add to that that doing I/O in big chunks is also putting more pressure
on the buffer cache.
The buffer cache keeps a copy of whatever goes through it regardless
of size. The io is broken down into 64k chunks no matter what
On Sat, Feb 6, 2010 at 1:54 PM, Theo de Raadt dera...@cvs.openbsd.org
wrote:
How? cp reads 64k
So change it to 1MB.
Yeah, right, like anyone will ok a diff like that on the vax.
But using sysctl is insane. That is not portable.
Why does cp need to be portable? Who's porting OpenBSD cp to
18 matches
Mail list logo