- Original Message -
From: Corinna Vinschen
On Mar 27 16:39, Steven Hartland wrote:
I've done quite a bit of digging and not found any real answers
on why cygwin's scp performance is so poor.
Cygwin is just emulating POSIX by calling Windows functions. It's not
an operating system
On Mar 28 11:43, Steven Hartland wrote:
- Original Message -
From: Corinna Vinschen
On Mar 27 16:39, Steven Hartland wrote:
I've done quite a bit of digging and not found any real answers
on why cygwin's scp performance is so poor.
Cygwin is just emulating POSIX by calling
On Tue, 28 Mar 2006, Corinna Vinschen wrote:
It turns out that three factors limit the speed on the client side:
- The worst of all is ssh itself. When reading blocks from the network,
it uses an 8K buffer. Whatever you try with setting different socket
buffer sizes or disabling the
On Tue, 28 Mar 2006, Igor Peshansky wrote:
On Tue, 28 Mar 2006, Corinna Vinschen wrote:
It turns out that three factors limit the speed on the client side:
- The worst of all is ssh itself. When reading blocks from the network,
it uses an 8K buffer. Whatever you try with setting
On Mar 28 09:57, Igor Peshansky wrote:
All of the above will probably need to be suggested to the OpenSSH team
(preferably in the form of patches). Volunteers welcome (nudge-nudge,
wink-wink, Steve). :-)
You don't seriously believe that stuff like that hasn't been already
suggested a couple
On Mar 28 17:12, Corinna Vinschen wrote:
On Mar 28 09:57, Igor Peshansky wrote:
All of the above will probably need to be suggested to the OpenSSH team
(preferably in the form of patches). Volunteers welcome (nudge-nudge,
wink-wink, Steve). :-)
You don't seriously believe that stuff
On Tue, 28 Mar 2006, Corinna Vinschen wrote:
On Mar 28 09:57, Igor Peshansky wrote:
All of the above will probably need to be suggested to the OpenSSH team
(preferably in the form of patches). Volunteers welcome (nudge-nudge,
wink-wink, Steve). :-)
You don't seriously believe that stuff
- Original Message -
From: Corinna Vinschen
Yeah, I'm just slightly annoyed about the Cygwin is slow routine on
this mailing list.
I would not say Cygwin is not slow persay but there issues in certain
areas which have issues. This is what I was trying to highlight and as
such hopefully
On Mar 28 19:43, Steven Hartland wrote:
From: Corinna Vinschen
- The worst of all is ssh itself. When reading blocks from the network,
it uses an 8K buffer. Whatever you try with setting different socket
buffer sizes or disabling the Nagle algorithm, nothing has any
interesting impact if
I've done quite a bit of digging and not found any real answers
on why cygwin's scp performance is so poor.
So I decided to do some tests, here the results:
== machines ==
* P4 2.8Ghz
* 1GB RAM
* IDE disk
* Running nothing but these test
=== test1 ===
* FreeBSD 5.4-RELEASE
* OpenSSH_3.8.1p1
On 27 March 2006 16:39, Steven Hartland wrote:
I've done quite a bit of digging and not found any real answers
on why cygwin's scp performance is so poor.
See the thread about select() too slow last week for an explanation of the
Nagle algorithm, how windoze's implementation of it appears to
- Original Message -
From: Dave Korn
On 27 March 2006 16:39, Steven Hartland wrote:
I've done quite a bit of digging and not found any real answers
on why cygwin's scp performance is so poor.
See the thread about select() too slow last week for an explanation of the
Nagle
Hello,
I've initiated the post select() too slow.
The example I've done was a non-blocking tcp echo_server.c and how
slow it was on linux compared with cygwin.
In fact after activation oh tcp_nodelay option the times were similar.
Meanwhile I've done another test, I've added ssl on top of
- Original Message -
From: Pedro Inacio
I've initiated the post select() too slow.
The example I've done was a non-blocking tcp echo_server.c and how
slow it was on linux compared with cygwin.
In fact after activation oh tcp_nodelay option the times were similar.
Meanwhile I've done
I'm starting to think that openssl have some performance issues on
cygwin.
my fixed non-blocking echo_server.c with openssl is too slow when
compared with the same code compiled on Linux.
is something like 40ms on Linux to 1040ms on Cygwin.
On 2006/03/27, at 23:32, Steven Hartland wrote:
- Original Message -
From: Pedro Inacio
I'm starting to think that openssl have some performance issues on
cygwin.
my fixed non-blocking echo_server.c with openssl is too slow when
compared with the same code compiled on Linux.
is something like 40ms on Linux to 1040ms on Cygwin.
Also very interesting is when running sshd from the command line with
/usr/sbin/sshd -D vs running it via cygrunsvr I get:
* cmdline = 192MB 4.4MB/s 00:44
* cygrunsvr = 192MB 6.4MB/s 00:30
* cmdline without -D = 192MB 6.4MB/s 00:30
I tried running:
/usr/sbin/sshd -D 21 /dev/null but
Steven Hartland wrote:
Also very interesting is when running sshd from the command line with
/usr/sbin/sshd -D vs running it via cygrunsvr I get:
* cmdline = 192MB 4.4MB/s 00:44
* cygrunsvr = 192MB 6.4MB/s 00:30
* cmdline without -D = 192MB 6.4MB/s 00:30
I tried running:
Interesting idea that I just tried setting high prio on the command line
version and it does benefit obtaining 6.0MB/s but not quite matching
the 6.2MB/s of the daemonised version.
Note: Using realtime prio drops the rate back to 4.3MB/s
Oh just tried using above normal and that hits 6.2MB/s so
On Mar 27 16:39, Steven Hartland wrote:
I've done quite a bit of digging and not found any real answers
on why cygwin's scp performance is so poor.
Cygwin is just emulating POSIX by calling Windows functions. It's not
an operating system which runs natively on the machine, so what do
you
20 matches
Mail list logo
