This is the mail archive of the cygwin mailing list for the Cygwin project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: very poor cygwin scp performance in some situations

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'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 that echo_server.c with similar results than on linux, with the tcp_nodelay set, and the results are again against cygwin binary.
On cygwin is too slow. I just don't know where the problem is.

Thanks for that what was interesting with scp was direction had a large impact on performance. On FreeBSD from Cygwin -> FreeBSD 700KB/s On Cygwin from Cygwin -> FreeBSD 1.2MB/s On FreeBSD from FreeBSD -> Cygwin 6.4MB/s

So there is definitely performance to be gained. I had a similar
problem with a basic perl FTP script uploading from Cygwin to
a FreeBSD machine and there simply setting the block size
to 8K fixed the issue. Note: From FreeBSD -> FreeBSD the
script didn't require said fix but it didn't effect it either. This
may be something to look at as well.


This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it.
In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137
or return the E.mail to

-- Unsubscribe info: Problem reports: Documentation: FAQ:

Unsubscribe info:
Problem reports:

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]