OpenSSH
[Top] [All Lists]

Nagle & delayed ACK strike again

To: openssh-unix-dev@mindrot.org
Subject: Nagle & delayed ACK strike again
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Wed, 20 Dec 2006 17:14:37 +0100
Delivered-to: sp-com-lists@consult.net
Delivered-to: openssh-unix-dev-list1@securepoint.com
Delivered-to: openssh-unix-dev-tmda@mindrot.org
Delivered-to: openssh-unix-dev@mindrot.org
List-archive: <http://lists.mindrot.org/pipermail/openssh-unix-dev>
List-help: <mailto:openssh-unix-dev-request@mindrot.org?subject=help>
List-id: Development of portable OpenSSH <openssh-unix-dev.mindrot.org>
List-post: <mailto:openssh-unix-dev@mindrot.org>
List-subscribe: <http://lists.mindrot.org/mailman/listinfo/openssh-unix-dev>, <mailto:openssh-unix-dev-request@mindrot.org?subject=subscribe>
List-unsubscribe: <http://lists.mindrot.org/mailman/listinfo/openssh-unix-dev>, <mailto:openssh-unix-dev-request@mindrot.org?subject=unsubscribe>
Sender: openssh-unix-dev-bounces+openssh-unix-dev-list1=securepoint.com@mindrot.org
This time the problem is that the ssh server only sets TCP_NODELAY for
interactive (tty) sessions or if X11 forwarding is enabled.  Neither
of which are true for the use of the sftp subsystem.  This hurts
upload performance for sftp/sshfs.

I'm not sure why this hasn't cropped up earlier.  Were there any
TCP_NODELAY related changes in the sshd code recently?

Is there a reason not to enable NODELAY unconditionally?  Any reason
why the server end is different from the client (where NODELAY is now
uncoditionally enabled) in this respect?

Thanks,
Miklos
_______________________________________________
openssh-unix-dev mailing list
openssh-unix-dev@mindrot.org
http://lists.mindrot.org/mailman/listinfo/openssh-unix-dev

<Prev in Thread] Current Thread [Next in Thread>