From owner-freebsd-alpha Tue Nov 24 07:55:37 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id HAA05098 for freebsd-alpha-outgoing; Tue, 24 Nov 1998 07:55:37 -0800 (PST) (envelope-from owner-freebsd-alpha@FreeBSD.ORG) Received: from duke.cs.duke.edu (duke.cs.duke.edu [152.3.140.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id HAA05093 for ; Tue, 24 Nov 1998 07:55:36 -0800 (PST) (envelope-from gallatin@cs.duke.edu) Received: from grasshopper.cs.duke.edu (grasshopper.cs.duke.edu [152.3.145.30]) by duke.cs.duke.edu (8.9.1/8.9.1) with ESMTP id KAA27814; Tue, 24 Nov 1998 10:54:29 -0500 (EST) Received: (from gallatin@localhost) by grasshopper.cs.duke.edu (8.9.1/8.9.1) id KAA63314; Tue, 24 Nov 1998 10:53:58 -0500 (EST) (envelope-from gallatin@cs.duke.edu) From: Andrew Gallatin MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Date: Tue, 24 Nov 1998 10:53:58 -0500 (EST) To: shimon@simon-shapiro.org Cc: matth@uk.aiesec.org, freebsd-alpha@FreeBSD.ORG Subject: Re: SCP/FTP Performance In-Reply-To: References: X-Mailer: VM 6.43 under 20.4 "Emerald" XEmacs Lucid Message-ID: <13914.54304.379294.304492@grasshopper.cs.duke.edu> Sender: owner-freebsd-alpha@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Simon Shapiro writes: > > Matt Hamilton, On 24-Nov-98 you wrote: > > On Mon, 23 Nov 1998, Simon Shapiro wrote: > > > > > I know I am missing something here, but it appears Alpha based. > > > > Not that I know a huge amount about this, but could it be some > > byte-order > > related problem? Something to do with switching the byte order around > > un-necessarily, before sticking on the wire? Or switching it wrongly > > when > > it gets back? > > I doubt that; First, it may add as much as 1% on an alpha. Second, the > alpha is already in network order. > > Simon Actually, its not in network byte order, but as you state, that's of little consequence. The alpha byte-swapping & checksum code could probably use a little work, but you're not going to notice much impact with 433+ Mhz Mhz 21164a's at speeds as slow as 100Mb. My suspicion is that its the fault of the 433au's tulip interface. The if_de.c driver support for DEC-branded 21143's, such as the one in your 433au, is bad. For example, I cannot get my personal workstations go into full-duplex mode in either FreeBSD or NetBSD. Your 64kb/sec speeds are typical of a duplex mismatch. With the 433au's tulip set to autosense, I suspect the duplex modes might be waffling between full & half. You might try hardcoding the alphas nics to 100baseTX. Cheers, Drew To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message