From owner-freebsd-bugs Fri May 15 16:23:57 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA22273 for freebsd-bugs-outgoing; Fri, 15 May 1998 16:23:57 -0700 (PDT) (envelope-from owner-freebsd-bugs@FreeBSD.ORG) Received: from freefall.freebsd.org (freefall.FreeBSD.ORG [204.216.27.21]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA22265 for ; Fri, 15 May 1998 16:23:56 -0700 (PDT) (envelope-from gnats@FreeBSD.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.8.8/8.8.5) id QAA14099; Fri, 15 May 1998 16:20:01 -0700 (PDT) Date: Fri, 15 May 1998 16:20:01 -0700 (PDT) Message-Id: <199805152320.QAA14099@freefall.freebsd.org> To: freebsd-bugs@FreeBSD.ORG From: Bill Fenner Subject: Re: bin/6646: dump(8) using remote tape drive is too slow Reply-To: Bill Fenner Sender: owner-freebsd-bugs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org The following reply was made to PR bin/6646; it has been noted by GNATS. From: Bill Fenner To: wataru-s@mfeed.ad.jp Cc: freebsd-gnats-submit@FreeBSD.ORG Subject: Re: bin/6646: dump(8) using remote tape drive is too slow Date: Fri, 15 May 1998 16:21:02 PDT This is a TCP bug. Lowering the window size is a workaround, but someone should figure out what's really going on. It's clearly delayed ACK's that is causing the poor throughput with the session with the higher MSS; the sender sends 7 packets, the receiver acks 6 and the sender doesn't send any more so the receiver acks the 7th after 200ms; then the sender sends another 7 packets. I haven't gone into it any deeper than that (e.g. why isn't the sender sending packets in response to each ack). Setting TCP_MAXSEG to 1024 is an OK workaround for now, but we need to figure out what's wrong with the TCP stack that it's not sending anything until the whole outstanding window is ACK'd. (It almost feels like SWS avoidance is kicking in by accident...) Bill To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-bugs" in the body of the message