From owner-freebsd-hackers Sun Jul 26 19:12:53 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA19294 for freebsd-hackers-outgoing; Sun, 26 Jul 1998 19:12:53 -0700 (PDT) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from tokyonet-entrance.astec.co.jp (tokyonet-entrance.astec.co.jp [202.239.16.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA19250 for ; Sun, 26 Jul 1998 19:12:35 -0700 (PDT) (envelope-from hamada@astec.co.jp) Received: from amont.astec.co.jp (amont.astec.co.jp [172.20.10.1]) by tokyonet-entrance.astec.co.jp (8.9.1+3.0W/3.7W-astecMX2.3) with ESMTP id LAA10775; Mon, 27 Jul 1998 11:11:52 +0900 (JST) Received: from stone.astec.co.jp (stone.astec.co.jp [172.20.26.2]) by amont.astec.co.jp (8.7.6/3.6W-astecMX2.4) with ESMTP id LAA24520; Mon, 27 Jul 1998 11:11:52 +0900 (JST) Received: (from hamada@localhost) by stone.astec.co.jp (8.8.5/3.5W-solaris1-1.2) id LAA27031; Mon, 27 Jul 1998 11:11:50 +0900 (JST) Date: Mon, 27 Jul 1998 11:11:50 +0900 (JST) Message-Id: <199807270211.LAA27031@stone.astec.co.jp> From: HAMADA Naoki References: <199807270133.SAA13259@antipodes.cdrom.com> To: mike@smith.net.au CC: smoergrd@oslo.geco-prakla.slb.com, sbabkin@dcn.att.com, hackers@FreeBSD.ORG In-reply-to: Mike Smith's message of "Sun, 26 Jul 1998 18:33:47 -0700" <199807270133.SAA13259@antipodes.cdrom.com> Subject: Re: NIC drivers Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG >> smoergrd@oslo.geco-prakla.slb.com writes: >> >Believe me, it still sucks. Search the archives (both the mailing list >> >archives and the PR database) for "no buffer space", and/or "ep0". >> >Basically, the driver is fine for telnet and mail, but wedges under >> >sustained load. I can get it to hang without ever going above 20 kBps >> >(160 kbps). Gimme an Intel EtherExpress. >> >> I carefully looked through the source code to find a bug which results >> mbuf leaks. Could you try this patch? > >Have you guys gone any further on this one? Is the patch OK, or broken? Sorry guys, this patch is wrong. ERR_RX_INCOMPLETE (which should be renamed to `RX_INCOMPLETE') is an indication of not an error but an incoming packet, so you must not remove the incoming packet. NetBSD's ep driver seems to have some kluge for locking problems, but now I want to spend my time to support new 3C905B adapters... - nao To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message