From owner-freebsd-scsi Wed May 13 09:00:21 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA20303 for freebsd-scsi-outgoing; Wed, 13 May 1998 09:00:21 -0700 (PDT) (envelope-from owner-freebsd-scsi@FreeBSD.ORG) Received: from carpe.net (news.carpe.net [194.162.243.7]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id JAA20298 for ; Wed, 13 May 1998 09:00:18 -0700 (PDT) (envelope-from grefen@carpe.net) Received: from helva.grefen.carpe.net (root@helva.grefen.carpe.net [194.162.243.129]) by carpe.net (8.8.6/8.8.6) with ESMTP id RAA00992; Wed, 13 May 1998 17:59:56 +0200 (MET DST) Received: from hex.grefen.carpe.net (root@hex [194.162.243.130]) by helva.grefen.carpe.net (8.7.5/8.7.3) with ESMTP id RAA04981; Wed, 13 May 1998 17:56:31 +0200 (MET DST) Received: from hex.grefen.carpe.net (grefen@localhost [127.0.0.1]) by hex.grefen.carpe.net (8.7.3/8.7.3) with ESMTP id RAA23011; Wed, 13 May 1998 17:56:28 +0200 (MET DST) To: fireston@lexmark.com Cc: gibbs@narnia.plutotech.com (Justin T. Gibbs), freebsd-scsi@FreeBSD.ORG Subject: Re: SCSI timeouts in dataout mode Reply-To: grefen@carpe.net In-reply-to: Mik Firestone's message <199805131353.AA11660@interlock2.lexmark.com> of Wed, 13 May 98 09:53:45 EDT. References: <199805131353.AA11660@interlock2.lexmark.com> Date: Wed, 13 May 1998 17:56:27 +0200 Message-ID: <23007.895074987@hex.grefen.carpe.net> From: Stefan Grefen Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In message <199805131353.AA11660@interlock2.lexmark.com> Mik Firestone wrote: [...] > > I will make the observation that this error is somehow related to the amount > of time it takes to write the file. If it takes more then 10 seconds to > write, we see this error. We have not yet tried to read a large file to see > what problems that can cause. > > To hazard a guess, I really think this is some strange interaction between th > e > scsi code and the cache on the HP. Either the HP is doing the right kind of > handshaking or the FreeBSD box is missing it. But this is only a guess. If I remember correctly some of those RAID arrays report good-status even if the data is not on disk yet (either assuing or providing UPS for the array). If the Cache is full you have to wait until some space is freeed, so the command 'hangs' and times out. The SCSI analyser would just see an initial transfer and no reconnection. Try increasing the timeout by a factor of 2 or 4 (or 8) and see if it still happens. Or you could try configure the RAID for write-through instead of write-back. But than you should turn on tags ... (I think you can configure some HP-arrays with a terminal over a serial line) > > -- > Mik Firestone fireston@lexmark.com > If ever I become an Evil Overlord: > All naive, busty tavern wenches in my realm will be replaced with surly, > world-weary waitresses who will provide no unexpected reinforcement and/or > romantic subplot for the hero or his sidekick. > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-scsi" in the body of the message -- Stefan Grefen Am Hummertal 4, 55283 Nierstein, Germany grefen@carpe.net +49 6133 927484 Fax:+49 6133 927486 Idiot, n.: A member of a large and powerful tribe whose influence in human affairs has always been dominant and controlling. -- Ambrose Bierce, "The Devil's Dictionary" To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message