From owner-freebsd-current Sun Jan 17 17:46:13 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id RAA12812 for freebsd-current-outgoing; Sun, 17 Jan 1999 17:46:13 -0800 (PST) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.26.10.9]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id RAA12777 for ; Sun, 17 Jan 1999 17:46:05 -0800 (PST) (envelope-from bde@godzilla.zeta.org.au) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.7/8.8.7) id MAA16732; Mon, 18 Jan 1999 12:45:57 +1100 Date: Mon, 18 Jan 1999 12:45:57 +1100 From: Bruce Evans Message-Id: <199901180145.MAA16732@godzilla.zeta.org.au> To: bde@zeta.org.au, kpielorz@tdx.co.uk Subject: Re: Problems with new IDE's & -current Cc: current@FreeBSD.ORG, lcremean@tidalwave.net Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG >> New models of IBM IDE drives are fast enough to consume a significant >> fraction (perhaps > 100%) of PIO mode 4 bandwidth (16.6 MB/s). Don't >> use them without DMA. Don't use them without UltraDMA (33.3 MB/s) if >> you want full performance. > >I presume the last "don't" should have been a 'do', i.e. _do_ use them >with UltraDMA if you want full performance...? Don't use without == do use with. >Also, the controller their running off isn't _Any_ DMA capable, at a guess >it's going to be PIO4 tops, in which case (and as EIDA/UltraDMA are mean't >to be 'backwards' compatible) - does this point to a bug/problem with the >wdc driver? (i.e. drive too fast = wdc interrupt timeouts?) This is a general problem with i/o capabilties exceeding system capabilities. Bruce To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message