From owner-freebsd-hackers Fri Apr 18 04:37:55 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id EAA27035 for hackers-outgoing; Fri, 18 Apr 1997 04:37:55 -0700 (PDT) Received: from labinfo.iet.unipi.it (labinfo.iet.unipi.it [131.114.9.5]) by freefall.freebsd.org (8.8.5/8.8.5) with SMTP id EAA26983 for ; Fri, 18 Apr 1997 04:36:48 -0700 (PDT) Received: from localhost (luigi@localhost) by labinfo.iet.unipi.it (8.6.5/8.6.5) id MAA08521; Fri, 18 Apr 1997 12:44:39 +0200 From: Luigi Rizzo Message-Id: <199704181044.MAA08521@labinfo.iet.unipi.it> Subject: Re: video capture driver interface to file system? To: dufault@hda.com (Peter Dufault) Date: Fri, 18 Apr 1997 12:44:39 +0200 (MET DST) Cc: hackers@freebsd.org In-Reply-To: <199704181112.HAA17117@hda.hda.com> from "Peter Dufault" at Apr 18, 97 07:12:36 am X-Mailer: ELM [version 2.4 PL23] Content-Type: text Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > > and probably, in addition to preallocation, make sure that your write() > > calls are aligned to the FS/device blocksize otherwise (probably) each > > write will be preceeded by a hidden read to take care of fragmentation ? > > Or you'll get an EIO somewhere along the line when you try to do > the unaligned access. Amancio is trying to avoid the buffer copy > inherent in going through the buffer cache - I'm waiting to see > what his numbers are to see if he has to do that or it just hurts > his sense of system utilization to not do it. About the only way probably the latter :) I have IDE disks (WD Caviar) streming files at about 3MB/s (sustained over about 10 minutes) with a Pentium 133 running "tv" at the same time. Even if the raw disk speed would go up to 10MB/s I doubt the copy overhead would barely slow down the process on a PPro. Luigi