Date: Sat, 1 Nov 1997 21:36:30 -0800 (PST) From: "Jamil J. Weatherbee" <jamil@trojanhorse.ml.org> To: Mike Smith <mike@smith.net.au> Cc: hackers@freebsd.org, dufault@hda.com Subject: Re: Strategy Routines Message-ID: <Pine.BSF.3.96.971101212300.671C-100000@trojanhorse.ml.org> In-Reply-To: <199711020252.NAA00521@word.smith.net.au>
next in thread | previous in thread | raw e-mail | index | archive | help
Ok, so say I am doing outb(), one bang after the other. Since timo can
sleep up to 1/100 of a second. What would be a good "packet size" (i.e.
number of outb() to limit myself to in a loop. My initial estimates would
indicate that I could break up the buffer in something like:
(this is just for example I know the modulus is pretty damn
innefficient)
for (i=0; i<len; buf++)
{
outb (port, *buf)
if (!(++i % 2048)) tsleep (myself, PPAUSE, "iosink", 1);
}
> This is a fault in the driver design. Drivers should not hog the
> cpu, obviously. Try calling tsleep() out of the driver with a very
> short timeout.
>
> mike
>
>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.96.971101212300.671C-100000>