Date: Mon, 25 Jan 1999 17:35:25 -0800 (PST) From: Matthew Dillon <dillon@apollo.backplane.com> To: Brian Feldman <green@unixhelp.org> Cc: Sheldon Hearn <axl@iafrica.com>, Lee Cremeans <lee@st-lcremean.tidalwave.net>, current@FreeBSD.ORG Subject: Re: IDE DMA works, I'll be a... Message-ID: <199901260135.RAA11762@apollo.backplane.com> References: <Pine.BSF.4.05.9901252016180.7918-100000@janus.syracuse.net>
next in thread | previous in thread | raw e-mail | index | archive | help
:> I would like to know if your transfer rate improves or not, and by
:> how much.
:>
:> #if 0
:> if (cnt.v_inactive_count / 3 > page_shortage) {
:> maxlaunder = 0;
:> launder_loop = 0;
:> } else
:> #endif
:> {
:> -Matt
:
:I'd rather use if (0 && cnt.v_inactive_count / 3 > page_shortage) {. I'm
:trying it out now, here's the "before":
:
:IOZONE performance measurements:
: 2972048 bytes/second for writing the file
: 2962863 bytes/second for reading the file
: Brian Feldman _ __ ___ ___ ___
Welll... I went ahead and tested it on my diskless workstation,
which actually has a DMA IDE drive connected to it at the moment
for another test I'm running.
I didn't see any change in performance. That doesn't meant that
hasn't been a chance, just that it doesn't look like the one thing
I thought might be causing it is causing it.
Are you sure the problem isn't simply that your disk is getting
a bit more full and causing the test to skip around more ( or move
to more inner tracks, which have lower transfer rates), and
thus appear to slow down a little ?
-Matt
Before ( iozone 64 on a 48MB machine )
IOZONE performance measurements:
7809031 bytes/second for writing the file
10324440 bytes/second for reading the file
IOZONE performance measurements:
8388608 bytes/second for writing the file
10324440 bytes/second for reading the file
After ( iozone 64 on a 48MB machine )
IOZONE performance measurements:
8103711 bytes/second for writing the file
10336864 bytes/second for reading the file
IOZONE performance measurements:
8429768 bytes/second for writing the file
10324440 bytes/second for reading the file
Matthew Dillon
<dillon@backplane.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199901260135.RAA11762>