From: Anssi Saari <as@sci.fi>
To: linux-kernel@vger.kernel.org
Subject: Re: Linux 2.4.20-pre4-ac1
Date: Fri, 23 Aug 2002 19:30:56 +0300 [thread overview]
Message-ID: <20020823163056.GA7426@sci.fi> (raw)
In-Reply-To: <200208231046.g7NAk2914276@devserv.devel.redhat.com>
On Fri, Aug 23, 2002 at 06:46:02AM -0400, Alan Cox wrote:
> IDE status
[...]
This new IDE stuff has certainly worsened my longstanding CD writing problem.
Former situation (linux 2.2.19, 2.4.whatever, up to 2.4.19-ac4):
Audio CD writes hog system if writing at > 4x so that CPU intensive
stuff like watching video goes poorly, frames are dropped a lot, even
if video is 160x100 mpeg1 which needs about 1% CPU time. Writing speed
is about 14x according to cdrecord, when trying to write at 16x which
is the drive's max speed. Apparently the writer is smart enough to be
able to limit writing speed on the fly if data doesn't arrive fast enough.
cdrecord's fifo keeps at 0-3% mostly.
Data writes go fine at 16x. Audio writes work fine at 16x in FreeBSD
and Windows 98 with the same system. DMA is on, unmask_irq is on, 32bit
transfers are on, but don't matter much.
New situation (2.4.20-pre2-ac6, 2.4.20-pre4-ac1):
All writes now at no faster than 4x and even at that speed, system
can't keep cdrecord's fifo filled. System is really slow, mouse cursor
moves jerkily, opening an xterm takes several seconds.
System: MSI K7T Turbo-R motherboard, VIA kt133a/686b chipset, Duron 800MHz.
CD writer is LG GCE-8160B in /dev/hdc, main HD is /dev/hda.
No problems otherwise, though, so far.
next prev parent reply other threads:[~2002-08-23 16:25 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-08-23 10:46 Linux 2.4.20-pre4-ac1 Alan Cox
2002-08-23 12:21 ` Erik Andersen
2002-08-23 14:06 ` Eyal Lebedinsky
2002-08-23 14:29 ` Linux 2.4.20-pre4-ac1 (this time regarding 2.5.31) Thunder from the hill
2002-08-23 14:53 ` Steven Cole
2002-08-23 15:07 ` Thunder from the hill
2002-08-23 15:52 ` Greg KH
2002-08-23 15:51 ` Linux 2.4.20-pre4-ac1 Greg KH
2002-08-23 14:59 ` Erik Andersen
2002-08-23 15:16 ` [PATCH] fix bitops.h circular dependancies Erik Andersen
2002-08-23 15:59 ` Erik Andersen
2002-08-23 15:57 ` Linux 2.4.20-pre4-ac1 Markus Plail
2002-08-23 18:16 ` Andre Hedrick
2002-08-23 16:30 ` Anssi Saari [this message]
2002-08-23 16:56 ` Markus Plail
2002-08-24 16:03 ` Anssi Saari
2002-08-23 17:18 ` Alan Cox
2002-08-23 19:30 ` Anssi Saari
2002-08-24 13:27 ` Allan Duncan
2002-08-24 13:55 ` Alan Cox
2002-08-24 14:07 ` Erik Andersen
2002-08-25 11:01 ` Tomas Szepe
2002-08-25 11:10 ` Thunder from the hill
2002-08-25 11:32 ` Thomas Molina
2002-08-25 11:45 ` Sean Neakums
2002-08-25 12:10 ` Geert Uytterhoeven
2002-08-25 12:19 ` Thunder from the hill
2002-08-25 12:25 ` Sean Neakums
2002-08-25 13:44 ` Tomas Szepe
2002-08-26 2:01 ` Rik van Riel
2002-08-25 11:41 ` Tomas Szepe
2002-08-26 0:24 ` Allan Duncan
2002-08-25 21:33 ` Henning P. Schmiedehausen
2002-08-24 17:32 ` Axel Siebenwirth
2002-08-24 17:59 ` Alan Cox
2002-08-25 4:49 ` Zephaniah E. Hull
2002-08-25 20:15 ` Adrian Bunk
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20020823163056.GA7426@sci.fi \
--to=as@sci.fi \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox