Re: High system load when burning audio CDs on VIA686B
* Markus Plail writes: * Len Sorensen writes: use 2048byte blocks, can't use dma on current linux kernels (supposedly it will be possible in 2.6 kernels). Audio would fit that category and hence use a lot more cpu. It is already possible in 2.5 kernels and I am still convinced that it's also possible with 2.4 kernels. Just tested it once again. Audio CD at 20x speed with less than 3% CPU load (user+system). My kernel must be doing something wrong ;-) Just a quick update. Today I bought a cd writer for a friend. It's an MSI 48x. Now I have the very same symptoms as everybody else. At 20x RAW it takes about 15% system load and when the drive switches to 30x it's getting unstable already, i.e. 0% idle and buffer getting low. I have no idea why I only have 3% system load with my acer 20x drive. regards Markus -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Nov 26 at 02:28, David Bell spoke: Is this an issue in the kernel or cdrecord? It might be an issue of the OS. Try FreeBSD with DMA enabled. If not, if I put the burner on a Promise IDE controller card, would the problems subside? Promise 100/133 TX2 don't support DMA when burning on ATAPI-Writers. Controllers based on Silicon Images 0680 do. -Hanspeter -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
From: Hanspeter Roth [EMAIL PROTECTED] On Nov 26 at 02:28, David Bell spoke: Is this an issue in the kernel or cdrecord? It might be an issue of the OS. And it cannot be cdrecord Jörg EMail:[EMAIL PROTECTED] (home) Jörg Schilling D-13353 Berlin [EMAIL PROTECTED] (uni) If you don't have iso-8859-1 [EMAIL PROTECTED] (work) chars I am Jorg Schilling URL: http://www.fokus.gmd.de/usr/schilling ftp://ftp.fokus.gmd.de/pub/unix -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Dec 01 at 22:00, Joerg Schilling spoke: From: Hanspeter Roth [EMAIL PROTECTED] On Nov 26 at 02:28, David Bell spoke: Is this an issue in the kernel or cdrecord? It might be an issue of the OS. And it cannot be cdrecord It's probably a matter of DMA. On certain OS' it's easy to switch on DMA for ATAPI-drives. For others the kernel hackers won't tell you how to accomplish this. -Hanspeter -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Wed, Nov 27, 2002 at 11:54:22PM +0100, Markus Plail wrote: Yes, ATAPI. acer CDRW 2010A (crappy), ECS KSS5A with Athlon XP1800+. SIS5513: chipset revision 208 SIS5513: not 100%% native mode: will probe irqs later SiS735ATA 100 controller As soon as I disable DMA I get the high loads reported everywhere. Are you disableing dma on the HD or the cd burner though? Len Soresen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
* Len Sorensen writes: On Wed, Nov 27, 2002 at 11:54:22PM +0100, Markus Plail wrote: Yes, ATAPI. acer CDRW 2010A (crappy), ECS KSS5A with Athlon XP1800+. SIS5513: chipset revision 208 SIS5513: not 100%% native mode: will probe irqs later SiS735ATA 100 controller As soon as I disable DMA I get the high loads reported everywhere. Are you disableing dma on the HD or the cd burner though? Haven't tried disabling the HD as well. I was refering to disabling DMA on the burner. regards Markus -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Thu, Nov 28, 2002 at 03:48:03PM +0100, Markus Plail wrote: Haven't tried disabling the HD as well. I was refering to disabling DMA on the burner. Well I can't imagine why yours works an no one elses seems to. But what do I know. I only know what I read about it. Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
* Len Sorensen writes: On Tue, Nov 26, 2002 at 03:56:21PM -0600, David Bell wrote: On Tue, 2002-11-26 at 15:37, Len Sorensen wrote: I see NOTHING there that indicates if dma is on or off, only what is supported. The * does NOT indicate linux is using dma. /proc/ide/hd?/settings does, as might hdparm device, by itself. Your method most certainly does not. Sorry about that, It seems I wanted hdparm -v, not hdparm -i: [hdparm saying DMA is on] ...As you can see (I hope), DMA is enabled on all of these devices. Yep. Looks on. Can't think of anything else, other than maybe you are burning cds that are not plain iso data images. Anything that doens't Well, have a look at the subject ;-) use 2048byte blocks, can't use dma on current linux kernels (supposedly it will be possible in 2.6 kernels). Audio would fit that category and hence use a lot more cpu. It is already possible in 2.5 kernels and I am still convinced that it's also possible with 2.4 kernels. Just tested it once again. Audio CD at 20x speed with less than 3% CPU load (user+system). My kernel must be doing something wrong ;-) regards Markus -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Wed, Nov 27, 2002 at 10:53:35PM +0100, Markus Plail wrote: It is already possible in 2.5 kernels and I am still convinced that it's also possible with 2.4 kernels. Just tested it once again. Audio CD at 20x speed with less than 3% CPU load (user+system). My kernel must be doing something wrong ;-) With an ATAPI cd burner? Which IDE chipset, which CPU and speed? Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
* Len Sorensen writes: On Wed, Nov 27, 2002 at 10:53:35PM +0100, Markus Plail wrote: It is already possible in 2.5 kernels and I am still convinced that it's also possible with 2.4 kernels. Just tested it once again. Audio CD at 20x speed with less than 3% CPU load (user+system). My kernel must be doing something wrong ;-) With an ATAPI cd burner? Which IDE chipset, which CPU and speed? Yes, ATAPI. acer CDRW 2010A (crappy), ECS KSS5A with Athlon XP1800+. SIS5513: chipset revision 208 SIS5513: not 100%% native mode: will probe irqs later SiS735ATA 100 controller As soon as I disable DMA I get the high loads reported everywhere. regards Markus -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
* David Bell writes: [high system load when doing anything other than burning plain data discs] Is this an issue in the kernel or cdrecord? Kernel. Is it expected to be fixed soon? Kinda fixed since 2.5.47 IIRC. ide_scsi isn't needed anymore, but readcd doesn't work yet. If not, if I put the burner on a Promise IDE controller card, would the problems subside? Probably not. Promise controllers are known for not really liking devices other than hard discs. I seem to be one of very few people who got audio CD burning to work in 2.4 kernels. In the end I could write audio CDs at 20x speed in RAW96 mode with no more than 3% system load. You can contatc me personally if you want to know my settings (or google for them) but they don't seem to work for everyone and Joerg didn't even believe me I got it working ;-) regards Markus -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
* David Bell writes: Yes, DMA is enabled on all drives: [12:50:51][root@david:/home/david]# hdparm -i /dev/hda hdparm -i isn't really appropriate here. You should use -v. man hdparm: -i Display the identification info that was obtained from the drive at boot time, if available. This is a feature of modern IDE drives, and may not be supported by older devices. The data returned may or may not be current, depending on activity since booting the system. However, the current multiple sector mode count is always shown. For a more detailed interpretation of the identifica tion info, refer to AT Attachment Interface for Disk Drives (ANSI ASC X3T9.2 working draft, revision 4a, April 19/93). regards Markus -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Tue, Nov 26, 2002 at 12:53:36PM -0600, David Bell wrote:
Yes, DMA is enabled on all drives:
[12:50:51][root@david:/home/david]# hdparm -i /dev/hda
/dev/hda:
Model=Maxtor 6E040L0, FwRev=NAR61590, SerialNo=E10RVGWE
Config={ Fixed }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
BuffType=DualPortCache, BuffSize=2048kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=80293248
IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 *udma5 udma6
AdvancedPM=yes: disabled (255) WriteCache=enabled
Drive Supports : ataATA-1 ATA-2 ATA-3 ATA-4 ATA-5 ATA-6 ATA-7
I see NOTHING there that indicates if dma is on or off, only what is
supported. The * does NOT indicate linux is using dma.
/proc/ide/hd?/settings does, as might hdparm device, by itself.
Your method most certainly does not.
Len Sorensen
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
Re: High system load when burning audio CDs on VIA686B
On Tue, 2002-11-26 at 15:37, Len Sorensen wrote: I see NOTHING there that indicates if dma is on or off, only what is supported. The * does NOT indicate linux is using dma. /proc/ide/hd?/settings does, as might hdparm device, by itself. Your method most certainly does not. Sorry about that, It seems I wanted hdparm -v, not hdparm -i: Maxtor 7200RPM hard drive: [15:53:45][root@david:/home/david]# hdparm -v /dev/hda /dev/hda: multcount= 16 (on) I/O support = 1 (32-bit) unmaskirq= 1 (on) using_dma= 1 (on) keepsettings = 0 (off) nowerr = 0 (off) readonly = 0 (off) readahead= 8 (on) geometry = 4998/255/63, sectors = 80293248, start = 0 busstate = 1 (on) Pioneer 106S DVD-ROM: [15:53:47][root@david:/home/david]# hdparm -v /dev/hdc /dev/hdc: HDIO_GET_MULTCOUNT failed: Input/output error I/O support = 3 (32-bit w/sync) unmaskirq= 0 (off) using_dma= 1 (on) keepsettings = 0 (off) HDIO_GET_NOWERR failed: Input/output error readonly = 0 (off) BLKRAGET failed: Input/output error HDIO_GETGEO failed: Invalid argument busstate = 1 (on) Lite-On 24x CD-RW: [15:54:28][root@david:/home/david]# hdparm -v /dev/hdd /dev/hdd: HDIO_GET_MULTCOUNT failed: Input/output error I/O support = 3 (32-bit w/sync) unmaskirq= 0 (off) using_dma= 1 (on) keepsettings = 0 (off) HDIO_GET_NOWERR failed: Input/output error readonly = 0 (off) BLKRAGET failed: Input/output error HDIO_GETGEO failed: Invalid argument busstate = 1 (on) ...As you can see (I hope), DMA is enabled on all of these devices. Thanks. -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of unsubscribe. Trouble? Contact [EMAIL PROTECTED]
