[linux-audio-user] Interuptions While Recording

[Tobias Ulbricht]

On Tue, Feb 11, 2003 at 03:22:13PM -0500, linuxmedia4 at netscape.net wrote:

> Here's what doesn't make sense to me. The Web Site that you referred
> me to says:
> "Ultra DMA modes, such as UDMA2, 4, and 5, are also referred to as
> ATA/33, ATA/66, and ATA/100, respectively."
> 
> Now, the term "respectivly" means that mode 5 refers to ATA/100.
> When I look at the output of "dmesg" I see the line:
> 
> "SiS730    ATA 100 controller"
> 

Hi rocco.

hm. last time you wrote something like:

<snip>
Here is the output of hdparm -Tt /dev/hda:

Timing buffer-cache reads:   128 MB in  0.97 seconds =131.96 MB/sec
Timing buffered disk reads:  64 MB in  1.35 seconds = 47.41 MB/sec
</snip>

If I'm not mistaken, you wouldn't get the 47.41 MB/sec if your DMA controller wouldn't be driven in at least udma4. (see log below)


>  PIO modes:  pio0 pio1 pio2 pio3 pio4
>  DMA modes:  mdma0 mdma1 mdma2
>  UDMA modes: udma0 udma1 udma2
>  AdvancedPM=yes: disabled (255) WriteCache=enabled
>  Drive conforms to: (null):  1 2 3 4 5 6 7
> 
> There's not even a listing for udma5.
> Since I keep reading all these warnings
> about not trying settings that aren't supported,
> should I try udma5?

This is strange as well. I don't know for sure if the listing above is a hardware listing from the drive or a request "hey. IDE-Controller-driver, what's up with drive /dev/hda ?". I'd say its from the harddrives chip and just not implemented but still there.


<mainboard bla>
> up to 100 MB/s by providing a separate data path for two
> IDE channels and improving multi-tasking performance
</mainboard bla>

This is the usual and it says definitely that you could do 100 MB/sec, from the controller side.

I would say. Take the 47 MB/sec for granted and don't worry about the udma5 not showing up in your "hdparm -i". 
* Setting to -X69 won't give you the bite...(haeh?)
* It might still be that SiS 730 Controller is not fully supported under linux yet.
* In any case  I would try to find the black Peter for your dropouts in the PCI interrupts

cheers, tobias.

here's my (lenghty) log.

root at florides:~# hdparm -i /dev/hda

/dev/hda:

 Model=IC35L060AVV207-0, FwRev=V22OA63A, SerialNo=VNVB01G2R2T43D
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
 RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=52
 BuffType=DualPortCache, BuffSize=1821kB, MaxMultSect=16, MultSect=16
 CurCHS=4047/16/255, CurSects=16511760, LBA=yes, LBAsects=120103200
 IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
 PIO modes:  pio0 pio1 pio2 pio3 pio4
 DMA modes:  mdma0 mdma1 mdma2
 UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5
 AdvancedPM=yes: disabled (255) WriteCache=enabled
 Drive conforms to: ATA/ATAPI-6 T13 1410D revision 3a:  2 3 4 5 6

root at florides:~# hdparm -tT /dev/hda

/dev/hda:
 Timing buffer-cache reads:   128 MB in  1.64 seconds = 78.05 MB/sec
 Timing buffered disk reads:  64 MB in  1.56 seconds = 41.03 MB/sec
Hmm.. suspicious results: probably not enough free memory for a proper test.
root at florides:~# hdparm -X68 /dev/hda

/dev/hda:
 setting xfermode to 68 (UltraDMA mode4)
root at florides:~# hdparm -i /dev/hda

/dev/hda:

 Model=IC35L060AVV207-0, FwRev=V22OA63A, SerialNo=VNVB01G2R2T43D
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
 RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=52
 BuffType=DualPortCache, BuffSize=1821kB, MaxMultSect=16, MultSect=16
 CurCHS=4047/16/255, CurSects=16511760, LBA=yes, LBAsects=120103200
 IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
 PIO modes:  pio0 pio1 pio2 pio3 pio4
 DMA modes:  mdma0 mdma1 mdma2
 UDMA modes: udma0 udma1 udma2 udma3 *udma4 udma5
 AdvancedPM=yes: disabled (255) WriteCache=enabled
 Drive conforms to: ATA/ATAPI-6 T13 1410D revision 3a:  2 3 4 5 6

root at florides:~# hdparm -tT /dev/hda

/dev/hda:
 Timing buffer-cache reads:   128 MB in  1.66 seconds = 77.11 MB/sec
 Timing buffered disk reads:  64 MB in  1.52 seconds = 42.11 MB/sec
Hmm.. suspicious results: probably not enough free memory for a proper test.
root at florides:~# hdparm -X66 /dev/hda

/dev/hda:
 setting xfermode to 66 (UltraDMA mode2)
root at florides:~# hdparm -tT /dev/hda

/dev/hda:
 Timing buffer-cache reads:   128 MB in  1.66 seconds = 77.11 MB/sec
 Timing buffered disk reads:  64 MB in  2.20 seconds = 29.09 MB/sec
root at florides:~# hdparm -i /dev/hda

/dev/hda:

 Model=IC35L060AVV207-0, FwRev=V22OA63A, SerialNo=VNVB01G2R2T43D
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
 RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=52
 BuffType=DualPortCache, BuffSize=1821kB, MaxMultSect=16, MultSect=16
 CurCHS=4047/16/255, CurSects=16511760, LBA=yes, LBAsects=120103200
 IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
 PIO modes:  pio0 pio1 pio2 pio3 pio4
 DMA modes:  mdma0 mdma1 mdma2
 UDMA modes: udma0 udma1 *udma2 udma3 udma4 udma5
 AdvancedPM=yes: disabled (255) WriteCache=enabled
 Drive conforms to: ATA/ATAPI-6 T13 1410D revision 3a:  2 3 4 5 6