libata - DMA problems ICH7 rev 02

libata - DMA problems ICH7 rev 02

[Jan Niklas Hasse]

[-- Attachment #1: Type: text/plain, Size: 478 bytes --]

Hi everyone,

I don't have DMA on my notebook, I think it's this problem:
http://ata.wiki.kernel.org/index.php/Libata_FAQ#Intel_combined_mode
I tried all steps mention there (the first one wasn't possible because
my BIOS didn't support it), but none of them worked (every time my
harddisk is loading my CPU is spammed with IOWait).

Output of uname -a and lspci is attached.

I hope you can help me, very hard to work without DMA. Sorry if there
are some English mistakes.

Jan

[-- Attachment #2: lspci.txt --]
[-- Type: text/plain, Size: 2390 bytes --]

jhasse@ubuntu:~$ uname -a
Linux ubuntu 2.6.24-16-generic #1 SMP Thu Apr 10 12:47:45 UTC 2008 x86_64 GNU/Linux
jhasse@ubuntu:~$ lspci
00:00.0 Host bridge: Intel Corporation Mobile 945GM/PM/GMS, 943/940GML and 945GT Express Memory Controller Hub (rev 03)
00:02.0 VGA compatible controller: Intel Corporation Mobile 945GM/GMS, 943/940GML Express Integrated Graphics Controller (rev 03)
00:02.1 Display controller: Intel Corporation Mobile 945GM/GMS/GME, 943/940GML Express Integrated Graphics Controller (rev 03)
00:1b.0 Audio device: Intel Corporation 82801G (ICH7 Family) High Definition Audio Controller (rev 02)
00:1c.0 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 1 (rev 02)
00:1c.1 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 2 (rev 02)
00:1c.2 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 3 (rev 02)
00:1c.3 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 4 (rev 02)
00:1d.0 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #1 (rev 02)
00:1d.1 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #2 (rev 02)
00:1d.2 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #3 (rev 02)
00:1d.3 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI Controller #4 (rev 02)
00:1d.7 USB Controller: Intel Corporation 82801G (ICH7 Family) USB2 EHCI Controller (rev 02)
00:1e.0 PCI bridge: Intel Corporation 82801 Mobile PCI Bridge (rev e2)
00:1f.0 ISA bridge: Intel Corporation 82801GBM (ICH7-M) LPC Interface Bridge (rev 02)
00:1f.1 IDE interface: Intel Corporation 82801G (ICH7 Family) IDE Controller (rev 02)
00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 02)
03:00.0 Network controller: Intel Corporation PRO/Wireless 3945ABG Network Connection (rev 02)
08:05.0 Ethernet controller: Broadcom Corporation BCM4401-B0 100Base-TX (rev 02)
08:09.0 CardBus bridge: Ricoh Co Ltd RL5c476 II (rev b4)
08:09.1 FireWire (IEEE 1394): Ricoh Co Ltd R5C552 IEEE 1394 Controller (rev 09)
08:09.2 SD Host controller: Ricoh Co Ltd R5C822 SD/SDIO/MMC/MS/MSPro Host Adapter (rev 18)
08:09.3 System peripheral: Ricoh Co Ltd R5C843 MMC Host Controller
08:09.4 System peripheral: Ricoh Co Ltd R5C592 Memory Stick Bus Host Adapter (rev 09)
08:09.5 System peripheral: Ricoh Co Ltd xD-Picture Card Controller (rev 04)

Re: libata - DMA problems ICH7 rev 02

[Alan Cox]

> my BIOS didn't support it), but none of them worked (every time my
> harddisk is loading my CPU is spammed with IOWait).

Then you must have a different problem ?

> 
> Output of uname -a and lspci is attached.
> 
> I hope you can help me, very hard to work without DMA. 

Please send the output of "dmesg" after boot


Alan

Re: libata - DMA problems ICH7 rev 02

[Jan Niklas Hasse]

On Fri, May 2, 2008 at 2:58 PM, Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:
> > my BIOS didn't support it), but none of them worked (every time my
>  > harddisk is loading my CPU is spammed with IOWait).
>
>  Then you must have a different problem ?

Maybe, but it seems as DMA isn't used. Everytime my hard disk is
reading/writing my system gets very slow. Here's the line when i run
top:

Cpu(s): 12.6%us,  5.4%sy,  0.0%ni,  6.5%id, 74.2%wa,  0.5%hi,  0.8%si,  0.0%st

The thing I mean is "wa".

>  > Output of uname -a and lspci is attached.
>  >
>  > I hope you can help me, very hard to work without DMA.
>
>  Please send the output of "dmesg" after boot

Okay, I pasted it here: http://rafb.net/p/KiWhqE72.html

Re: libata - DMA problems ICH7 rev 02

[Robert Hancock]

Jan Niklas Hasse wrote:
> On Fri, May 2, 2008 at 2:58 PM, Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:
>>> my BIOS didn't support it), but none of them worked (every time my
>>  > harddisk is loading my CPU is spammed with IOWait).
>>
>>  Then you must have a different problem ?
> 
> Maybe, but it seems as DMA isn't used. Everytime my hard disk is
> reading/writing my system gets very slow. Here's the line when i run
> top:
> 
> Cpu(s): 12.6%us,  5.4%sy,  0.0%ni,  6.5%id, 74.2%wa,  0.5%hi,  0.8%si,  0.0%st
> 
> The thing I mean is "wa".

This is expected. IOWait just means the system is blocked waiting for IO 
  and has nothing else to do. It does not mean that DMA is not working.

> 
>>  > Output of uname -a and lspci is attached.
>>  >
>>  > I hope you can help me, very hard to work without DMA.
>>
>>  Please send the output of "dmesg" after boot
> 
> Okay, I pasted it here: http://rafb.net/p/KiWhqE72.html

Looks like you are using DMA:

ata1.00: configured for UDMA/100
ata1.01: configured for UDMA/33

Re: libata - DMA problems ICH7 rev 02

[Jan Niklas Hasse]

On Sat, May 3, 2008 at 4:38 AM, Robert Hancock <hancockr@shaw.ca> wrote:
>  This is expected. IOWait just means the system is blocked waiting for IO
> and has nothing else to do. It does not mean that DMA is not working.
>
>  [...]
>
>  Looks like you are using DMA:
>
>  ata1.00: configured for UDMA/100
>  ata1.01: configured for UDMA/33
>

Hm.. strange. But the problem is that my system slows down
nevertheless (sometimes the mouse cursor stops moving for a short time
or all my programs don't react). How can i find out what is causing
the problem?

Here I was creating a DVD with dvdauthor which was copying some big
video files. It was nearly impossible to use a web browser, although
CPU load seems only to be 12.7%.

top - 20:33:08 up  4:58,  2 users,  load average: 2.94, 2.81, 2.49
Tasks: 134 total,   2 running, 132 sleeping,   0 stopped,   0 zombie
Cpu(s):  5.0%us,  7.7%sy,  0.0%ni, 16.2%id, 70.1%wa,  0.3%hi,  0.8%si,  0.0%st
Mem:   1019568k total,   996316k used,    23252k free,     1148k buffers
Swap:  2916344k total,    83892k used,  2832452k free,   325284k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
 2609 root      15  -5     0    0    0 S    6  0.0   6:41.67 kcryptd
 6344 root      20   0  543m 129m  10m S    3 13.0   6:33.63 Xorg
27062 jhasse    20   0 23164 6424 1176 D    3  0.6   0:11.98 dvdauthor
 6891 jhasse    20   0  208m  18m 8956 S    2  1.9   3:13.41 transmission
27173 jhasse    20   0  263m  24m  12m S    2  2.4   0:00.66 gnome-terminal
  195 root      20   0     0    0    0 S    1  0.0   0:00.14 pdflush

Another example: When I'm burning a disc and at the end, when my drive
finishes the disc (and makes those noises) the computer freezes untill
the CD is finished and ejected (about 3 seconds).

I hope it's the right place to ask here at the mailing list and thanks
for your help so far.

Re: libata - DMA problems ICH7 rev 02

[Robert Hancock]

Jan Niklas Hasse wrote:
> On Sat, May 3, 2008 at 4:38 AM, Robert Hancock <hancockr@shaw.ca> wrote:
>>  This is expected. IOWait just means the system is blocked waiting for IO
>> and has nothing else to do. It does not mean that DMA is not working.
>>
>>  [...]
>>
>>  Looks like you are using DMA:
>>
>>  ata1.00: configured for UDMA/100
>>  ata1.01: configured for UDMA/33
>>
> 
> Hm.. strange. But the problem is that my system slows down
> nevertheless (sometimes the mouse cursor stops moving for a short time
> or all my programs don't react). How can i find out what is causing
> the problem?
> 
> Here I was creating a DVD with dvdauthor which was copying some big
> video files. It was nearly impossible to use a web browser, although
> CPU load seems only to be 12.7%.
> 
> top - 20:33:08 up  4:58,  2 users,  load average: 2.94, 2.81, 2.49
> Tasks: 134 total,   2 running, 132 sleeping,   0 stopped,   0 zombie
> Cpu(s):  5.0%us,  7.7%sy,  0.0%ni, 16.2%id, 70.1%wa,  0.3%hi,  0.8%si,  0.0%st
> Mem:   1019568k total,   996316k used,    23252k free,     1148k buffers
> Swap:  2916344k total,    83892k used,  2832452k free,   325284k cached
> 
>   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
>  2609 root      15  -5     0    0    0 S    6  0.0   6:41.67 kcryptd
>  6344 root      20   0  543m 129m  10m S    3 13.0   6:33.63 Xorg
> 27062 jhasse    20   0 23164 6424 1176 D    3  0.6   0:11.98 dvdauthor
>  6891 jhasse    20   0  208m  18m 8956 S    2  1.9   3:13.41 transmission
> 27173 jhasse    20   0  263m  24m  12m S    2  2.4   0:00.66 gnome-terminal
>   195 root      20   0     0    0    0 S    1  0.0   0:00.14 pdflush
> 
> Another example: When I'm burning a disc and at the end, when my drive
> finishes the disc (and makes those noises) the computer freezes untill
> the CD is finished and ejected (about 3 seconds).
> 
> I hope it's the right place to ask here at the mailing list and thanks
> for your help so far.

It looks like you have the hard drive and the burner on the same IDE 
channel? Such problems are unavoidable in this setup since commands to 
one device on the channel can't execute while the other device is busy 
(especially for long commands like finalizing the disc). It would be 
better to move the drives onto separate channels.

Re: libata - DMA problems ICH7 rev 02

[Jan Niklas Hasse]

On Wed, May 28, 2008 at 3:34 PM, Jan Niklas Hasse <jhasse@gmail.com> wrote:
>>
>> It looks like you have the hard drive and the burner on the same IDE channel? Such problems are unavoidable in this setup since commands to one device on the channel can't execute while the other device is busy (especially for long commands like finalizing the disc). It would be better to move the drives onto separate channels.
>

As I have a notebook, I think I can't do that, can I?

Re: libata - DMA problems ICH7 rev 02

[Alan Jenkins]

Jan Niklas Hasse wrote:
> On Wed, May 28, 2008 at 3:34 PM, Jan Niklas Hasse <jhasse@gmail.com> wrote:
> >>
> >> It looks like you have the hard drive and the burner on the same IDE channel? Such problems are unavoidable in this setup since commands to one device on the channel can't execute while the other device is busy (especially for long commands like finalizing the disc). It would be better to move the drives onto separate channels.
> >
>
> As I have a notebook, I think I can't do that, can I?

This is the exact situation cdrecord's -immed option was designed
for.  "wodim"/cdrkit should have inherited it.  It sets a flag in the
commands to avoid blocking, though the documentation I read said it
was slightly experimental.

Re: libata - DMA problems ICH7 rev 02

[Alan Jenkins]

Jan Niklas Hasse wrote:
> On Wed, May 28, 2008 at 3:34 PM, Jan Niklas Hasse <jhasse@gmail.com> wrote:
> >>
> >> It looks like you have the hard drive and the burner on the same IDE channel? Such problems are unavoidable in this setup since commands to one device on the channel can't execute while the other device is busy (especially for long commands like finalizing the disc). It would be better to move the drives onto separate channels.
> >
>
> As I have a notebook, I think I can't do that, can I?

This is the exact situation cdrecord's -immed option was designed
for.  "wodim"/cdrkit should have inherited it.  It sets a flag in the
commands to avoid blocking, though the documentation I read said it
was slightly experimental.

Re: libata - DMA problems ICH7 rev 02

[Robert Hancock]

Jan Niklas Hasse wrote:
> On Wed, May 28, 2008 at 3:34 PM, Jan Niklas Hasse <jhasse@gmail.com> wrote:
>>> It looks like you have the hard drive and the burner on the same IDE channel? Such problems are unavoidable in this setup since commands to one device on the channel can't execute while the other device is busy (especially for long commands like finalizing the disc). It would be better to move the drives onto separate channels.
> 
> As I have a notebook, I think I can't do that, can I?

Likely not, no. That is pretty poor design by the manufacturer, to set 
things up that way..