| 1 |
"Luigi Cristalli" <luigi.cristalli@×××××.com> posted |
| 2 |
bacd36480608041740r1b41d2d7neea4a898a6fa567b@××××××××××.com, excerpted |
| 3 |
below, on Sat, 05 Aug 2006 02:40:08 +0200: |
| 4 |
|
| 5 |
> Almost one year ago I helped a friend of mine to get a working gentoo |
| 6 |
> linux box on an Acer Ferrari (AMD 64). . I was surprised because it was so |
| 7 |
> slow when I tried to emerge something! :-D Finally I found the DMA was |
| 8 |
> off...can U believe? :-D check it making: |
| 9 |
> |
| 10 |
> #hdparm /dev/hda | grep using_dma |
| 11 |
> |
| 12 |
> if it's set to 0 (off) we know our enemy! :-D |
| 13 |
|
| 14 |
That was going to be my suggestion! =8^) |
| 15 |
|
| 16 |
So yeah, you have two votes for checking DMA. If it's off, particularly |
| 17 |
if you are swapping, that /could/ be killing responsiveness, including |
| 18 |
mouse. |
| 19 |
|
| 20 |
Note that if you are using the wrong IDE/SATA/SCSI chipset drivers, it's |
| 21 |
likely you'll have no luck trying to turn DMA on, until you get the right |
| 22 |
drivers. In particular, I noted one guy earlier this week with SATA, |
| 23 |
generic IDE, and some Via chipset IDE, all turned on at once, according to |
| 24 |
his dmesg. The generic was loading first so the Via, while it detected |
| 25 |
the chip, couldn't load as the generic was already loaded. There's a good |
| 26 |
chance he was running without DMA as a result. The SATA drivers likely |
| 27 |
weren't interfering with DMA, but dmesg didn't say any SATA drives were |
| 28 |
recognized, so chances are he had the chip but no drives hung off it, so |
| 29 |
that too might as well have been disabled. |
| 30 |
|
| 31 |
Hope you get it working, in any case! |
| 32 |
|
| 33 |
-- |
| 34 |
Duncan - List replies preferred. No HTML msgs. |
| 35 |
"Every nonfree program has a lord, a master -- |
| 36 |
and if you use the program, he is your master." Richard Stallman |
| 37 |
|
| 38 |
-- |
| 39 |
gentoo-amd64@g.o mailing list |
Archives