|
Setting DMA with hdparm
The problem : Setting DMA with hdparm -d 1 /dev/hdc returns :
/dev/hdc:
setting using_dma to 1 (on)
HDIO_SET_DMA failed: Operation not permitted
using_dma = 0 (off)
I compiled the kernel myself and built my chipset support as a module because I wasn't sure of the precise chipset. My purchase order says MSI 661FM-L, so I flagged most of them for module building and the kernel detected the SIS 5513.
dmesg returns the following:
SIS5513: IDE controller at PCI slot 0000:00:02.5
ACPI: PCI interrupt 0000:00:02.5[A] -> GSI 16 (level, low) -> IRQ 16
SIS5513: chipset revision 0
SIS5513: not 100% native mode: will probe irqs later
SIS5513: SiS 962/963 MuTIOL IDE UDMA133 controller
SIS5513: port 0x01f0 already claimed by ide0
SIS5513: port 0x0170 already claimed by ide1
SIS5513: neither IDE port enabled (BIOS)
The kernel is quite sibylline on the subject:
- SIS5513: SiS 962/963 MuTIOL IDE UDMA133 controller -> Is this the same as DMA ?
- SIS5513: not 100% native mode: will probe irqs later -> Does this affect anything at all ? If so, have they been properly probed as claimed ?
- SIS5513: neither IDE port enabled (BIOS) -> Are my BIOS setting at fault ?
There is a special -X flag in hdparm but the man page states that it is "seldom necessary since most/all modern IDE drives default to their fastest PIO transfer mode at power-on" and that "Fiddling with this can be both needless and risky".
I still tried it like so: hdparm -d1 -X mdma2 /dev/hdc ands I got this:
/dev/hdc:
setting using_dma to 1 (on)
HDIO_SET_DMA failed: Operation not permitted
setting xfermode to 34 (multiword DMA mode2)
using_dma = 0 (off)
Ok, so no crash so far. But still on a slump.
Any help appreciated.
---
narc.
|
