>> ALI15X3: MultiWord DMA enabled
>> hda: Maxtor 90680D4, 2014MB w/256kB Cache, CHS=826/255/63, (U)DMA
AK> ^^^^
AK> This means that kernel decides your chipset is not UDMA capable, while the
AK> drive is...
AK> Note, that driver author (from ALI) suggested that for M5229 rev. <= 0x20
AK> UDMA is "not stable", so it should be disabled by the driver...
OK, but I have rev c1 of the M5229 and still can't understand the
results.
As I already reported:
>> 00:0f.0 IDE interface: Acer Laboratories Inc. M5229 (rev c1)
>> ALI15X3: IDE controller on PCI bus 00 dev 78
>> ALI15X3: not 100% native mode: will probe irqs later
>> ide0: BM-DMA at 0xb400-0xb407, BIOS settings: hda:DMA, hdb:DMA
>> ide1: BM-DMA at 0xb408-0xb40f, BIOS settings: hdc:DMA, hdd:pio
>> hda: ST34311A, ATA DISK drive
>> hdb: ST34311A, ATA DISK drive
>> hdc: IBM-DJNA-351520, ATA DISK drive
>> hdd: NEC CD-ROM DRIVE:282, ATAPI CDROM drive
>> ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
>> ide1 at 0x170-0x177,0x376 on irq 15
>> ALI15X3: Ultra DMA enabled
>> hda: ST34311A, 4126MB w/256kB Cache, CHS=8944/15/63, UDMA(33)
>> ALI15X3: Ultra DMA enabled
>> hdb: ST34311A, 4126MB w/256kB Cache, CHS=526/255/63, UDMA(33)
Identical disks, both have DMA enabled in the BIOS and have different
benchmark results. Strange.
>> ALI15X3: Ultra DMA enabled
>> hdc: IBM-DJNA-351520, 14664MB w/430kB Cache, CHS=29795/16/63, (U)DMA
This is confusin wrt your explanation. UDMA enabled so driver believes
that chipset is UDMA capable. But the (U)DMA indicates that the chipset
is not UDMA capable. How can the second interface be worse than the
first? Or is it just a reporting bug (since the driver runs _fast_ and
it certainly looks like it uses udma).
>> ALI15X3: MultiWord DMA enabled
>> hdd: ATAPI 40X CD-ROM drive, 128kB Cache, (U)DMA
OK, this was pio in bios and gets assigned multiword dma.
But why is there the (U)DMA string again? If the drive supports UDMA
then the bios should have initialized it to udma, right?
-- Meelis Roos (mroos@tartu.cyber.ee)- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sat Jan 15 2000 - 21:00:20 EST