I tested linux-2.4.0-test3-pre1 today and still had massive problems under
heavy disk I/O. A single bonnie process works for a while, then locking up
leaving the IDE disk LED on and doing nothing. The system is still up, but
anything trying to access the drive just halts. But the MP3 I played over
network in the background still continued. So it seems to be disk realted, not
the whole I/O subsystem locking up.
Hardware is a uniprocessor Intel Pentium-II board with 440LX chipset and
a Ultra33 PIIX4 IDE onboard, serving two Harddisks, a ZIP drive and a CD-ROM.
On boot, everything looks normal:
Uniform Multi-Platform E-IDE driver Revision: 6.31
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
PIIX4: IDE controller on PCI bus 00 dev 39
PIIX4: chipset revision 1
PIIX4: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0x1000-0x1007, BIOS settings: hda:DMA, hdb:pio
ide1: BM-DMA at 0x1008-0x100f, BIOS settings: hdc:DMA, hdd:DMA
hda: QUANTUM BIGFOOT_CY4320A, ATA DISK drive
hdb: IOMEGA ZIP 100 ATAPI, ATAPI FLOPPY drive
hdc: QUANTUM FIREBALL_TM2110A, ATA DISK drive
hdd: HITACHI CDR-8335, ATAPI CDROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide1 at 0x170-0x177,0x376 on irq 15
hda: 8467200 sectors (4335 MB) w/67KiB Cache, CHS=527/255/63, DMA
hdc: 4124736 sectors (2112 MB) w/76KiB Cache, CHS=4092/16/63, DMA
Partition check:
hda: hda1 hda2 < hda5 hda6 >
hdc: [PTBL] [1023/64/63] hdc1 hdc2
The HD's are a bit older, thus not running in UDMA mode but "normal" DMA.
Disabling DMA with hdparm seems to fix the problem. Is there anything broken
with DMA? This didn't happen before with the earlier 2.3 series...
The overall system performance during the HD access is also quite bad..
sometimes I can't even move the mouse cursor under X.
I hope to be able to help in this.
Greetings,
Andreas
-- ->>>----------------------- Andreas Franck --------<<<- ---<<<---- Andreas.Franck@post.rwth-aachen.de --->>>--- ->>>---- Keep smiling! ----------------------------<<<-- 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/