> Stuff is flushed when the disk change is detected. Is the drive reported
> as removable does the kernel log show disk change events ?
The castlewood support line guys swore that the disk doesn't cache.
More reflection, and the fact that partition tables are (partially)
preserved across ejects, leads me to conjecture that the ide driver is
caching *and* not detecting ejects.
The kernel log does *not* show disk change events:
(editted from the dmesg command)
PIIX4: IDE controller on PCI bus 00 dev 21
PIIX4: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0xd800-0xd807, BIOS settings: hda:pio, hdb:pio
ide1: BM-DMA at 0xd808-0xd80f, BIOS settings: hdc:pio, hdd:pio
hdc: CASTLEWOOD ORB2-E, ATA DISK drive
ide1 at 0x170-0x177,0x376 on irq 15
hdc: CASTLEWOOD ORB2-E, 2103MB w/0kB Cache, CHS=4273/16/63, DMA
As of right now:
# cat /proc/ide/ide1/hdc/settings
name value min max mode
---- ----- --- --- ----
bios_cyl 534 0 65535 rw
bios_head 128 0 255 rw
bios_sect 63 0 63 rw
breada_readahead 4 0 127 rw
bswap 0 0 1 r
file_readahead 124 0 2097151 rw
io_32bit 0 0 3 rw
keepsettings 0 0 1 rw
max_kb_per_request 64 1 127 rw
multcount 0 0 8 rw
nice1 1 0 1 rw
nowerr 0 0 1 rw
pio_mode write-only 0 255 w
slow 0 0 1 rw
unmaskirq 0 0 1 rw
using_dma 0 0 1 rw
I've got a request in the pipeline with Castlewood for more
specifications of what the linux drivers need to do. They'd not heard
of this problem before.
-- Perry Wagle (wagle@cse.ogi.edu)
PS. Is there a way to manually force a flush?
-
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/