> I am not going to get into this too much,
> but I would guess that the ide-tape *and* ide-cd *and* ide-floppy
> stuff should already be darned-near SMP-safe, since the entry
> points are all (?) through the SMP firewall code in ide.c.
>
> The intent of the fine-grained SMP support I added in ide.c
> was that it would protect all of the sub-drivers, provided they
> don't go out of their way to be foolish (except for ide-scsi).
>
> Interrupt masking shouldn't really be needed or matter in the
> sub-drivers.. most of it can probably just be "#if 0"'d .
>
> Are there actually reported problems (I wouldn't know)?
> Do they go away when the save_flags/cli/restore_flags is commented-out
> in ide-tape.c ?
Mark, I will take a poke at that thursday night, but I just got a pile of
integrations to add Alladin M5229 initial UDMA support along with PIIX
chipset tuning. This may help with the SMP errors, if the chipset is
tuned correctly for the hardware speed. I just don't know.
Something that I have notice is putting the brakes of the tape-streaming.
That is to say, if I do something silly like add compression flags to
'tar', this slows down the tape accessing and has reduced faults.
>From this simple test, I would believe that a timing issue has popped up
as the finer tuning of the Intel SMP progresses.
Oh, come on back and join the fun Mark........I now truly understand what
you did for six (6) years and have a new appreciation...........
Cheers,
Andre Hedrick
The IDE-FNG for Linux
The APC UPS Specialist for Linux
http://www.dyer.vanderbilt.edu/server/udma/
http://www.dyer.vanderbilt.edu/server/apcupsd/apcupsd-3.4.9.bin.linux.tar.gz
-
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/