Re: Severe I/O performance regression 2.6.6 to 2.6.7 or 2.6.8-rc3

[Berkley Shands]

	I took the 2.6.6-bk7 image, and replaced mm/readahead.c and mm/vmscan.c
from the 2.6.6-bk6 image (just those two files), and the read ahead error
has vanished. However, the kernel panic'ed when reading a 16gb file.
It may be related to an ongoing issue with pci-x and scsi error recovery
on the x86_64, so until I get into the office, I will not be able
to see what's on the console. 
	So clearly the code in readahead.c and vmscan.c in -bk7 is
the source of one regression. I'll keep looking at the second bug
in the morning.
	Thanks to all for the pointers on where to look.

berkley
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/