On Sun, 21 Jan 2007 22:54:26 -0500
"Perry E. Metzger" <perry@piermont.com> wrote:

> 
> Tom Spindler <dogcow@babymeat.com> writes:
> >> As of Jan, something seems to have broken BUFQ_READPRIO -- unclear
> >> who did it or why, but it is very clear to me that it got broken.
> >> The old symptoms of lots of disk i/o locking out userland
> >> processes trying to read something have returned.
> >
> > FWIW, I do _not_ have BUFQ_READPRIO in either of my kernels that
> > this manifests itself.
> 
> My point was that I think that the behavior that BUFQ_READPRIO
> formerly prevented on my machines is now happening again for me.
> 
Which is why I asked if the problem just started for him.  If it's new,
it has nothing to do with BUFQ_READPRIO, since if it were BUFQ_READPRIO
he would have been experiencing it all along.


		--Steve Bellovin, http://www.cs.columbia.edu/~smb