On Fri, Aug 31, 2012 at 07:23:05PM -0700, Tejun Heo wrote:
> On Tue, Aug 28, 2012 at 03:17:15PM -0700, Kent Overstreet wrote:
> > I still think they should be symmetrical, but if that's true bi_ioc and
> > bi_css need to be moved, and also bio_disassociate_task() should be
> > getting called from b
Hello,
On Tue, Aug 28, 2012 at 03:17:15PM -0700, Kent Overstreet wrote:
> > Better to explain why some bio fields are re-ordered and why that
> > shouldn't make things worse cacheline-wise?
>
> Well it may (struct bio is what, 3 or 4 cachelines now?) but even on
> ridiculous million iop devices s
On Tue, Aug 28, 2012 at 03:17:15PM -0700, Kent Overstreet wrote:
> On Tue, Aug 28, 2012 at 01:31:48PM -0700, Tejun Heo wrote:
> > > + unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
> > > +
> > > + if (bio_integrity(bio))
> > > + bio_integrity_free(bio, bio->bi_pool);
> > >
On Tue, Aug 28, 2012 at 01:31:48PM -0700, Tejun Heo wrote:
> Hello, Kent.
>
> On Tue, Aug 28, 2012 at 10:37:30AM -0700, Kent Overstreet wrote:
> > Reusing bios is something that's been highly frowned upon in the past,
> > but driver code keeps doing it anyways. If it's going to happen anyways,
> >
Hello, Kent.
On Tue, Aug 28, 2012 at 10:37:30AM -0700, Kent Overstreet wrote:
> Reusing bios is something that's been highly frowned upon in the past,
> but driver code keeps doing it anyways. If it's going to happen anyways,
> we should provide a generic method.
>
> This'll help with getting rid
5 matches
Mail list logo
