Re: [Xen-devel] [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-25 Thread Konrad Rzeszutek Wilk
On Wed, Oct 24, 2012 at 08:40:10AM +0100, Jan Beulich wrote: > >>> On 23.10.12 at 20:50, Konrad Rzeszutek Wilk wrote: > > On Tue, Oct 23, 2012 at 08:09:27PM +0200, Roger Pau Monné wrote: > >> On 23/10/12 19:20, Konrad Rzeszutek Wilk wrote: > >> diff --git a/drivers/block/xen-blkback/blkback.c

Re: [Xen-devel] [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-24 Thread Roger Pau Monné
On 23/10/12 20:50, Konrad Rzeszutek Wilk wrote: > On Tue, Oct 23, 2012 at 08:09:27PM +0200, Roger Pau Monné wrote: >> On 23/10/12 19:20, Konrad Rzeszutek Wilk wrote: >> diff --git a/drivers/block/xen-blkback/blkback.c >> b/drivers/block/xen-blkback/blkback.c >> index c6decb9..2b982b2 1

Re: [Xen-devel] [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-24 Thread Jan Beulich
>>> On 23.10.12 at 20:50, Konrad Rzeszutek Wilk wrote: > On Tue, Oct 23, 2012 at 08:09:27PM +0200, Roger Pau Monné wrote: >> On 23/10/12 19:20, Konrad Rzeszutek Wilk wrote: >> diff --git a/drivers/block/xen-blkback/blkback.c > b/drivers/block/xen-blkback/blkback.c >> index c6decb9..2b98

Re: [Xen-devel] [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-23 Thread Konrad Rzeszutek Wilk
On Tue, Oct 23, 2012 at 08:09:27PM +0200, Roger Pau Monné wrote: > On 23/10/12 19:20, Konrad Rzeszutek Wilk wrote: > diff --git a/drivers/block/xen-blkback/blkback.c > b/drivers/block/xen-blkback/blkback.c > index c6decb9..2b982b2 100644 > --- a/drivers/block/xen-blkback/blkbac

Re: [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-23 Thread Roger Pau Monné
On 23/10/12 19:20, Konrad Rzeszutek Wilk wrote: diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index c6decb9..2b982b2 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -78,6 +78,7 @@ s

Re: [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-23 Thread Konrad Rzeszutek Wilk
On Tue, Oct 23, 2012 at 06:07:36PM +0200, Roger Pau Monné wrote: > On 22/10/12 15:47, Konrad Rzeszutek Wilk wrote: > > On Thu, Oct 18, 2012 at 01:22:01PM +0200, Roger Pau Monne wrote: > >> This patch implements persistent grants for the xen-blk{front,back} > >> mechanism. The effect of this change

Re: [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-23 Thread Roger Pau Monné
On 22/10/12 15:47, Konrad Rzeszutek Wilk wrote: > On Thu, Oct 18, 2012 at 01:22:01PM +0200, Roger Pau Monne wrote: >> This patch implements persistent grants for the xen-blk{front,back} >> mechanism. The effect of this change is to reduce the number of unmap >> operations performed, since they caus

Re: [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-22 Thread Konrad Rzeszutek Wilk
On Thu, Oct 18, 2012 at 01:22:01PM +0200, Roger Pau Monne wrote: > This patch implements persistent grants for the xen-blk{front,back} > mechanism. The effect of this change is to reduce the number of unmap > operations performed, since they cause a (costly) TLB shootdown. This > allows the I/O per

Re: [Xen-devel] [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-19 Thread Roger Pau Monné
On 19/10/12 03:34, James Harper wrote: >> >> This patch implements persistent grants for the xen-blk{front,back} >> mechanism. The effect of this change is to reduce the number of unmap >> operations performed, since they cause a (costly) TLB shootdown. This allows >> the I/O performance to scale b

RE: [Xen-devel] [PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-18 Thread James Harper
> > This patch implements persistent grants for the xen-blk{front,back} > mechanism. The effect of this change is to reduce the number of unmap > operations performed, since they cause a (costly) TLB shootdown. This allows > the I/O performance to scale better when a large number of VMs are > perf

[PATCH RFC] Persistent grant maps for xen blk drivers

2012-10-18 Thread Roger Pau Monne
This patch implements persistent grants for the xen-blk{front,back} mechanism. The effect of this change is to reduce the number of unmap operations performed, since they cause a (costly) TLB shootdown. This allows the I/O performance to scale better when a large number of VMs are performing I/O.