Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level?compression

2013-11-17 Thread Avi Kivity
On 11/17/2013 05:37 PM, Michael S. Tsirkin wrote: On Thu, Nov 14, 2013 at 05:42:26PM +0200, Avi Kivity wrote: On 11/14/2013 05:37 PM, Michael S. Tsirkin wrote: On Thu, Nov 14, 2013 at 04:56:43PM +0200, Avi Kivity wrote: On 11/14/2013 04:40 PM, Michael S. Tsirkin wrote: On Thu, Nov 14, 2013 at

Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level?compression

2013-11-17 Thread Michael S. Tsirkin
On Thu, Nov 14, 2013 at 05:42:26PM +0200, Avi Kivity wrote: > On 11/14/2013 05:37 PM, Michael S. Tsirkin wrote: > >On Thu, Nov 14, 2013 at 04:56:43PM +0200, Avi Kivity wrote: > >>On 11/14/2013 04:40 PM, Michael S. Tsirkin wrote: > >>>On Thu, Nov 14, 2013 at 08:54:11AM +, Avi Kivity wrote: > >>>

Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level?compression

2013-11-14 Thread Avi Kivity
On 11/14/2013 05:37 PM, Michael S. Tsirkin wrote: On Thu, Nov 14, 2013 at 04:56:43PM +0200, Avi Kivity wrote: On 11/14/2013 04:40 PM, Michael S. Tsirkin wrote: On Thu, Nov 14, 2013 at 08:54:11AM +, Avi Kivity wrote: Michael S. Tsirkin redhat.com> writes: At the moment, memory radix tree

Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level?compression

2013-11-14 Thread Michael S. Tsirkin
On Thu, Nov 14, 2013 at 04:56:43PM +0200, Avi Kivity wrote: > On 11/14/2013 04:40 PM, Michael S. Tsirkin wrote: > >On Thu, Nov 14, 2013 at 08:54:11AM +, Avi Kivity wrote: > >>Michael S. Tsirkin redhat.com> writes: > >> > >>>At the moment, memory radix tree is already variable width, but it can

Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level?compression

2013-11-14 Thread Avi Kivity
On 11/14/2013 04:40 PM, Michael S. Tsirkin wrote: On Thu, Nov 14, 2013 at 08:54:11AM +, Avi Kivity wrote: Michael S. Tsirkin redhat.com> writes: At the moment, memory radix tree is already variable width, but it can only skip the low bits of address. This is efficient if we have huge mem

Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level?compression

2013-11-14 Thread Michael S. Tsirkin
On Thu, Nov 14, 2013 at 08:54:11AM +, Avi Kivity wrote: > Michael S. Tsirkin redhat.com> writes: > > > > > At the moment, memory radix tree is already variable width, but it can > > only skip the low bits of address. > > > > This is efficient if we have huge memory regions but inefficient i

Re: [Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level compression

2013-11-14 Thread Avi Kivity
Michael S. Tsirkin redhat.com> writes: > > At the moment, memory radix tree is already variable width, but it can > only skip the low bits of address. > > This is efficient if we have huge memory regions but inefficient if we > are only using a tiny portion of the address space. > > After we h

[Qemu-devel] [PATCH v2 5/7] exec: memory radix tree page level compression

2013-11-13 Thread Michael S. Tsirkin
At the moment, memory radix tree is already variable width, but it can only skip the low bits of address. This is efficient if we have huge memory regions but inefficient if we are only using a tiny portion of the address space. After we have built up the map, detect configurations where a single