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

2013-11-11 Thread Eric Blake
On 11/11/2013 09:41 AM, Michael S. Tsirkin wrote: > 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. > > Afte

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

2013-11-11 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, it's a simple matter to detect confi