This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


Re: [XenPPC] [RFC] 64mb Chunk Allocator

* Orran Krieger <okrieg@xxxxxxxxxx> [2006-06-23 11:35]:
> So... in K42, chris yeoh recently explored a chunk based allocator, and he 
> now 
> has a prototype working in linux.  I think this would make much more sense 
> for 
> Xen than for Linux/k42.  I think the notion would be, that all allocates, 
> even 
> inside hypervisor for its own memory, are on behalf of some domain.  Allocate 
> some chunks to the domain, and then sub-allocate for individual uses.  When 
> the 
> domain gets freed, all the memory of the chunks naturally gets freed.   If 
> memory gets moved from one client to anther, chunks can be partial, when 
> freed, 
> but thats okay.  
> I guess my impression is that we wanted to do something simple for now.  
> However, would it make sense to consider something like this?   Ryan, would 
> it 
> be crazy to try to get something like this into Xen?
> I am talking now about the page allocator, but you might also want a heap 
> allocator on top of this. 

I think the biggest hurdle would be figuring out how to handle DMA
addresses for 32-bit x86 without IOMMU or swiotlb.  Otherwise, it seems
sane to have all memory allocations come from the chunks of memory
assigned to the domain.  This makes sense for NUMA as well, giving us
locality for domain structures.  

I was thinking for DMA we could have a special DMA domain which could
own chunks of memory that were DMAable and force all other domains to
use up non-dma chunks first.  When a domain needs DMAable pages, we
could redirect the request to the DMA domain's heap.

Ryan Harper
Software Engineer; Linux Technology Center
IBM Corp., Austin, Tx
(512) 838-9253   T/L: 678-9253

Xen-ppc-devel mailing list