Re: [kvm-devel] [RFC PATCH 1/8] IOQ: Adding basic definitions for IO-Queue logic

2007-08-14 Thread Gregory Haskins
On Tue, 2007-08-14 at 07:44 -0400, Gregory Haskins wrote: > On Tue, 2007-08-14 at 01:01 -0700, Dor Laor wrote: > > Instead of the above code I would call to iter_seek and do everything inside > > then return a proper error code if needed. > > Im not sure I fully understand your point. But if I d

Re: [kvm-devel] [RFC PATCH 1/8] IOQ: Adding basic definitions for IO-Queue logic

2007-08-14 Thread Gregory Haskins
On Tue, 2007-08-14 at 01:01 -0700, Dor Laor wrote: > Why not use the standard naming for guest/host or front/backend? I was trying to stress that this isn't virtualization specific. For instance, you could use an IOQ on something like an AMP or RDMA based system too. However, that being said I

Re: [kvm-devel] [RFC PATCH 1/8] IOQ: Adding basic definitions for IO-Queue logic

2007-08-14 Thread Dor Laor
>IOQ is a generic shared-memory-queue mechanism that happens to be >friendly >to virtualization boundaries. Note that it is not virtualization >specific >due to its flexible transport layer. > >Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]> >--- > > include/linux/ioq.h | 178 +

[kvm-devel] [RFC PATCH 1/8] IOQ: Adding basic definitions for IO-Queue logic

2007-08-13 Thread Gregory Haskins
IOQ is a generic shared-memory-queue mechanism that happens to be friendly to virtualization boundaries. Note that it is not virtualization specific due to its flexible transport layer. Signed-off-by: Gregory Haskins <[EMAIL PROTECTED]> --- include/linux/ioq.h | 178 +++