Messages in this thread | | | From | Nick Piggin <> | Subject | Re: [PATCH] [RESEND] x86_64: add memory hotremove config option | Date | Mon, 8 Sep 2008 15:52:49 +1000 |
| |
On Saturday 06 September 2008 18:53, Andi Kleen wrote: > On Sat, Sep 06, 2008 at 04:06:38PM +0900, Yasunori Goto wrote: > > > not. > > > > > > This means I don't see a real use case for this feature. > > > > I don't think its driver is almighty. > > IIRC, balloon driver can be cause of fragmentation for 24-7 system. > > Sure the balloon driver can be likely improved too, it's just > that I don't think a balloon driver should call into the function > the original patch in the series hooked up. > > > In addition, I have heard that memory hotplug would be useful for > > reducing of power consumption of DIMM. > > It's unclear that memory hotplug is the right model for DIMM power > management. The problem is that DIMMs are interleaved, so you again have to > completely free a quite large area. It's not much easier than node hotplug. > > > I have to admit that memory hotplug has many issues, but I would like to > > Let's call it "node" or "hardware" memory hot unplug, not that > anyone confuses it with the easier VM based hot unplug or the really > easy hotadd. > > > solve them step by step. > > The question is if they are even solvable in a useful way. > I'm not sure it's that useful to start and then find out > that it doesn't work anyways.
You use non-linear mappings for the kernel, so that kernel data is not tied to a specific physical address. AFAIK, that is the only way to really do it completely (like the fragmentation problem).
Of course, I don't think that would be a good idea to do that in the forseeable future.
| |