Re: [PATCH] Do not use cpu_to_node() to find an offlined cpu's node.

[Peter Zijlstra <peterz@infradead.org>]

On Tue, 2012-10-09 at 16:27 -0700, David Rientjes wrote:
> On Tue, 9 Oct 2012, Peter Zijlstra wrote:
> 
> > Well the code they were patching is in the wakeup path. As I think Tang
> > said, we leave !runnable tasks on whatever cpu they ran on last, even if
> > that cpu is offlined, we try and fix up state when we get a wakeup.
> > 
> > On wakeup, it tries to find a cpu to run on and will try a cpu of the
> > same node first.
> > 
> > Now if that node's entirely gone away, it appears the cpu_to_node() map
> > will not return a valid node number.
> > 
> > I think that's a change in behaviour, it didn't used to do that afaik.
> > Certainly this code hasn't change in a while.
> > 
> 
> If cpu_to_node() always returns a valid node id even if all cpus on the 
> node are offline, then the cpumask_of_node() implementation, which the 
> sched code is using, should either return an empty cpumask (if 
> node_to_cpumask_map[nid] isn't freed) or cpu_online_mask.  The change in 
> behavior here occurred because 
> cpu_hotplug-unmap-cpu2node-when-the-cpu-is-hotremoved.patch in -mm doesn't 
> return a valid node id and forces it to return -1 so a kzalloc_node(..., 
> -1) fallsback to allocate anywhere.

I think that's broken semantics.. so far the entire cpu<->node mapping
was invariant during hotplug. Changing that is going to be _very_
interesting and cannot be done lightly.

Because as I said, per-cpu memory is preserved over hotplug, and that
has numa affinity.

So for now, let me NACK that patch. You cannot go change stuff like
that.

> 
> But if you only need cpu_to_node() when waking up to find a runnable cpu 
> for this NUMA information, then I think you can just change the 
> kzalloc_node() in alloc_{fair,rt}_sched_group() to do 
> kzalloc(..., cpu_online(cpu) ? cpu_to_node(cpu) : NUMA_NO_NODE).

That's a confusing statement, the wakeup stuff and the
alloc_{fair,rt}_sched_group() stuff are unrelated, although both sites
might need fixing if we're going to go ahead with this.