Re: [PATCH] kthread: ensure locality of task_struct allocations

[David Rientjes <rientjes@google.com>]

On Wed, 29 Jan 2014, Christoph Lameter wrote:

> > > diff --git a/kernel/kthread.c b/kernel/kthread.c
> > > index b5ae3ee..8573e4e 100644
> > > --- a/kernel/kthread.c
> > > +++ b/kernel/kthread.c
> > > @@ -217,7 +217,7 @@ int tsk_fork_get_node(struct task_struct *tsk)
> > >  	if (tsk == kthreadd_task)
> > >  		return tsk->pref_node_fork;
> > >  #endif
> > > -	return numa_node_id();
> > > +	return numa_mem_id();
> >
> > I'm wondering why return NUMA_NO_NODE wouldn't have the same effect and
> > prefer the local node?
> >
> 
> The idea here seems to be that the allocation may occur from a cpu that is
> different from where the process will run later on.
> 

Yeah, that makes sense for kthreadd, but I'm wondering why we have to 
return numa_mem_id() rather than just NUMA_NO_NODE.  Sorry for not being 
specific about doing s/numa_mem_id/NUMA_NO_NODE/ here.

That should just turn kmem_cache_alloc_node() into kmem_cache_alloc() and 
alloc_pages_node() into alloc_pages() for the allocators that use this 
return value, task_struct and thread_info.  If that's not allocating local 
memory, if possible, and numa_mem_id() magically does, then there's a 
problem.

Eric, did you try this when writing 207205a2ba26 ("kthread: NUMA aware 
kthread_create_on_node()") or was it always numa_node_id() from the 
beginning?