Re: [PATCH 2/2] mm: eliminate node 0 bias in MPOL_INTERLEAVE

[Andi Kleen]

On Wed, Sep 22, 2004 at 11:32:45PM -0500, Ray Bryant wrote:
> Each of these cases potentially breaks the (assumed) invariant of

I would prefer to keep the invariant.

> +++ linux-2.6.9-rc2-mm1/mm/mempolicy.c	2004-09-21 17:44:58.000000000 -0700
> @@ -435,7 +435,7 @@ asmlinkage long sys_set_mempolicy(int re
>  		default_policy[policy] = new;
>  	}
>  	if (new && new->policy == MPOL_INTERLEAVE)
> -		current->il_next = find_first_bit(new->v.nodes, MAX_NUMNODES);
> +		current->il_next = current->pid % MAX_NUMNODES;

Please do the find_next/find_first bit here in the slow path. 

Another useful change may be to check if il_next points to a node
that is in the current interleaving mask. If yes don't change it.
This way skew when interleaving policy is set often could be avoided.

>  	return 0;
>  }
>  
> @@ -714,6 +714,11 @@ static unsigned interleave_nodes(struct 
>  
>  	nid = me->il_next;
>  	BUG_ON(nid >= MAX_NUMNODES);
> +	if (!test_bit(nid, policy->v.nodes)) {
> +		nid = find_next_bit(policy->v.nodes, MAX_NUMNODES, 1+nid);
> +		if (nid >= MAX_NUMNODES)
> +			nid = find_first_bit(policy->v.nodes, MAX_NUMNODES);
> +	}

And remove it here.

>  	next = find_next_bit(policy->v.nodes, MAX_NUMNODES, 1+nid);
>  	if (next >= MAX_NUMNODES)
>  		next = find_first_bit(policy->v.nodes, MAX_NUMNODES);
> Index: linux-2.6.9-rc2-mm1/kernel/fork.c
> ===================================================================
> --- linux-2.6.9-rc2-mm1.orig/kernel/fork.c	2004-09-21 16:24:49.000000000 -0700
> +++ linux-2.6.9-rc2-mm1/kernel/fork.c	2004-09-21 17:41:12.000000000 -0700
> @@ -873,6 +873,8 @@ static task_t *copy_process(unsigned lon
>  			goto bad_fork_cleanup;
>  		}
>  	}
> +	/* randomize placement of first page across nodes */
> +	p->il_next = p->pid % MAX_NUMNODES;

Same here.

-Andi
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/