Re: [PATCH 2/6] futex: Implement FUTEX2_NUMA

From
Peter Zijlstra <peterz@infradead.org>
Date
2024-10-28 09:38:39
Also in
linux-arch, linux-mm, lkml
Reply to
Davidlohr Bueso, 2024-10-25
On Fri, Oct 25, 2024 at 11:30:26AM -0700, Davidlohr Bueso wrote:
On Fri, 25 Oct 2024, Peter Zijlstra wrote:\n
quoted
static int __init futex_init(void)
{
-	unsigned int futex_shift;
-	unsigned long i;
+	unsigned int order, n;
+	unsigned long size, i;

#ifdef CONFIG_BASE_SMALL
	futex_hashsize = 16;
#else
-	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+	futex_hashsize = 256 * num_possible_cpus();
+	futex_hashsize /= num_possible_nodes();
+	futex_hashsize = roundup_pow_of_two(futex_hashsize);
#endif
+	futex_hashshift = ilog2(futex_hashsize);
+	size = sizeof(struct futex_hash_bucket) * futex_hashsize;
+	order = get_order(size);
+
+	for_each_node(n) {
Probably want to skip nodes that don't have CPUs, those will never
have the remote for .node value.
What if the CPU-less node is placed equidistant between two (or more)
regular nodes and it is the best location for a futex that is spanning
those nodes?

That is to say, just because it doesn't have CPUs, doesn't mean it is
never the right node.

Hmm?
Thread (17 messages) 17 messages, 5 authors, last reply 2024-10-28
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help