linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 0/2] nodemask: Use nr_node_ids
@ 2023-08-02 11:24 Peter Zijlstra
  2023-08-02 11:24 ` [PATCH 1/2] mm: Mark nr_node_ids __ro_after_init Peter Zijlstra
  2023-08-02 11:25 ` [PATCH 2/2] mm,nodemask: Use nr_node_ids Peter Zijlstra
  0 siblings, 2 replies; 12+ messages in thread
From: Peter Zijlstra @ 2023-08-02 11:24 UTC (permalink / raw)
  To: yury.norov, andriy.shevchenko, linux
  Cc: peterz, Andrew Morton, linux-kernel, linux-mm, tglx, rppt

Hi,

While working on some NUMA code recently, I stumbled over how nodemask
operations are unconditionally using MAX_NUMNODES length, which is typically
1024 for distro configs.

OTOH typical machines only have <=4 nodes, so doing these crazy long bitmap ops
is silly.

Therefore do as cpumask does and use nr_node_ids analogous to nr_cpu_ids.

These patches are lightly tested -- as in they seem to boot on a 2 node system.




^ permalink raw reply	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2023-08-04  8:14 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-08-02 11:24 [PATCH 0/2] nodemask: Use nr_node_ids Peter Zijlstra
2023-08-02 11:24 ` [PATCH 1/2] mm: Mark nr_node_ids __ro_after_init Peter Zijlstra
2023-08-02 14:58   ` Mike Rapoport
2023-08-02 11:25 ` [PATCH 2/2] mm,nodemask: Use nr_node_ids Peter Zijlstra
2023-08-02 15:32   ` Mike Rapoport
2023-08-02 15:48     ` Peter Zijlstra
2023-08-02 19:36   ` [PATCH v2 " Peter Zijlstra
2023-08-03  0:45     ` Yury Norov
2023-08-03  8:41       ` Peter Zijlstra
2023-08-03 20:41         ` Yury Norov
2023-08-03 21:00           ` Yury Norov
2023-08-04  8:14           ` Peter Zijlstra

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox