diff mbox series

rt-numa: Use a reasonable default max CPU value.

Message ID 20230119195117.61460-1-jkacur@redhat.com
State New
Headers show
Series rt-numa: Use a reasonable default max CPU value. | expand

Commit Message

John Kacur Jan. 19, 2023, 7:51 p.m. UTC 
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

numa_num_task_cpus() returns here > 100 CPUs while the system has only
32 populated. The BIOS assumes that I can probably use larger CPUs (with
more cores) on the socket so the number of "configured CPUs" is rather
high.

It makes sense to use the current affinity instead of looking
at the number of possible CPUs which could be brought online.
It still depends on the affinity of the created threads
if the additional CPUs can be used. In a container setup
this may not be the case.

Use sched_getaffinity() to figure out the number of possible CPUs.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
- Edited the commit message to remove reference to -S
Signed-off-by: John Kacur <jkacur@redhat.com>
---
 src/lib/rt-numa.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/src/lib/rt-numa.c b/src/lib/rt-numa.c
index 3eead80c3b2b..1b09cff8d948 100644
--- a/src/lib/rt-numa.c
+++ b/src/lib/rt-numa.c
@@ -35,10 +35,19 @@  int numa_initialize(void)
 
 int get_available_cpus(struct bitmask *cpumask)
 {
+	cpu_set_t cpuset;
+	int ret;
+
 	if (cpumask)
 		return numa_bitmask_weight(cpumask);
 
-	return numa_num_task_cpus();
+	CPU_ZERO(&cpuset);
+
+	ret = sched_getaffinity(0, sizeof(cpu_set_t), &cpuset);
+	if (ret < 0)
+		fatal("sched_getaffinity failed: %m\n");
+
+	return CPU_COUNT(&cpuset);
 }
 
 int cpu_for_thread_sp(int thread_num, int max_cpus, struct bitmask *cpumask)