The percpu workqueue pool are persistend and never be freed.
But cpu<->node relationship can be changed by cpu hotplug and pool->node
can point to an offlined node.
If pool->node points to an offlined node,
following allocation failure can happen.
==
SLUB: Unable to allocate memory on node 2 (gfp=0x80d0)
cache: kmalloc-192, object size: 192, buffer size: 192, default
order:
1, min order: 0
node 0: slabs: 6172, objs: 259224, free: 245741
node 1: slabs: 3261, objs: 136962, free: 127656
==
This patch clears per-cpu workqueue pool's node affinity at
cpu offlining and restore it at cpu onlining.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hir...@jp.fujitsu.com>
---
kernel/workqueue.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 7809154..2fd0bd7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4586,6 +4586,11 @@ static int workqueue_cpu_up_callback(struct
notifier_block *nfb,
case CPU_DOWN_FAILED:
case CPU_ONLINE:
mutex_lock(&wq_pool_mutex);
+ /*
+ * now cpu <-> node info is established. update numa node
+ */
+ for_each_cpu_worker_pool(pool, cpu)
+ pool->node = cpu_to_node(cpu);
for_each_pool(pool, pi) {
mutex_lock(&pool->attach_mutex);
@@ -4619,6 +4624,7 @@ static int workqueue_cpu_down_callback(struct
notifier_block *nfb,
int cpu = (unsigned long)hcpu;
struct work_struct unbind_work;
struct workqueue_struct *wq;
+ struct worker_pool *pool;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
@@ -4626,10 +4632,13 @@ static int workqueue_cpu_down_callback(struct
notifier_block *nfb,
INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn);
queue_work_on(cpu, system_highpri_wq, &unbind_work);
- /* update NUMA affinity of unbound workqueues */
mutex_lock(&wq_pool_mutex);
+ /* update NUMA affinity of unbound workqueues */
list_for_each_entry(wq, &workqueues, list)
wq_update_unbound_numa(wq, cpu, false);
+ /* clear per-cpu workqueues's numa affinity. */
+ for_each_cpu_worker_pool(pool, cpu)
+ pool->node = NUMA_NO_NODE; /* restored at online */
mutex_unlock(&wq_pool_mutex);
/* wait for per-cpu unbinding to finish */
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
