Hello,
Sorry about the delay. I was wondering what happened to this thread earlier
in the morning and realized that I missed your reply. Thanks for the dump
and instruction. I was only testing on NUMA setups and made a silly mistake.
Can you please try the following patch?
------ 8< ------
workqueue: The default node_nr_active should have its max set to max_active
The default nna (node_nr_active) is used when the pool isn't tied to a
specific NUMA node. This can happen in the following cases:
1. On NUMA, if per-node pwq init failure and the fallback pwq is used.
2. On NUMA, if a pool is configured to span multiple nodes.
3. On single node setups.
5797b1c18919 ("workqueue: Implement system-wide nr_active enforcement for
unbound workqueues") set the default nna->max to min_active because only #1
was being considered. For #2 and #3, using min_active means that the max
concurrency in normal operation is pushed down to min_active which is
currently 8, which can obviously lead to performance issues.
#1 is very unlikely to happen to begin with and even when it does which
exact value nna->max is set to doesn't really matter. #2 can only happen if
the workqueue is intentionally configured to ignore NUMA boundaries and
there's no good way to distribute max_active in this case. #3 is the default
behavior on single node machines.
Let's set it the default nna->max to max_active. This fixes the artificially
lowered concurrency problem on single node machines and shouldn't hurt
anything for other cases.
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@xxxxxxx>
Fixes: 5797b1c18919 ("workqueue: Implement system-wide nr_active enforcement for unbound workqueues")
Link: http://lkml.kernel.org/r/20240410082822.2131994-1-shinichiro.kawasaki@xxxxxxx
---
kernel/workqueue.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0066c8f6c154..f94ae51c6f2b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1606,7 +1606,7 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
min_active, max_active);
}
- wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active;
+ wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
}
/**
