[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20201103203401.305923534@linuxfoundation.org>
Date: Tue, 3 Nov 2020 21:34:24 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Jens Axboe <axboe@...nel.dk>
Subject: [PATCH 5.9 213/391] io-wq: assign NUMA node locality if appropriate
From: Jens Axboe <axboe@...nel.dk>
commit a8b595b22d31f83b715511f59012f152a269d83b upstream.
There was an assumption that kthread_create_on_node() would properly set
NUMA affinities in terms of CPUs allowed, but it doesn't. Make sure we
do this when creating an io-wq context on NUMA.
Cc: stable@...r.kernel.org
Stefan Metzmacher <metze@...ba.org>
Signed-off-by: Jens Axboe <axboe@...nel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
fs/io-wq.c | 1 +
1 file changed, 1 insertion(+)
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -654,6 +654,7 @@ static bool create_io_worker(struct io_w
kfree(worker);
return false;
}
+ kthread_bind_mask(worker->task, cpumask_of_node(wqe->node));
raw_spin_lock_irq(&wqe->lock);
hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
Powered by blists - more mailing lists