[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <20240816071109.63059-1-neeraj.upadhyay@kernel.org>
Date: Fri, 16 Aug 2024 12:41:09 +0530
From: neeraj.upadhyay@...nel.org
To: rcu@...r.kernel.org
Cc: linux-kernel@...r.kernel.org,
kernel-team@...a.com,
rostedt@...dmis.org,
paulmck@...nel.org,
neeraj.upadhyay@...nel.org,
neeraj.upadhyay@....com,
boqun.feng@...il.com,
joel@...lfernandes.org,
urezki@...il.com,
frederic@...nel.org,
Waiman Long <longman@...hat.com>,
Vratislav Bendel <vbendel@...hat.com>,
Breno Leitao <leitao@...ian.org>
Subject: [PATCH rcu] rcu: Use system_unbound_wq to avoid disturbing isolated CPUs
From: Waiman Long <longman@...hat.com>
It was discovered that isolated CPUs could sometimes be disturbed by
kworkers processing kfree_rcu() works causing higher than expected
latency. It is because the RCU core uses "system_wq" which doesn't have
the WQ_UNBOUND flag to handle all its work items. Fix this violation of
latency limits by using "system_unbound_wq" in the RCU core instead.
This will ensure that those work items will not be run on CPUs marked
as isolated.
Beside the WQ_UNBOUND flag, the other major difference between system_wq
and system_unbound_wq is their max_active count. The system_unbound_wq
has a max_active of WQ_MAX_ACTIVE (512) while system_wq's max_active
is WQ_DFL_ACTIVE (256) which is half of WQ_MAX_ACTIVE.
Reported-by: Vratislav Bendel <vbendel@...hat.com>
Closes: https://issues.redhat.com/browse/RHEL-50220
Signed-off-by: Waiman Long <longman@...hat.com>
Reviewed-by: "Uladzislau Rezki (Sony)" <urezki@...il.com>
Tested-by: Breno Leitao <leitao@...ian.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@...nel.org>
---
kernel/rcu/tree.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e641cc681901..494aa9513d0b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3539,10 +3539,10 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
if (delayed_work_pending(&krcp->monitor_work)) {
delay_left = krcp->monitor_work.timer.expires - jiffies;
if (delay < delay_left)
- mod_delayed_work(system_wq, &krcp->monitor_work, delay);
+ mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
return;
}
- queue_delayed_work(system_wq, &krcp->monitor_work, delay);
+ queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
}
static void
@@ -3634,7 +3634,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
// be that the work is in the pending state when
// channels have been detached following by each
// other.
- queue_rcu_work(system_wq, &krwp->rcu_work);
+ queue_rcu_work(system_unbound_wq, &krwp->rcu_work);
}
}
@@ -3704,7 +3704,7 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
!atomic_xchg(&krcp->work_in_progress, 1)) {
if (atomic_read(&krcp->backoff_page_cache_fill)) {
- queue_delayed_work(system_wq,
+ queue_delayed_work(system_unbound_wq,
&krcp->page_cache_work,
msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
} else {
--
2.40.1
Powered by blists - more mailing lists