From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758286Ab3BFUJR (ORCPT ); Wed, 6 Feb 2013 15:09:17 -0500 Received: from mx1.redhat.com ([209.132.183.28]:4541 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758185Ab3BFUJJ (ORCPT ); Wed, 6 Feb 2013 15:09:09 -0500 Date: Wed, 6 Feb 2013 15:05:29 -0500 From: Rik van Riel To: linux-kernel@vger.kernel.org Cc: aquini@redhat.com, eric.dumazet@gmail.com, lwoodman@redhat.com, knoel@redhat.com, chegu_vinod@hp.com, raghavendra.kt@linux.vnet.ibm.com, mingo@redhat.com Subject: [PATCH -v5 3/5] x86,smp: auto tune spinlock backoff delay factor Message-ID: <20130206150529.43150afa@cuia.bos.redhat.com> In-Reply-To: <20130206150311.19cd1e52@cuia.bos.redhat.com> References: <20130206150311.19cd1e52@cuia.bos.redhat.com> Organization: Red Hat, Inc Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Many spinlocks are embedded in data structures; having many CPUs pounce on the cache line the lock is in will slow down the lock holder, and can cause system performance to fall off a cliff. The paper "Non-scalable locks are dangerous" is a good reference: http://pdos.csail.mit.edu/papers/linux:lock.pdf In the Linux kernel, spinlocks are optimized for the case of there not being contention. After all, if there is contention, the data structure can be improved to reduce or eliminate lock contention. Likewise, the spinlock API should remain simple, and the common case of the lock not being contended should remain as fast as ever. However, since spinlock contention should be fairly uncommon, we can add functionality into the spinlock slow path that keeps system performance from falling off a cliff when there is lock contention. Proportional delay in ticket locks is delaying the time between checking the ticket based on a delay factor, and the number of CPUs ahead of us in the queue for this lock. Checking the lock less often allows the lock holder to continue running, resulting in better throughput and preventing performance from dropping off a cliff. Proportional spinlock delay with a high delay factor works well when there is lots contention on a lock. Likewise, a smaller delay factor works well when a lock is lightly contended. Making the code auto-tune the delay factor results in a system that performs well with both light and heavy lock contention. Signed-off-by: Rik van Riel Acked-by: Rafael Aquini Reviewed-by: Michel Lespinasse --- arch/x86/kernel/smp.c | 41 ++++++++++++++++++++++++++++++++++++++--- 1 files changed, 38 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index aa743e9..b19648a 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -112,13 +112,34 @@ static atomic_t stopping_cpu = ATOMIC_INIT(-1); static bool smp_no_nmi_ipi = false; +#define DELAY_SHIFT 8 +#define DELAY_FIXED_1 (1<tickets.head) != ticket); break; } - loops = 50 * waiters_ahead; + + /* Aggressively increase delay, to minimize lock accesses. */ + if (delay < MAX_SPINLOCK_DELAY) + delay += DELAY_FIXED_1 / 7; + + loops = (delay * waiters_ahead) >> DELAY_SHIFT; while (loops--) cpu_relax(); head = ACCESS_ONCE(lock->tickets.head); - if (head == ticket) + if (head == ticket) { + /* + * We overslept, and do not know by how much. + * Exponentially decay the value of delay, + * to get it back to a good value quickly. + */ + if (delay >= 2 * DELAY_FIXED_1) + delay -= max(delay/32, DELAY_FIXED_1); break; + } } + __this_cpu_write(spinlock_delay, delay); } /*