Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932601AbWKSR6A (ORCPT ); Sun, 19 Nov 2006 12:58:00 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932638AbWKSR6A (ORCPT ); Sun, 19 Nov 2006 12:58:00 -0500 Received: from host-233-54.several.ru ([213.234.233.54]:40126 "EHLO mail.screens.ru") by vger.kernel.org with ESMTP id S932601AbWKSR57 (ORCPT ); Sun, 19 Nov 2006 12:57:59 -0500 Date: Sun, 19 Nov 2006 22:00:27 +0300 From: Oleg Nesterov To: Jens Axboe Cc: "Paul E. McKenney" , Alan Stern , Linus Torvalds , Thomas Gleixner , Ingo Molnar , LKML , john stultz , David Miller , Arjan van de Ven , Andrew Morton , Andi Kleen , manfred@colorfullife.com Subject: Re: [patch] cpufreq: mark cpufreq_tsc() as core_initcall_sync Message-ID: <20061119190027.GA3676@oleg> References: <20061117065128.GA5452@us.ibm.com> <20061117092925.GT7164@kernel.dk> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20061117092925.GT7164@kernel.dk> User-Agent: Mutt/1.5.11 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2259 Lines: 86 On 11/17, Jens Axboe wrote: > > It works for me, but the overhead is still large. Before it would take > 8-12 jiffies for a synchronize_srcu() to complete without there actually > being any reader locks active, now it takes 2-3 jiffies. So it's > definitely faster, and as suspected the loss of two of three > synchronize_sched() cut down the overhead to a third. > > It's still too heavy for me, by far the most calls I do to > synchronize_srcu() doesn't have any reader locks pending. I'm still a > big advocate of the fastpath srcu_readers_active() check. I can > understand the reluctance to make it the default, but for my case it's > "safe enough", so if we could either export srcu_readers_active() or > export a synchronize_srcu_fast() (or something like that), then SRCU > would be a good fit for barrier vs plug rework. Just an idea. How about another variant of srcu which is more optimized for writers? struct xxx_struct { int completed; atomic_t ctr[2]; struct mutex mutex; wait_queue_head_t wq; }; void init_xxx_struct(struct xxx_struct *sp) { sp->completed = 0; atomic_set(sp->ctr + 0, 1); atomic_set(sp->ctr + 1, 1); mutex_init(&sp->mutex); init_waitqueue_head(&sp->wq); } int xxx_read_lock(struct xxx_struct *sp) { int idx; idx = sp->completed & 0x1; atomic_inc(sp->ctr + idx); smp_mb__after_atomic_inc(); return idx; } void xxx_read_unlock(struct xxx_struct *sp, int idx) { if (atomic_dec_and_test(sp->ctr + idx)) wake_up(&sp->wq); } void synchronize_xxx(struct xxx_struct *sp) { wait_queue_t wait; int idx; init_wait(&wait); mutex_lock(&sp->mutex); idx = sp->completed++ & 0x1; for (;;) { prepare_to_wait(&sp->wq, &wait, TASK_UNINTERRUPTIBLE); if (!atomic_add_unless(sp->ctr + idx, -1, 1)) break; schedule(); atomic_inc(sp->ctr + idx); } finish_wait(&sp->wq, &wait); mutex_unlock(&sp->mutex); } Very simple. Note that synchronize_xxx() is O(1), doesn't poll, and could be optimized further. Oleg. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/