From mboxrd@z Thu Jan  1 00:00:00 1970
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Subject: Re: [PATCH][RFC]: mutex: adaptive spin
Date: Wed, 07 Jan 2009 15:34:47 +0800
Message-ID: <49645B17.7000001@cn.fujitsu.com>
References: <87r63ljzox.fsf@basil.nowhere.org>	 <20090103191706.GA2002@parisc-linux.org> <1231093310.27690.5.camel@twins>	 <20090104184103.GE2002@parisc-linux.org> <1231242031.11687.97.camel@twins>	 <20090106121052.GA27232@elte.hu> <4963584A.4090805@novell.com>	 <20090106131643.GA15228@elte.hu> <1231248041.11687.107.camel@twins>	 <49636799.1010109@novell.com>  <20090106214229.GD6741@linux.vnet.ibm.com>	 <1231278275.11687.111.camel@twins>	 <alpine.LFD.2.00.0901061349520.3057@localhost.localdomain>	 <1231279660.11687.121.camel@twins>	 <alpine.LFD.2.00.0901061413310.3057@localhost.localdomain>	 <1231281801.11687.125.camel@twins>  <49642829.20006@cn.fujitsu.com> <1231309970.11687.163.camel@twins>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	paulmck@linux.vnet.ibm.com, Gregory Haskins <ghaskins@novell.com>,
	Ingo Molnar <mingo@elte.hu>, Matthew Wilcox <matthew@wil.cx>,
	Andi Kleen <andi@firstfloor.org>,
	Chris Mason <chris.mason@oracle.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	linux-btrfs <linux-btrfs@vger.kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Steven Rostedt <rostedt@goodmis.org>,
	Nick Piggin <npiggin@suse.de>,
	Peter Morreale <pmorreale@novell.com>,
	Sven Dietrich <SDietrich@novell.com>
To: Peter Zijlstra <peterz@infradead.org>
Return-path: <linux-btrfs-owner@vger.kernel.org>
In-Reply-To: <1231309970.11687.163.camel@twins>
List-ID: <linux-btrfs.vger.kernel.org>

Peter Zijlstra wrote:
> On Wed, 2009-01-07 at 11:57 +0800, Lai Jiangshan wrote:
>> Peter Zijlstra wrote:
>>> +void mutex_spin_or_schedule(struct mutex_waiter *waiter, long state, unsigned long *flags)
>>> +{
>>> +	struct mutex *lock = waiter->lock;
>>> +	struct task_struct *task = waiter->task;
>>> +	struct task_struct *owner = lock->owner;
>>> +	struct rq *rq;
>>> +
>>> +	if (!owner)
>>> +		goto do_schedule;
>>> +
>>> +	rq = task_rq(owner);
>>> +
>>> +	if (rq->curr != owner) {
>>> +do_schedule:
>>> +		__set_task_state(task, state);
>>> +		spin_unlock_mutex(&lock->wait_lock, *flags);
>>> +		schedule();
>>> +	} else {
>>> +		spin_unlock_mutex(&lock->wait_lock, *flags);
>>> +		for (;;) {
>>> +			/* Stop spinning when there's a pending signal. */
>>> +			if (signal_pending_state(state, task))
>>> +				break;
>>> +
>>> +			/* Owner changed, bail to revalidate state */
>>> +			if (lock->owner != owner)
>>> +				break;
>>> +
>>> +			/* Owner stopped running, bail to revalidate state */
>>> +			if (rq->curr != owner)
>>> +				break;
>>> +
>> 2 questions from my immature thought:
>>
>> 1) Do we need keep gcc from optimizing when we access lock->owner
>>    and rq->curr in the loop?
> 
> cpu_relax() is a compiler barrier iirc.
> 
>> 2) "if (rq->curr != owner)" need become smarter.
>>    schedule()
>>    {
>> 	select_next
>> 	rq->curr = next;
>> 	contex_swith
>>    }
>> we also spin when owner is select_next-ing in schedule().
>> but select_next is not fast enough.
> 
> I'm not sure what you're saying here..
> 
> 

I means when mutex owner calls schedule(), current task is also spinning
until rq->curr is changed.

I think such spin is not necessary, it is doing nothing but wasting time.
And this spin period is not short, and when this spin period ended,
rq->curr is changed too, current task has to sleep.

So I think current task should sleep earlier when it detects that
mutex owner start schedule().