Re: [RFC][PATCH 2/3] futex: Reduce hash bucket lock contention

[Darren Hart <dvhart@linux.intel.com>]

On 09/14/2011 08:51 AM, Peter Zijlstra wrote:
> On Wed, 2011-09-14 at 08:46 -0700, Darren Hart wrote:
>>
>> On 09/14/2011 06:30 AM, Peter Zijlstra wrote:
>>> Use the brand spanking new wake_list to delay the futex wakeups until
>>> after we've released the hash bucket locks. This avoids the newly
>>> woken tasks from immediately getting stuck on the hb lock.
>>>
>>> This is esp. painful on -rt, where the hb lock is preemptible.
>>
>> Nice!
>>
>> Have you run this through the functional and performance tests from
>> futextest? Looks like I should also add a multiwake test to really
>> showcase this.
> 
> Not more functional than booting, but a very similar patch used to live
> in 33-rt.. I lost the use-case we had that led to that patch, for -rt it
> made a huge difference because we endlessly scheduled back and forth
> between the waker and the wakee bouncing on the hb lock.
> 
>> If you don't have it local I can setup a github repository for futextest
>> until korg is back.... or do the testing myself... right.
> 
> Right, I don't think I have futextest, or I might, I'd have to dig
> around a bit.

In case you want to grab a quick copy, I decided I didn't want to have a
github repo lying around confusing people :)

http://www.dvhart.com/darren/linux/futextest.tar.bz2

> 
>>> @@ -988,7 +986,7 @@ futex_wake(u32 __user *uaddr, unsigned i
>>>  			if (!(this->bitset & bitset))
>>>  				continue;
>>>  
>>> -			wake_futex(this);
>>> +			wake_futex(&wake_list, this);
>>
>>
>> I guess this is OK. wake_futex_pi will always be one task I believe, so
>> the list syntax might confuse newcomers... Would it make sense to have a
>> wake_futex_list() call? Thinking outloud...
> 
> To what purpose? Even delaying a single wakeup until after we release
> the hb lock is useful. On it matters even on !-rt since the woken task
> can wake on another cpu and then spin on hb-lock.

Duh. You're correct of course.

>  
>>> @@ -1437,6 +1441,7 @@ static int futex_requeue(u32 __user *uad
>>>  	put_futex_key(&key2);
>>>  out_put_key1:
>>>  	put_futex_key(&key1);
>>> +	wake_up_list(&wake_list, TASK_NORMAL);
>>>  out:
>>>  	if (pi_state != NULL)
>>>  		free_pi_state(pi_state);
>>>
>>>
>>
>> I _think_ requeue_pi is in the clear here as it uses
>> requeue_pi_wake_futex, which calls wake_up_state directly. Still, some
>> testing with futextest functional/futex_requeue_pi is in order.
> 
> Ah, right, that might want frobbing too..

-- 
Darren Hart
Intel Open Source Technology Center
Yocto Project - Linux Kernel