linux-kernel - Re: [PATCH] sched, fair: Allow a small degree of load imbalance between SD

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <383de0cc-ad84-4cc1-48d6-512e7d3ddaa8@arm.com>
Date:   Thu, 19 Dec 2019 11:56:09 +0000
From:   Valentin Schneider <valentin.schneider@....com>
To:     Mel Gorman <mgorman@...hsingularity.net>
Cc:     Vincent Guittot <vincent.guittot@...aro.org>,
        Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>, pauld@...hat.com,
        srikar@...ux.vnet.ibm.com, quentin.perret@....com,
        dietmar.eggemann@....com, Morten.Rasmussen@....com,
        hdanton@...a.com, parth@...ux.ibm.com, riel@...riel.com,
        LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] sched, fair: Allow a small degree of load imbalance
 between SD_NUMA domains

On 18/12/2019 22:50, Mel Gorman wrote:
>> I'm quite sure you have reasons to have written it that way, but I was
>> hoping we could squash it down to something like:
> 
> I wrote it that way to make it clear exactly what has changed, the
> thinking behind the checks and to avoid 80-col limits to make review
> easier overall. It's a force of habit and I'm happy to reformat it as
> you suggest except....
> 

I tend to disregard the 80 col limit, so I might not be the best example
here :D

>> ---
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 08a233e97a01..f05d09a8452e 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -8680,16 +8680,27 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
>>  			env->migration_type = migrate_task;
>>  			lsub_positive(&nr_diff, local->sum_nr_running);
>>  			env->imbalance = nr_diff >> 1;
>> -			return;
>> +		} else {
>> +
>> +			/*
>> +			 * If there is no overload, we just want to even the number of
>> +			 * idle cpus.
>> +			 */
>> +			env->migration_type = migrate_task;
>> +			env->imbalance = max_t(long, 0, (local->idle_cpus -
>> +							 busiest->idle_cpus) >> 1);
>>  		}
>>  
>>  		/*
>> -		 * If there is no overload, we just want to even the number of
>> -		 * idle cpus.
>> +		 * Allow for a small imbalance between NUMA groups; don't do any
>> +		 * of it if there is at least half as many tasks / busy CPUs as
>> +		 * there are available CPUs in the busiest group
>>  		 */
>> -		env->migration_type = migrate_task;
>> -		env->imbalance = max_t(long, 0, (local->idle_cpus -
>> -						 busiest->idle_cpus) >> 1);
>> +		if (env->sd->flags & SD_NUMA &&
>> +		    (busiest->sum_nr_running < busiest->group_weight >> 1) &&
> 
> This last line is not exactly equivalent to what I wrote. It would need
> to be
> 
> 	(busiest->sum_nr_running < (busiest->group_weight >> 1) - imbalance_adj) &&
> 

Right, I was implicitly suggesting that maybe we could forgo the
imbalance_adj computation and just roll with the imbalance_pct (with perhaps
and extra shift here and there). IMO the important thing here is the 
half-way cutoff.

> I can test as you suggest to see if it's roughly equivalent in terms of
> performance. The intent was to have a cutoff just before we reached 50%
> running tasks / busy CPUs.
> 

I think that cutoff makes sense; it's also important that it isn't purely
busy CPU-based because we're not guaranteed to have 1 task per CPU (due to
affinity or else), so I think the "half as many tasks as available CPUs"
thing has some merit.