linux-kernel - Re: [PATCH] sched: make update_sd_pick

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: <20140725141542.GO19379@twins.programming.kicks-ass.net>
Date:	Fri, 25 Jul 2014 16:15:42 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	Rik van Riel <riel@...hat.com>
Cc:	Vincent Guittot <vincent.guittot@...aro.org>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	Michael Neuling <mikey@...ling.org>,
	Ingo Molnar <mingo@...nel.org>, Paul Turner <pjt@...gle.com>,
	jhladky@...hat.com, ktkhai@...allels.com,
	tim.c.chen@...ux.intel.com,
	Nicolas Pitre <nicolas.pitre@...aro.org>
Subject: Re: [PATCH] sched: make update_sd_pick_busiest return true on a
 busier sd

On Fri, Jul 25, 2014 at 10:02:43AM -0400, Rik van Riel wrote:
> On a related note, that part of the load balancing code probably
> needs to be rewritten to deal with unequal group_capacity_factors
> anyway.
> 
> Say that one group has a group_capacity_factor twice that of
> another group.
> 
> The group with the smaller group_capacity_factor is overloaded
> by a factor 1.3. The larger group is loaded by a factor 0.8.
> This means the larger group has a higher load than the first
> group, and the current code in update_sd_pick_busiest will
> not select the overloaded group as the busiest one, due to not
> scaling load with the capacity...
> 
> static bool update_sd_pick_busiest(struct lb_env *env,
>                                    struct sd_lb_stats *sds,
>                                    struct sched_group *sg,
>                                    struct sg_lb_stats *sgs)
> {
>         if (sgs->avg_load <= sds->busiest_stat.avg_load)
>                 return false;
> 
> I believe we may need to factor the group_capacity_factor
> into this calculation, in order to properly identify which
> group is busiest.

(sorry, going through this backwards, I'll get to the actual patch in a
bit)

Note how update_sg_lb_stats() where we compute sgs->avg_load we do
divide by sgs->group_capacity.

(also, curse this renaming of stuff)

The group_capacity_factor is something ugly and Vincent was going to
poke at that.

Content of type "application/pgp-signature" skipped