linux-kernel - Re: [PATCH 2/2 v4] sched: Rewrite per entity runnable load average

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: <20140731191638.GG28673@intel.com>
Date:	Fri, 1 Aug 2014 03:16:38 +0800
From:	Yuyang Du <yuyang.du@...el.com>
To:	Vincent Guittot <vincent.guittot@...aro.org>
Cc:	peterz@...radead.org, mingo@...hat.com,
	linux-kernel@...r.kernel.org, pjt@...gle.com, bsegall@...gle.com,
	arjan.van.de.ven@...el.com, len.brown@...el.com,
	rafael.j.wysocki@...el.com, alan.cox@...el.com,
	mark.gross@...el.com, fengguang.wu@...el.com,
	morten.rasmussen@....com
Subject: Re: [PATCH 2/2 v4] sched: Rewrite per entity runnable load average

Hi Vincent,

On Thu, Jul 31, 2014 at 11:56:13AM +0200, Vincent Guittot wrote:
> 
> load_sum is now the average runnable time before being weighted

So when weight changes, load_avg will completely use new weight. I have
some cents:

1) Task does not change weight much, so it is practically ok

2) Group entity does change weight much, and very likely back and forth,
   so I really think keeping the intact history will make everything
   more predictable/stable, prevent thrashing, etc.

3) If you do the same for cfs_rq->load.weight, then we simply abandoned
   blocked entities, and all states won't compute. So we then need to
   maintain blocked load average again, and we just can't do cfs_rq load
   average as a whole anymore, but must update at the granularity of an
   entity...

Anyway, it does not seem to me you really need to change load_sum, no? So
could you please not change it?

> The sum of usage_sum of the tasks that are on a rq, is used to detect
> the overload of a rq.

I think you only need usage_sum for task and rq, but not cfs_rq. Others
are ok.

> Does something like the patch below to be applied of top of your patchset, seem
> reasonable add-on?
> 

If you only add running statistics, I am all good, and indeed reasonable if
you can make good use of it. I am not at all against adding anything or
adding running average or unweighted anything...

Thanks,
Yuyang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/