linux-kernel - Re: [PATCH v2] sched/completion: convert completions to use simple wait queues

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] [day] [month] [year] [list]

Date:	Mon, 23 May 2016 16:09:52 +0200
From:	Daniel Wagner <wagi@...om.org>
To:	Luiz Capitulino <lcapitulino@...hat.com>
Cc:	linux-kernel@...r.kernel.org, linux-rt-users@...r.kernel.org,
	"Peter Zijlstra (Intel)" <peterz@...radead.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	Daniel Wagner <daniel.wagner@...-carit.de>
Subject: Re: [PATCH v2] sched/completion: convert completions to use simple
 wait queues

[Sorry for the late response. I was a few days on holiday]

On 05/16/2016 10:38 PM, Luiz Capitulino wrote:
> On Thu, 12 May 2016 16:08:34 +0200
> Daniel Wagner <wagi@...om.org> wrote:
> 
>> In short, I haven't figured out yet why the kernel builds get slightly slower. 
> 
> You're doing make -j 200, right? How many cores do you have? Couldn't it
> be that you're saturating your CPUs?

For the above numbers I used mmtest as test framework with 2x<NR CPUs>,
that is 128.

> You could try make -j<NR CPUs>, or some process creation benchmark. Although
> I don't know what's the best way to measure this.

Yeah, I consider the kernel benchmark not as a good workload to figure
out what's going on. It's more like to see something is hiding. The
micro benchmarks I used so far couldn't highlight the problem(s). I
guess more testing is needed.

cheers,
daniel