linux-kernel - Re: RT wakeup woes in Linux 2.6.31.6 on Mac Mini

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]

Message-ID: <a27c0c970911131724o3ffb03d3sc58f1e78e17932b1@mail.gmail.com>
Date:	Fri, 13 Nov 2009 17:24:59 -0800
From:	Greg Steuck <greg@...t.cx>
To:	rostedt@...dmis.org
Cc:	linux-kernel@...r.kernel.org, Ingo Molnar <mingo@...e.hu>,
	Thomas Gleixner <tglx@...utronix.de>,
	Peter Zijlstra <peterz@...radead.org>
Subject: Re: RT wakeup woes in Linux 2.6.31.6 on Mac Mini

Hi Steven,

Thanks for your reply. I believe the answer to my outliers question is
- that's normal. I am lucky enough that 1ms delay is acceptable for my
project and so I can stick with vanilla kernel for now.

On Thu, Nov 12, 2009 at 4:14 PM, Steven Rostedt <rostedt@...dmis.org> wrote:
> Have you tried the -rt kernel?

I have now.

> I think you want "wakeup_rt", since that ignores SCHED_OTHER tasks.
> SCHED_OTHER may wake up poorly, and hide the results of your RT task.

Yes, done that now.

> Looks like NEED_RESCHED is set, but interrupts are disabled. This is
> typical for vanilla linux. I really suggest trying out the latest -rt
> patch.

With -rt9 I see a different set of interesting behaviors. I should
mention that my task needs to send network packets. So, I end up
trying to juggle priorities of  irq/27-eth0, sirq-net-rx/1 and my
rxtest tasks. If I make my task higher priority than the other two, I
get interrupts delayed (because my task is being a hog sometimes). If
I go the other way and my task gets lower priority, I end up with my
task not getting to run when there is a lot of network activity which
ultimately kills it.

Thanks
Greg
-- 
nest.cx is Gmail hosted, use PGP for anything private. Key:
http://tinyurl.com/ho8qg
Fingerprint: 5E2B 2D0E 1E03 2046 BEC3  4D50 0B15 42BD 8DF5 A1B0
--
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/