linux-kernel - Re: [PATCH 08/57] microblaze_v7: Interrupt handling, timer support, selfmod code

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: <alpine.LFD.2.00.0903211206090.29264@localhost.localdomain>
Date:	Sat, 21 Mar 2009 12:14:04 +0100 (CET)
From:	Thomas Gleixner <tglx@...utronix.de>
To:	Michal Simek <monstr@...str.eu>
cc:	john stultz <johnstul@...ibm.com>,
	LKML <linux-kernel@...r.kernel.org>, john.williams@...alogix.com
Subject: Re: [PATCH 08/57] microblaze_v7: Interrupt handling, timer support,
 selfmod code

On Sat, 21 Mar 2009, Michal Simek wrote:
> CONFIG_HZ_100=y
> # CONFIG_HZ_250 is not set
> # CONFIG_HZ_300 is not set
> # CONFIG_HZ_1000 is not set
> CONFIG_HZ=100
> 
> For NO_HZ val I shouldn't use HZ value because of NO_HZ and HZ values shouldn't
> be in .config file. Am I right?

No. NO_HZ does not remove the HZ value from the kernel. There is way
too much code depending on it. What NO_HZ does is to supress the
periodic tick when the system goes idle and the next timer expiry is
farther away than 1 HZ. When the system is non idle then the periodic
tick runs again. NO_HZ is merily for power saving.

In a normal kernel when the machine is idle then we wake up every HZ
to find out that there is no work to do and we go idle again. But if
you think about it then this is stupid, because the kernel knows when
the next timer is due to expire. So if the next timer expiry is
e.g. 100ms away, then we can sleep for full 100ms instead of sleeping
10 * 10ms (HZ=100) or 100 * 1ms (HZ=1000). This allows systems to go
into deeper power saving states.

You should be able to observe the difference by monitoring
/proc/interrupts. A nohz enabled kernel should have significantly less
timer interrupts on an idle system.

Thanks,

	tglx
--
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/