Messages in this thread | | | Subject | Re: nohz: Warn if the machine can not perform nohz_full | From | Steven Rostedt <> | Date | Mon, 15 Jul 2013 14:49:42 -0400 |
| |
On Mon, 2013-07-15 at 13:38 -0400, Dave Jones wrote: > On Mon, Jul 15, 2013 at 01:24:23PM -0400, Dave Jones wrote: > > On Mon, Jul 15, 2013 at 07:18:02PM +0200, Frederic Weisbecker wrote: > > > > > > So I guess you guys never want this to be enabled on distro kernels ? > > > > If that's the case, can you add something to that effect in Kconfig ? > > > > > > I believe we want it to be enabled on distros in the long term. But right now it would > > > be a bad idea until the off case (nohz_full= parameter empty) is carefully optimized. > > > I'm currently working on that. > > > > > > Now for the unstable tsc, which is what it's about on the above code block, we need > > > the tick to be there to leverage the sched clock madness. May be there could be some > > > other solution that could work along full dynticks but for now we chose the easy path. > > > > > > Are broken TSCs that common? > > > > I just hit one apparently. http://paste.fedoraproject.org/25421/73907845/raw/ > > That's a fairly recent Atom board, so I suspect it's not uncommon on that platform. > > And here's a Core Duo from circa 2008. > http://paste.fedoraproject.org/25429/13739098/raw > > Two for two so far. I get the feeling you guys are going to get a ton of these reports. >
Hmm, we should only warn if the user tried to enable nohz-full via the command line. But it looks like it warns even without enabling nohz-full, which wasn't the desired effect.
I'll look at this, and send a patch to make sure the warning only happens when the user tries to use nohz-full, and doesn't just compile it in. The point of the patch is to not let the user think they have nohz-full when they don't.
-- Steve
| |