linux-kernel - Re: [RFC/RFT][PATCH 6/7] sched: idle: Predict idle duration before stopping the tick

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: <20180305133725.GU25201@hirez.programming.kicks-ass.net>
Date:   Mon, 5 Mar 2018 14:37:25 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Rik van Riel <riel@...riel.com>
Cc:     "Rafael J. Wysocki" <rjw@...ysocki.net>,
        Thomas Gleixner <tglx@...utronix.de>,
        Frederic Weisbecker <fweisbec@...il.com>,
        Paul McKenney <paulmck@...ux.vnet.ibm.com>,
        Thomas Ilsche <thomas.ilsche@...dresden.de>,
        Doug Smythies <dsmythies@...us.net>,
        Aubrey Li <aubrey.li@...ux.intel.com>,
        Mike Galbraith <mgalbraith@...e.de>,
        LKML <linux-kernel@...r.kernel.org>,
        Linux PM <linux-pm@...r.kernel.org>
Subject: Re: [RFC/RFT][PATCH 6/7] sched: idle: Predict idle duration before
 stopping the tick

On Mon, Mar 05, 2018 at 08:19:15AM -0500, Rik van Riel wrote:
> > Also, I think that at this point you've introduced a problem; by not
> > disabling the tick unconditionally, we'll have extra wakeups due to
> > the (now still running) tick, which will bias the estimation, as per
> > reflect(), downwards.
> > 
> > We should effectively discard tick wakeups when we could have
> > entered nohz but didn't, accumulating the idle period in reflect and
> > only commit once we get a !tick wakeup.
> 
> How much of a problem would that actually be?
> 
> Don't all but the very deepest C-states have
> target residencies that are orders of magnitude
> smaller than the tick period?
> 
> In other words, if our sleeps end up getting
> "cut short" to 600us, we will still select C6,
> and it will not result in picking C3 by mistake.
> 
> This only seems to affect C7 states and deeper.

On modern Intel, what about other platforms? This is something that
should work across the board.

> It may be worth fixing in the long run, but that
> would require keeping track of whether anything
> non-idle was done in-between two invocations of
> do_idle(), and then checking that there.
> 
> That would include not just seeing whether there
> have been any context switches on the CPU (easy?),
> but also whether any non-timer interrupts were run.

Right, its the interrupts that are 'interesting' although I suppose we
could magic something in irq_enter().