lkml.org 
[lkml]   [2013]   [Jan]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [patch 00/40] CPU hotplug rework - episode I
    On Thu, 31 Jan 2013, Andrew Morton wrote:

    > On Thu, 31 Jan 2013 15:44:10 -0000
    > Thomas Gleixner <tglx@linutronix.de> wrote:
    >
    > > At the end hotplug should run through an array of callbacks on both
    > > sides with explicit core synchronization points. The ordering should
    > > look like this:
    > >
    > > CPUHP_OFFLINE // Start state.
    > > CPUHP_PREP_<hardware> // Kick CPU into life / let it die
    > > CPUHP_PREP_<datastructures> // Get datastructures set up / freed.
    > > CPUHP_PREP_<threads> // Create threads for cpu
    > > CPUHP_SYNC // Synchronization point
    > > CPUHP_INIT_<hardware> // Startup/teardown on the CPU (interrupts, timers ...)
    > > CPUHP_SCHED_<stuff on CPU> // Unpark/park per cpu local threads on the CPU.
    > > CPUHP_ENABLE_<stuff_on_CPU> // Enable/disable facilities
    > > CPUHP_SYNC // Synchronization point
    > > CPUHP_SCHED // Expose/remove CPU from general scheduler.
    > > CPUHP_ONLINE // Final state
    >
    > What does CPUHP_SYNC do?

    This is a future step which makes sure that the cpu which controls the
    bringup and the teardown of the hotplugged cpu are synchronizing at
    some point. Right now, we have this synchronization burried somewhere
    in the architecture code and of course every arch does it different
    versus the generic bringup/teardown mechanisms.

    > Methinks Tejun needed a cc on this lot ;)

    Not really. The workqueue hotplug scheme is today one of the sanest in
    that area. Earlier versions have been a prime example of hotplug hell!

    TJ has converted it via the notifier priorities to a symetric
    startup/teardown scheme already. So the conversion is a no brainer and
    no real change.

    Sure, I should have spent the cycles to add every file owner to the cc
    list, but due to brain damage caused by decoding the current hotplug
    maze I skipped that painful exercise relying on you to fix it up for
    me :)

    Thanks,

    tglx





    \
     
     \ /
      Last update: 2013-01-31 23:42    [W:3.522 / U:0.188 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site