lkml.org 
[lkml]   [2013]   [Jul]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    Subject[PATCH RFC nohz_full 0/7] v4 Provide infrastructure for full-system idle
    Whenever there is at least one non-idle CPU, it is necessary to
    periodically update timekeeping information. Before NO_HZ_FULL, this
    updating was carried out by the scheduling-clock tick, which ran on
    every non-idle CPU. With the advent of NO_HZ_FULL, it is possible
    to have non-idle CPUs that are not receiving scheduling-clock ticks.
    This possibility is handled by assigning a timekeeping CPU that continues
    taking scheduling-clock ticks.

    Unfortunately, timekeeping CPU continues taking scheduling-clock
    interrupts even when all other CPUs are completely idle, which is
    not so good for energy efficiency and battery lifetime. Clearly, it
    would be good to turn off the timekeeping CPU's scheduling-clock tick
    when all CPUs are completely idle. This is conceptually simple, but
    we also need good performance and scalability on large systems, which
    rules out implementations based on frequently updated global counts of
    non-idle CPUs as well as implementations that frequently scan all CPUs.
    Nevertheless, we need a single global indicator in order to keep the
    overhead of checking acceptably low.

    The chosen approach is to enforce hysteresis on the non-idle to
    full-system-idle transition, with the amount of hysteresis increasing
    linearly with the number of CPUs, thus keeping contention acceptably low.
    This approach piggybacks on RCU's existing force-quiescent-state scanning
    of idle CPUs, which has the advantage of avoiding the scan entirely on
    busy systems that have high levels of multiprogramming. This scan
    takes per-CPU idleness information and feeds it into a state machine
    that applies the level of hysteresis required to arrive at a single
    full-system-idle indicator.

    The individual patches are as follows:

    1. Add a CONFIG_NO_HZ_FULL_SYSIDLE Kconfig parameter to enable
    this feature. Kernels built with CONFIG_NO_HZ_FULL_SYSIDLE=n
    act exactly as they do today.

    2. Add new fields to the rcu_dynticks structure that track CPU-idle
    information. These fields consider CPUs running usermode to be
    non-idle, in contrast with the existing fields in that structure.

    3. Track per-CPU idle states.

    4. Add full-system idle states and state variables.

    5. Expand force_qs_rnp(), dyntick_save_progress_counter(), and
    rcu_implicit_dynticks_qs() APIs to enable passing full-system
    idle state information.

    6. Add full-system-idle state machine.

    7. Force RCU's grace-period kthreads onto the timekeeping CPU.

    Changes since v3 (https://lkml.org/lkml/2013/7/8/441):

    o Fix an embarrassing bug that allowed multiple kthreads to be
    executing the state machine concurrently.

    Changes since v2 (https://lkml.org/lkml/2013/6/28/610):

    o Completed removing NMI support (thanks to Frederic for spotting
    the remaining cruft).

    o Fix a state-machine bug, again spotted by Frederic. See
    http://lists-archives.com/linux-kernel/27865835-nohz_full-add-full-system-idle-state-machine.html
    for the full details of the bug.

    o Updated commit log and comment as suggested by Josh Triplett.

    Changes since v1 (https://lkml.org/lkml/2013/6/25/664):

    o Removed NMI support because NMI handlers cannot safely read
    the time anyway (thanks to Thomas Gleixner and Peter Zijlstra).

    Thanx, Paul

    ------------------------------------------------------------------------

    b/include/linux/rcupdate.h | 18 +
    b/kernel/rcutree.c | 49 ++++-
    b/kernel/rcutree.h | 17 +
    b/kernel/rcutree_plugin.h | 430 ++++++++++++++++++++++++++++++++++++++++++++-
    b/kernel/time/Kconfig | 23 ++
    5 files changed, 522 insertions(+), 15 deletions(-)



    \
     
     \ /
      Last update: 2013-07-27 01:41    [W:5.656 / U:0.436 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site