watchdog: add watchdog_cpumask sysctl to assist nohz
authorChris Metcalf <cmetcalf@ezchip.com>
Wed, 24 Jun 2015 23:55:45 +0000 (16:55 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Thu, 25 Jun 2015 00:49:40 +0000 (17:49 -0700)
commitfe4ba3c34352b7e8068b7f18eb233444aed17011
treed4b34e0d809e784c59eea68cb27c16dc795e371b
parentb5242e98c1cb834feb1e84026f09a4796b49eb4d
watchdog: add watchdog_cpumask sysctl to assist nohz

Change the default behavior of watchdog so it only runs on the
housekeeping cores when nohz_full is enabled at build and boot time.
Allow modifying the set of cores the watchdog is currently running on
with a new kernel.watchdog_cpumask sysctl.

In the current system, the watchdog subsystem runs a periodic timer that
schedules the watchdog kthread to run.  However, nohz_full cores are
designed to allow userspace application code running on those cores to
have 100% access to the CPU.  So the watchdog system prevents the
nohz_full application code from being able to run the way it wants to,
thus the motivation to suppress the watchdog on nohz_full cores, which
this patchset provides by default.

However, if we disable the watchdog globally, then the housekeeping
cores can't benefit from the watchdog functionality.  So we allow
disabling it only on some cores.  See Documentation/lockup-watchdogs.txt
for more information.

[jhubbard@nvidia.com: fix a watchdog crash in some configurations]
Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Documentation/lockup-watchdogs.txt
Documentation/sysctl/kernel.txt
include/linux/nmi.h
kernel/smpboot.c
kernel/sysctl.c
kernel/watchdog.c