diff options
author | Manfred Spraul <manfred@colorfullife.com> | 2017-02-28 01:28:18 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-28 05:43:46 +0300 |
commit | 9de5ab8a2eeea9ae4b63b6f6353b415b93e020c0 (patch) | |
tree | cf33b34f1edcbca39139176cfe1781c41590ca3f /ipc/syscall.c | |
parent | 27d7be1801a4824ecccbc735593101d72c038f13 (diff) | |
download | linux-9de5ab8a2eeea9ae4b63b6f6353b415b93e020c0.tar.xz |
ipc/sem: add hysteresis
sysv sem has two lock modes: One with per-semaphore locks, one lock mode
with a single global lock for the whole array. When switching from the
per-semaphore locks to the global lock, all per-semaphore locks must be
scanned for ongoing operations.
The patch adds a hysteresis for switching from the global lock to the
per semaphore locks. This reduces how often the per-semaphore locks
must be scanned.
Compared to the initial patch, this is a simplified solution: Setting
USE_GLOBAL_LOCK_HYSTERESIS to 1 restores the current behavior.
In theory, a workload with exactly 10 simple sops and then one complex
op now scales a bit worse, but this is pure theory: If there is
concurrency, the it won't be exactly 10:1:10:1:10:1:... If there is no
concurrency, then there is no need for scalability.
Link: http://lkml.kernel.org/r/1476851896-3590-3-git-send-email-manfred@colorfullife.com
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: <1vier1@web.de>
Cc: kernel test robot <xiaolong.ye@intel.com>
Cc: <felixh@informatik.uni-bremen.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'ipc/syscall.c')
0 files changed, 0 insertions, 0 deletions