Messages in this thread | | | From | Waiman Long <> | Subject | [PATCH 0/5] locking/lockdep: Improve lockdep performance | Date | Fri, 28 Sep 2018 13:53:16 -0400 |
| |
Enabling CONFIG_LOCKDEP and other related debug options will greatly reduce system performance. This patchset aims to reduce the performance slowdown caused by the lockdep code.
Patch 1 just removes an inline function that wasn't used.
Patches 2 and 3 are minor twists to optimize the code.
Patch 4 makes class->ops a per-cpu counter.
Patch 5 moves the lock_release() call outside of a lock critical section.
Parallel kernel compilation tests (make -j <#cpu>) were performed on 2 different systems:
1) an 1-socket 22-core 44-thread Skylake system 2) a 4-socket 72-core 144-thread Broadwell system
The build times with pre-patch and post-patch debug kernels were:
System Pre-patch Post-patch %Change ------ --------- ---------- ------- 1-socket 8m53.9s 8m41.2s -2.4% 4-socket 7m27.0s 5m31.0s -26%
I think it is the last 2 patches that yield most of the performance improvement.
Waiman Long (5): locking/lockdep: Remove add_chain_cache_classes() locking/lockdep: Eliminate redundant irqs check in __lock_acquire() locking/lockdep: Add a faster path in __lock_release() locking/lockdep: Make class->ops a percpu counter locking/lockdep: Call lock_release after releasing the lock
include/linux/lockdep.h | 2 +- include/linux/rwlock_api_smp.h | 16 +++--- include/linux/spinlock_api_smp.h | 8 +-- kernel/locking/lockdep.c | 120 ++++++++++++--------------------------- 4 files changed, 48 insertions(+), 98 deletions(-)
-- 1.8.3.1
| |