This patchset adds an option to enable more aggressive optimistic spinning on both readers and writers waiting on a writer or reader owned lock. Spinning on writer is done by looking at the on_cpu flag of the lock owner. Spinning on readers, on the other hand, is count-based as there is no easy way to figure out if all the readers are running. The spinner will stop spinning once the count goes to 0. Because of that, spinning on readers may hurt performance in some cases. So this feature is optional and has to explicitly enabled for those rwsems where the readers are unlikely to go to sleep. Patch 1 reduces the length of the blocking window after a read locking attempt where writer lock stealing is disabled because of the active read lock. It can improve rwsem performance for contended lock. It is independent of the rest of the patchset. Patches 2-5 lays the groundwork for enabling reader optimistic spinning. Patch 6 enables reader optimistic spinning in XFS for inodes that comes from a DAX-enabled mount point on top of persistent memory as the CPUs can do I/O directly without waiting or sleeping. Waiman Long (6): locking/rwsem: Stop active read lock ASAP locking/rwsem: Enable optional count-based spinning on reader locking/rwsem: move down rwsem_down_read_failed function locking/rwsem: Change RWSEM_WAITING_BIAS for better disambiguation locking/rwsem: Enable spinning readers xfs: Enable reader optimistic spinning for DAX inodes arch/alpha/include/asm/rwsem.h | 7 +- arch/ia64/include/asm/rwsem.h | 6 +- arch/s390/include/asm/rwsem.h | 6 +- arch/x86/include/asm/rwsem.h | 13 ++- fs/xfs/xfs_icache.c | 9 ++ include/asm-generic/rwsem.h | 9 +- include/linux/rwsem.h | 21 ++++- kernel/locking/rwsem-xadd.c | 212 ++++++++++++++++++++++++++-------------- 8 files changed, 192 insertions(+), 91 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
![]() |