From: Mathieu Desnoyers Date: Sat, 16 Jul 2016 17:48:09 +0000 (-0400) Subject: Performance: remove rcu read lock from ring buffer get/put cpu X-Git-Tag: v2.9.0-rc1~21 X-Git-Url: https://git.lttng.org./?a=commitdiff_plain;h=36cb884cbb186c5b280f3427066294a2350a944a;p=lttng-ust.git Performance: remove rcu read lock from ring buffer get/put cpu The tracepoints are already protected by a RCU-bp read-side lock, so trying to take this nested lock is useless. We gain 132 ns/event on the ARM32 Cubietruck by removing this nested rcu read-side lock. Signed-off-by: Mathieu Desnoyers --- diff --git a/libringbuffer/frontend_api.h b/libringbuffer/frontend_api.h index 56dbef2a..77a26918 100644 --- a/libringbuffer/frontend_api.h +++ b/libringbuffer/frontend_api.h @@ -37,10 +37,10 @@ /** * lib_ring_buffer_get_cpu - Precedes ring buffer reserve/commit. * - * Grabs RCU read-side lock and keeps a ring buffer nesting count as - * supplementary safety net to ensure tracer client code will never - * trigger an endless recursion. Returns the processor ID on success, - * -EPERM on failure (nesting count too high). + * Keeps a ring buffer nesting count as supplementary safety net to + * ensure tracer client code will never trigger an endless recursion. + * Returns the processor ID on success, -EPERM on failure (nesting count + * too high). * * asm volatile and "memory" clobber prevent the compiler from moving * instructions out of the ring buffer nesting count. This is required to ensure @@ -53,7 +53,6 @@ int lib_ring_buffer_get_cpu(const struct lttng_ust_lib_ring_buffer_config *confi { int cpu, nesting; - rcu_read_lock(); cpu = lttng_ust_get_cpu(); nesting = ++URCU_TLS(lib_ring_buffer_nesting); cmm_barrier(); @@ -75,7 +74,6 @@ void lib_ring_buffer_put_cpu(const struct lttng_ust_lib_ring_buffer_config *conf { cmm_barrier(); URCU_TLS(lib_ring_buffer_nesting)--; /* TLS */ - rcu_read_unlock(); } /*