From d027e6a9c83440bf1ca9e5503539d58d8e0914f1 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 6 Aug 2013 18:08:47 +0200 Subject: [PATCH] tracing/perf: Avoid perf_trace_buf_*() in perf_trace_##call() when possible perf_trace_buf_prepare() + perf_trace_buf_submit(task => NULL) make no sense if hlist_empty(head). Change perf_trace_##call() to check ->perf_events beforehand and do nothing if it is empty. This removes the overhead for tasks without events associated with them. For example, "perf record -e sched:sched_switch -p1" attaches the counter(s) to the single task, but every task in system will do perf_trace_buf_prepare/submit() just to realize that it was not attached to this event. However, we can only do this if __task == NULL, so we also add the __builtin_constant_p(__task) check. With this patch "perf bench sched pipe" shows approximately 4% improvement when "perf record -p1" runs in parallel, many thanks to Steven for the testing. Link: http://lkml.kernel.org/r/20130806160847.GA2746@redhat.com Tested-by: David Ahern Acked-by: Peter Zijlstra Signed-off-by: Oleg Nesterov Signed-off-by: Steven Rostedt --- include/trace/ftrace.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 4163d93ccf38..5c7ab17cbb02 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -667,6 +667,12 @@ perf_trace_##call(void *__data, proto) \ int rctx; \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ + \ + head = this_cpu_ptr(event_call->perf_events); \ + if (__builtin_constant_p(!__task) && !__task && \ + hlist_empty(head)) \ + return; \ + \ __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\ sizeof(u64)); \ __entry_size -= sizeof(u32); \ @@ -681,7 +687,6 @@ perf_trace_##call(void *__data, proto) \ \ { assign; } \ \ - head = this_cpu_ptr(event_call->perf_events); \ perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ __count, &__regs, head, __task); \ } -- 2.11.0