tracing/function-graph-tracer: use the more lightweight local clock

Impact: decrease hangs risks with the graph tracer on slow systems

Since the function graph tracer can spend too much time on timer
interrupts, it's better now to use the more lightweight local
clock. Anyway, the function graph traces are more reliable on a
per cpu trace.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <49af243d.06e9300a.53ad.ffff840c@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Frederic Weisbecker 2009-03-05 01:49:22 +01:00 committed by Ingo Molnar
parent c4ef144a9d
commit 0012693ad4
3 changed files with 9 additions and 8 deletions

View file

@ -112,7 +112,7 @@ unsigned long ftrace_return_to_handler(void)
unsigned long ret;
ftrace_pop_return_trace(&trace, &ret);
trace.rettime = cpu_clock(raw_smp_processor_id());
trace.rettime = trace_clock_local();
ftrace_graph_return(&trace);
if (unlikely(!ret)) {