While testing rtla timerlat auto analysis, I reach a condition where
the interface was not receiving tracing data. I was able to manually
reproduce the problem with these steps:
# echo 0 > tracing_on # disable trace
# echo 1 > osnoise/stop_tracing_us # stop trace if timerlat irq > 1 us
# echo timerlat > current_tracer # enable timerlat tracer
# sleep 1 # wait... that is the time when rtla
# apply configs like prio or cgroup
# echo 1 > tracing_on # start tracing
# cat trace
# tracer: timerlat
#
# _-----=> irqs-off
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / _-=> migrate-disable
# |||| / delay
# ||||| ACTIVATION
# TASK-PID CPU# ||||| TIMESTAMP ID CONTEXT LATENCY
# | | | ||||| | | | |
NOTHING!
Then, trying to enable tracing again with echo 1 > tracing_on resulted
in no change: the trace was still not tracing.
This problem happens because the timerlat IRQ hits the stop tracing
condition while tracing is off, and do not wake up the timerlat thread,
so the timerlat threads are kept sleeping forever, resulting in no
trace, even after re-enabling the tracer.
Avoid this condition by always waking up the threads, even after stopping
tracing, allowing the tracer to return to its normal operating after
a new tracing on.
Cc: Steven Rostedt <[email protected]>
Cc: Daniel Bristot de Oliveira <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Fixes: a955d7eac177 ("trace: Add timerlat tracer")
Signed-off-by: Daniel Bristot de Oliveira <[email protected]>
---
kernel/trace/trace_osnoise.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index efbbec2caff8..e97e3fa5cbed 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1652,6 +1652,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
osnoise_stop_tracing();
notify_new_max_latency(diff);
+ wake_up_process(tlat->kthread);
+
return HRTIMER_NORESTART;
}
}
--
2.38.1