On Mon, Jun 30, 2025 at 04:04:30PM -0400, Steven Rostedt wrote:

On Tue, 10 Jun 2025 11:43:39 +0200
Nam Cao [off-list ref] wrote:

quoted

diff --git a/kernel/trace/rv/monitors/rtapp/Kconfig b/kernel/trace/rv/monitors/rtapp/Kconfig
new file mode 100644
index 0000000000000..658bb78e733a0
--- /dev/null
+++ b/kernel/trace/rv/monitors/rtapp/Kconfig

@@ -0,0 +1,14 @@
+config RV_MON_RTAPP
+	depends on RV
+	bool "rtapp monitor"
+	help
+	  Collection of monitors to check for common problems with real-time
+	  application that may cause unexpected latency.
+
+	  If you are developing a real-time system and not entirely sure whether
+	  the applications are designed correctly for real-time, you want to say
+	  Y here.
+
+	  Beware that enabling this may have impact on performance, even if the
+	  monitors are not running. Therefore you probably should say N for
+	  production kernel.

I'm trying to figure out from the patch how exactly does this cause
performance issues?

Can you elaborate?

Sorry for the confusion, this patch alone doesn't affect performance.

It is its child monitor which turns on CONFIG_TRACE_IRQFLAGS, which is
added in a later patch.

Let me move this paragraph to that patch instead.

Nam