perf/core: Add weighted samples

For some events it's useful to weight sample with a hardware provided number. This expresses how expensive the action the sample represent was. This allows the profiler to scale the samples to be more informative to the programmer. There is already the period which is used similarly, but it means something different, so I chose to not overload it. Instead a new sample type for WEIGHT is added. Can be used for multiple things. Initially it is used for TSX abort costs and profiling by memory latencies (so to make expensive load appear higher up in the histograms). The concept is quite generic and can be extended to many other kinds of events or architectures, as long as the hardware provides suitable auxillary values. In principle it could be also used for software tracepoints. This adds the generic glue. A new optional sample format for a 64-bit weight value. Signed-off-by: Andi Kleen <[email protected]> Signed-off-by: Stephane Eranian <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Ingo Molnar <[email protected]> Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
josf · Apr 1, 2013 · c3feedf · c3feedf
1 parent 9fac2cf
commit c3feedf
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 1 deletion.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
@@ -573,6 +573,7 @@ struct perf_sample_data {
 	struct perf_branch_stack	*br_stack;
 	struct perf_regs_user		regs_user;
 	u64				stack_user_size;
+	u64				weight;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -586,6 +587,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
+	data->weight = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
@@ -132,8 +132,10 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
 	PERF_SAMPLE_REGS_USER			= 1U << 12,
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+
+	PERF_SAMPLE_MAX = 1U << 15,		/* non-ABI */
 
-	PERF_SAMPLE_MAX = 1U << 14,		/* non-ABI */
 };
 
 /*
@@ -588,6 +590,8 @@ enum perf_event_type {
 	 * 	{ u64			size;
 	 * 	  char			data[size];
 	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,

diff --git a/kernel/events/core.c b/kernel/events/core.c
@@ -976,6 +976,9 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		size += sizeof(data->period);
 
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		size += sizeof(data->weight);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
 
@@ -4193,6 +4196,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 		perf_output_sample_ustack(handle,
 					  data->stack_user_size,
 					  data->regs_user.regs);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		perf_output_put(handle, data->weight);
 }
 
 void perf_prepare_sample(struct perf_event_header *header,