sched: add tracepoints related to NUMA task migration

This patch adds three tracepoints
 o trace_sched_move_numa	when a task is moved to a node
 o trace_sched_swap_numa	when a task is swapped with another task
 o trace_sched_stick_numa	when a numa-related migration fails

The tracepoints allow the NUMA scheduler activity to be monitored and the
following high-level metrics can be calculated

 o NUMA migrated stuck	 nr trace_sched_stick_numa
 o NUMA migrated idle	 nr trace_sched_move_numa
 o NUMA migrated swapped nr trace_sched_swap_numa
 o NUMA local swapped	 trace_sched_swap_numa src_nid == dst_nid (should never happen)
 o NUMA remote swapped	 trace_sched_swap_numa src_nid != dst_nid (should == NUMA migrated swapped)
 o NUMA group swapped	 trace_sched_swap_numa src_ngid == dst_ngid
			 Maybe a small number of these are acceptable
			 but a high number would be a major surprise.
			 It would be even worse if bounces are frequent.
 o NUMA avg task migs.	 Average number of migrations for tasks
 o NUMA stddev task mig	 Self-explanatory
 o NUMA max task migs.	 Maximum number of migrations for a single task

In general the intent of the tracepoints is to help diagnose problems
where automatic NUMA balancing appears to be doing an excessive amount
of useless work.

[akpm@linux-foundation.org: remove semicolon-after-if, repair coding-style]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Alex Thorlton <athorlton@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 87 insertions, 0 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 04c308413a5d..67e1bbf83695 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -443,6 +443,93 @@ TRACE_EVENT(sched_process_hang,
 );
 #endif /* CONFIG_DETECT_HUNG_TASK */
 
+DECLARE_EVENT_CLASS(sched_move_task_template,
+
+        TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+        TP_ARGS(tsk, src_cpu, dst_cpu),
+
+        TP_STRUCT__entry(
+                __field( pid_t, pid                     )
+                __field( pid_t, tgid                    )
+                __field( pid_t, ngid                    )
+                __field( int,   src_cpu                 )
+                __field( int,   src_nid                 )
+                __field( int,   dst_cpu                 )
+                __field( int,   dst_nid                 )
+        ),
+
+        TP_fast_assign(
+                __entry->pid            = task_pid_nr(tsk);
+                __entry->tgid           = task_tgid_nr(tsk);
+                __entry->ngid           = task_numa_group_id(tsk);
+                __entry->src_cpu        = src_cpu;
+                __entry->src_nid        = cpu_to_node(src_cpu);
+                __entry->dst_cpu        = dst_cpu;
+                __entry->dst_nid        = cpu_to_node(dst_cpu);
+        ),
+
+        TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d",
+                        __entry->pid, __entry->tgid, __entry->ngid,
+                        __entry->src_cpu, __entry->src_nid,
+                        __entry->dst_cpu, __entry->dst_nid)
+);
+
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes
+ */
+DEFINE_EVENT(sched_move_task_template, sched_move_numa,
+        TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+        TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
+        TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+        TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+TRACE_EVENT(sched_swap_numa,
+
+        TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+                 struct task_struct *dst_tsk, int dst_cpu),
+
+        TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu),
+
+        TP_STRUCT__entry(
+                __field( pid_t, src_pid                 )
+                __field( pid_t, src_tgid                )
+                __field( pid_t, src_ngid                )
+                __field( int,   src_cpu                 )
+                __field( int,   src_nid                 )
+                __field( pid_t, dst_pid                 )
+                __field( pid_t, dst_tgid                )
+                __field( pid_t, dst_ngid                )
+                __field( int,   dst_cpu                 )
+                __field( int,   dst_nid                 )
+        ),
+
+        TP_fast_assign(
+                __entry->src_pid        = task_pid_nr(src_tsk);
+                __entry->src_tgid       = task_tgid_nr(src_tsk);
+                __entry->src_ngid       = task_numa_group_id(src_tsk);
+                __entry->src_cpu        = src_cpu;
+                __entry->src_nid        = cpu_to_node(src_cpu);
+                __entry->dst_pid        = task_pid_nr(dst_tsk);
+                __entry->dst_tgid       = task_tgid_nr(dst_tsk);
+                __entry->dst_ngid       = task_numa_group_id(dst_tsk);
+                __entry->dst_cpu        = dst_cpu;
+                __entry->dst_nid        = cpu_to_node(dst_cpu);
+        ),
+
+        TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
+                        __entry->src_pid, __entry->src_tgid, __entry->src_ngid,
+                        __entry->src_cpu, __entry->src_nid,
+                        __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
+                        __entry->dst_cpu, __entry->dst_nid)
+);
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */