[PATCH] mm: emit tracepoint when RSS changes by threshold

[Joel Fernandes (Google)]

Useful to track how RSS is changing per TGID. Several Android teams have
been using this patch in various kernel trees for half a year now. Many
reported to me it is really useful.

Initial patch developed by Tim Murray. Changes I made from original patch:
o Prevent any additional space consumed by mm_struct.
o Keep overhead low by checking if tracing is enabled.
o Add some noise reduction and lower overhead by emitting only on
  threshold changes.

Co-developed-by: Tim Murray <timmurray@xxxxxxxxxx>
Signed-off-by: Tim Murray <timmurray@xxxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>

---

Cc: carmenjackson@xxxxxxxxxx
Cc: mayankgupta@xxxxxxxxxx
Cc: dancol@xxxxxxxxxx
Cc: rostedt@xxxxxxxxxxx
Cc: minchan@xxxxxxxxxx
Cc: akpm@xxxxxxxxxxxxxxxxxxxx
Cc: kernel-team@xxxxxxxxxxx

 include/linux/mm.h          | 14 +++++++++++---
 include/trace/events/kmem.h | 21 +++++++++++++++++++++
 mm/memory.c                 | 20 ++++++++++++++++++++
 3 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0334ca97c584..823aaf759bdb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1671,19 +1671,27 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 	return (unsigned long)val;
 }
 
+void mm_trace_rss_stat(int member, long count, long value);
+
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
 {
-	atomic_long_add(value, &mm->rss_stat.count[member]);
+	long count = atomic_long_add_return(value, &mm->rss_stat.count[member]);
+
+	mm_trace_rss_stat(member, count, value);
 }
 
 static inline void inc_mm_counter(struct mm_struct *mm, int member)
 {
-	atomic_long_inc(&mm->rss_stat.count[member]);
+	long count = atomic_long_inc_return(&mm->rss_stat.count[member]);
+
+	mm_trace_rss_stat(member, count, 1);
 }
 
 static inline void dec_mm_counter(struct mm_struct *mm, int member)
 {
-	atomic_long_dec(&mm->rss_stat.count[member]);
+	long count = atomic_long_dec_return(&mm->rss_stat.count[member]);
+
+	mm_trace_rss_stat(member, count, -1);
 }
 
 /* Optimized variant when page is already known not to be PageAnon */
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index eb57e3037deb..8b88e04fafbf 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -315,6 +315,27 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->change_ownership)
 );
 
+TRACE_EVENT(rss_stat,
+
+	TP_PROTO(int member,
+		long count),
+
+	TP_ARGS(member, count),
+
+	TP_STRUCT__entry(
+		__field(int, member)
+		__field(long, size)
+	),
+
+	TP_fast_assign(
+		__entry->member = member;
+		__entry->size = (count << PAGE_SHIFT);
+	),
+
+	TP_printk("member=%d size=%ldB",
+		__entry->member,
+		__entry->size)
+	);
 #endif /* _TRACE_KMEM_H */
 
 /* This part must be outside protection */
diff --git a/mm/memory.c b/mm/memory.c
index e2bb51b6242e..9d81322c24a3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -72,6 +72,8 @@
 #include <linux/oom.h>
 #include <linux/numa.h>
 
+#include <trace/events/kmem.h>
+
 #include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
@@ -140,6 +142,24 @@ static int __init init_zero_pfn(void)
 }
 core_initcall(init_zero_pfn);
 
+/*
+ * This threshold is the boundary in the value space, that the counter has to
+ * advance before we trace it. Should be a power of 2. It is to reduce unwanted
+ * trace overhead. The counter is in units of number of pages.
+ */
+#define TRACE_MM_COUNTER_THRESHOLD 128
+
+void mm_trace_rss_stat(int member, long count, long value)
+{
+	long thresh_mask = ~(TRACE_MM_COUNTER_THRESHOLD - 1);
+
+	if (!trace_rss_stat_enabled())
+		return;
+
+	/* Threshold roll-over, trace it */
+	if ((count & thresh_mask) != ((count - value) & thresh_mask))
+		trace_rss_stat(member, count);
+}
 
 #if defined(SPLIT_RSS_COUNTING)
 
-- 
2.23.0.187.g17f5b7556c-goog