[PATCH 3/3] vmscan: implement swap token priority decay

[KOSAKI Motohiro]

While testing for memcg aware swap token, I observed a swap token
was often grabbed an intermittent running process (eg init, auditd)
and they never release a token.

Why? Currently, swap toke priority is only decreased at page fault
path. Then, if the process sleep immediately after to grab swap
token, their swap token priority never be decreased. That makes
obviously undesired result.

This patch implement very poor (and lightweight) priority decay
mechanism. It only be affect to the above corner case and doesn't
change swap tendency workload performance (eg multi process qsbench
load)

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
---
 include/trace/events/vmscan.h |   12 ++++++++----
 mm/thrash.c                   |    5 ++++-
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 1798e0c..ba18137 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -366,9 +366,10 @@ DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token,

 TRACE_EVENT_CONDITION(update_swap_token_priority,
 	TP_PROTO(struct mm_struct *mm,
-		 unsigned int old_prio),
+		 unsigned int old_prio,
+		 struct mm_struct *swap_token_mm),

-	TP_ARGS(mm, old_prio),
+	TP_ARGS(mm, old_prio, swap_token_mm),

 	TP_CONDITION(mm->token_priority != old_prio),

@@ -376,16 +377,19 @@ TRACE_EVENT_CONDITION(update_swap_token_priority,
 		__field(struct mm_struct*, mm)
 		__field(unsigned int, old_prio)
 		__field(unsigned int, new_prio)
+		__field(unsigned int, token_prio)
 	),

 	TP_fast_assign(
 		__entry->mm = mm;
 		__entry->old_prio = old_prio;
 		__entry->new_prio = mm->token_priority;
+		__entry->token_prio = swap_token_mm ? swap_token_mm->token_priority : 0;
 	),

-	TP_printk("mm=%p old_prio=%u new_prio=%u",
-		  __entry->mm, __entry->old_prio, __entry->new_prio)
+	TP_printk("mm=%p old_prio=%u new_prio=%u token_prio=%u",
+		  __entry->mm, __entry->old_prio, __entry->new_prio,
+		  __entry->token_prio)
 );

 #endif /* _TRACE_VMSCAN_H */
diff --git a/mm/thrash.c b/mm/thrash.c
index 14c6c9f..0c4f0a8 100644
--- a/mm/thrash.c
+++ b/mm/thrash.c
@@ -47,6 +47,9 @@ void grab_swap_token(struct mm_struct *mm)
 	if (!swap_token_mm)
 		goto replace_token;

+	if (!(global_faults & 0xff))
+		mm->token_priority /= 2;
+
 	if (mm == swap_token_mm) {
 		mm->token_priority += 2;
 		goto update_priority;
@@ -64,7 +67,7 @@ void grab_swap_token(struct mm_struct *mm)
 		goto replace_token;

 update_priority:
-	trace_update_swap_token_priority(mm, old_prio);
+	trace_update_swap_token_priority(mm, old_prio, swap_token_mm);

 out:
 	mm->faultstamp = global_faults;
-- 
1.7.3.1



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/