vmscan: tracing: add trace event when a page is written

Add a trace event for when page reclaim queues a page for IO and records
whether it is synchronous or asynchronous.  Excessive synchronous IO for a
process can result in noticeable stalls during direct reclaim.  Excessive
IO from page reclaim may indicate that the system is seriously under
provisioned for the amount of dirty pages that exist.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michael Rubin <mrubin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 43 insertions, 0 deletions

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index c0552be1f50a..69789dc72100 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -8,6 +8,24 @@
 #include <linux/tracepoint.h>
 #include "gfpflags.h"
 
+#define RECLAIM_WB_ANON         0x0001u
+#define RECLAIM_WB_FILE         0x0002u
+#define RECLAIM_WB_SYNC         0x0004u
+#define RECLAIM_WB_ASYNC        0x0008u
+
+#define show_reclaim_flags(flags)                               \
+        (flags) ? __print_flags(flags, "|",                     \
+                {RECLAIM_WB_ANON,       "RECLAIM_WB_ANON"},     \
+                {RECLAIM_WB_FILE,       "RECLAIM_WB_FILE"},     \
+                {RECLAIM_WB_SYNC,       "RECLAIM_WB_SYNC"},     \
+                {RECLAIM_WB_ASYNC,      "RECLAIM_WB_ASYNC"}     \
+                ) : "RECLAIM_WB_NONE"
+
+#define trace_reclaim_flags(page, sync) ( \
+        (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \
+        (sync == PAGEOUT_IO_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC)   \
+        )
+
 TRACE_EVENT(mm_vmscan_kswapd_sleep,
 
         TP_PROTO(int nid),
@@ -155,6 +173,29 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
                 __entry->nr_lumpy_failed)
 );
 
+TRACE_EVENT(mm_vmscan_writepage,
+
+        TP_PROTO(struct page *page,
+                int reclaim_flags),
+
+        TP_ARGS(page, reclaim_flags),
+
+        TP_STRUCT__entry(
+                __field(struct page *, page)
+                __field(int, reclaim_flags)
+        ),
+
+        TP_fast_assign(
+                __entry->page = page;
+                __entry->reclaim_flags = reclaim_flags;
+        ),
+
+        TP_printk("page=%p pfn=%lu flags=%s",
+                __entry->page,
+                page_to_pfn(__entry->page),
+                show_reclaim_flags(__entry->reclaim_flags))
+);
+
 #endif /* _TRACE_VMSCAN_H */
 
 /* This part must be outside protection */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3d006d91a526..b7a4e6a3cf89 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -401,6 +401,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
                         /* synchronous write or broken a_ops? */
                         ClearPageReclaim(page);
                 }
+                trace_mm_vmscan_writepage(page,
+                        trace_reclaim_flags(page, sync_writeback));
                 inc_zone_page_state(page, NR_VMSCAN_WRITE);
                 return PAGE_SUCCESS;
         }