tracing, page-allocator: add trace events for page allocation and page freeing

This patch adds trace events for the allocation and freeing of pages,
including the freeing of pagevecs.  Using the events, it will be known
what struct page and pfns are being allocated and freed and what the call
site was in many cases.

The page alloc tracepoints be used as an indicator as to whether the
workload was heavily dependant on the page allocator or not.  You can make
a guess based on vmstat but you can't get a per-process breakdown.
Depending on the call path, the call_site for page allocation may be
__get_free_pages() instead of a useful callsite.  Instead of passing down
a return address similar to slab debugging, the user should enable the
stacktrace and seg-addr options to get a proper stack trace.

The pagevec free tracepoint has a different usecase.  It can be used to
get a idea of how many pages are being dumped off the LRU and whether it
is kswapd doing the work or a process doing direct reclaim.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Ingo Molnar <mingo@elte.hu>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Li Ming Chun <macli@brc.ubc.ca>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 1493c541f9c44566a21553c5947aa1fa93fc702e..0d358a0d45c1bbed47b272b5eb5febbe20140bef 100644 (file)
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -225,6 +225,80 @@ TRACE_EVENT(kmem_cache_free,
 
        TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
 );
+
+TRACE_EVENT(mm_page_free_direct,
+
+       TP_PROTO(struct page *page, unsigned int order),
+
+       TP_ARGS(page, order),
+
+       TP_STRUCT__entry(
+               __field(        struct page *,  page            )
+               __field(        unsigned int,   order           )
+       ),
+
+       TP_fast_assign(
+               __entry->page           = page;
+               __entry->order          = order;
+       ),
+
+       TP_printk("page=%p pfn=%lu order=%d",
+                       __entry->page,
+                       page_to_pfn(__entry->page),
+                       __entry->order)
+);
+
+TRACE_EVENT(mm_pagevec_free,
+
+       TP_PROTO(struct page *page, int cold),
+
+       TP_ARGS(page, cold),
+
+       TP_STRUCT__entry(
+               __field(        struct page *,  page            )
+               __field(        int,            cold            )
+       ),
+
+       TP_fast_assign(
+               __entry->page           = page;
+               __entry->cold           = cold;
+       ),
+
+       TP_printk("page=%p pfn=%lu order=0 cold=%d",
+                       __entry->page,
+                       page_to_pfn(__entry->page),
+                       __entry->cold)
+);
+
+TRACE_EVENT(mm_page_alloc,
+
+       TP_PROTO(struct page *page, unsigned int order,
+                       gfp_t gfp_flags, int migratetype),
+
+       TP_ARGS(page, order, gfp_flags, migratetype),
+
+       TP_STRUCT__entry(
+               __field(        struct page *,  page            )
+               __field(        unsigned int,   order           )
+               __field(        gfp_t,          gfp_flags       )
+               __field(        int,            migratetype     )
+       ),
+
+       TP_fast_assign(
+               __entry->page           = page;
+               __entry->order          = order;
+               __entry->gfp_flags      = gfp_flags;
+               __entry->migratetype    = migratetype;
+       ),
+
+       TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s",
+               __entry->page,
+               page_to_pfn(__entry->page),
+               __entry->order,
+               __entry->migratetype,
+               show_gfp_flags(__entry->gfp_flags))
+);
+
 #endif /* _TRACE_KMEM_H */
 
 /* This part must be outside protection */

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 913a8ebd3a8ebdad2ca9bea819ab2378c2b6642e..80f954d82d773f311ed66810126802865fe2b7e6 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1076,6 +1076,7 @@ static void free_hot_cold_page(struct page *page, int cold)
 
 void free_hot_page(struct page *page)
 {
+       trace_mm_page_free_direct(page, 0);
        free_hot_cold_page(page, 0);
 }
        
@@ -1920,6 +1921,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
                                zonelist, high_zoneidx, nodemask,
                                preferred_zone, migratetype);
 
+       trace_mm_page_alloc(page, order, gfp_mask, migratetype);
        return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -1954,13 +1956,16 @@ void __pagevec_free(struct pagevec *pvec)
 {
        int i = pagevec_count(pvec);
 
-       while (--i >= 0)
+       while (--i >= 0) {
+               trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
                free_hot_cold_page(pvec->pages[i], pvec->cold);
+       }
 }
 
 void __free_pages(struct page *page, unsigned int order)
 {
        if (put_page_testzero(page)) {
+               trace_mm_page_free_direct(page, order);
                if (order == 0)
                        free_hot_page(page);
                else