[PATCH 1/11] maps3: add proportional set size accounting in smaps

[Matt Mackall <mpm@selenic.com>]

From: Fengguang Wu <wfg@mail.ustc.edu.cn>

The "proportional set size" (PSS) of a process is the count of pages it has
in memory, where each page is divided by the number of processes sharing
it.  So if a process has 1000 pages all to itself, and 1000 shared with one
other process, its PSS will be 1500.

               - lwn.net: "ELC: How much memory are applications really using?"

The PSS proposed by Matt Mackall is a very nice metic for measuring an
process's memory footprint.  So collect and export it via
/proc/<pid>/smaps.

Matt Mackall's pagemap/kpagemap and John Berthels's exmap can also do the
job.  They are comprehensive tools.  But for PSS, let's do it in the simple
way.

Cc: John Berthels <jjberthels@gmail.com>
Cc: Bernardo Innocenti <bernie@codewiz.org>
Cc: Padraig Brady <P@draigBrady.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Cc: Hugh Dickins <hugh@veritas.com>
---

 fs/proc/task_mmu.c |   29 ++++++++++++++++++++++++++++-
 1 files changed, 28 insertions(+), 1 deletion(-)

Index: l/fs/proc/task_mmu.c
===================================================================
--- l.orig/fs/proc/task_mmu.c	2007-10-14 13:35:31.000000000 -0500
+++ l/fs/proc/task_mmu.c	2007-10-14 13:36:56.000000000 -0500
@@ -122,6 +122,27 @@ struct mem_size_stats
 	unsigned long private_clean;
 	unsigned long private_dirty;
 	unsigned long referenced;
+
+	/*
+	 * Proportional Set Size(PSS): my share of RSS.
+	 *
+	 * PSS of a process is the count of pages it has in memory, where each
+	 * page is divided by the number of processes sharing it.  So if a
+	 * process has 1000 pages all to itself, and 1000 shared with one other
+	 * process, its PSS will be 1500.               - Matt Mackall, lwn.net
+	 */
+	u64 	      pss;
+	/*
+	 * To keep (accumulated) division errors low, we adopt 64bit pss and
+	 * use some low bits for division errors. So (pss >> PSS_DIV_BITS)
+	 * would be the real byte count.
+	 *
+	 * A shift of 12 before division means(assuming 4K page size):
+	 * 	- 1M 3-user-pages add up to 8KB errors;
+	 * 	- supports mapcount up to 2^24, or 16M;
+	 * 	- supports PSS up to 2^52 bytes, or 4PB.
+	 */
+#define PSS_DIV_BITS	12
 };
 
 struct pmd_walker {
@@ -195,6 +216,7 @@ static int show_map_internal(struct seq_
 		seq_printf(m,
 			   "Size:           %8lu kB\n"
 			   "Rss:            %8lu kB\n"
+			   "Pss:            %8lu kB\n"
 			   "Shared_Clean:   %8lu kB\n"
 			   "Shared_Dirty:   %8lu kB\n"
 			   "Private_Clean:  %8lu kB\n"
@@ -202,6 +224,7 @@ static int show_map_internal(struct seq_
 			   "Referenced:     %8lu kB\n",
 			   (vma->vm_end - vma->vm_start) >> 10,
 			   mss->resident >> 10,
+			   (unsigned long)(mss.pss >> (10 + PSS_DIV_BITS)),
 			   mss->shared_clean  >> 10,
 			   mss->shared_dirty  >> 10,
 			   mss->private_clean >> 10,
@@ -226,6 +249,7 @@ static void smaps_pte_range(struct vm_ar
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
+	int mapcount;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
@@ -242,16 +266,19 @@ static void smaps_pte_range(struct vm_ar
 		/* Accumulate the size in pages that have been accessed. */
 		if (pte_young(ptent) || PageReferenced(page))
 			mss->referenced += PAGE_SIZE;
-		if (page_mapcount(page) >= 2) {
+		mapcount = page_mapcount(page);
+		if (mapcount >= 2) {
 			if (pte_dirty(ptent))
 				mss->shared_dirty += PAGE_SIZE;
 			else
 				mss->shared_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_DIV_BITS) / mapcount;
 		} else {
 			if (pte_dirty(ptent))
 				mss->private_dirty += PAGE_SIZE;
 			else
 				mss->private_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_DIV_BITS);
 		}
 	}
 	pte_unmap_unlock(pte - 1, ptl);