[RFC] mmaped copy too slow?

[KOSAKI Motohiro]

Hi

at one point, I found the large file copy speed was different depending on
the copy method.

I compared below method
 - read(2) and write(2).
 - mmap(2) x2 and memcpy.
 - mmap(2) and write(2).

in addition, effect of fadvice(2) and madvice(2) is checked.

to a strange thing, 
   - most faster method is read + write + fadvice.
   - worst method is mmap + memcpy.

some famous book(i.e. Advanced Programming in UNIX Environment 
by W. Richard Stevens) written mmap copy x2 faster than read-write.
but, linux doesn't.

and, I found bottleneck is page reclaim.
for comparision, I change page reclaim function a bit. and test again.


test machine:
   CPU:      Pentium4 with HT 2.8GHz
   memory:   512M
   Disk I/O: can about 20M/s transfer.
             (in other word, 1GB transfer need 50s at ideal state)


spent time of 1GB file copy.(unit is second)

                 2.6.24-rc6    2.6.24-rc6       ratio
                               +my patch        (small is faster)
    ------------------------------------------------------------
    rw_cp             59.32       58.60          98.79%
    rw_fadv_cp        57.96       57.96          100.0%
    mm_sync_cp        69.97       61.68          88.15%
    mm_sync_madv_cp   69.41       62.54          90.10%
    mw_cp             61.69       63.11         102.30%
    mw_madv_cp        61.35       61.31          99.93%

this patch is too premature and ugly.
but I think that there is enough information to discuss to 
page reclaim improvement. 

the problem is when almost page is mapped and PTE access bit on,
page reclaim process below steps.

  1) page move to inactive list -> active list
  2) page move to active list   -> inactive list
  3) really pageout

It is too roundabout and unnecessary memory pressure happend.
if you don't mind, please discuss.




Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>

---
 mm/vmscan.c |   46 +++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 43 insertions(+), 3 deletions(-)

Index: linux-2.6.24-rc6-cp3/mm/vmscan.c
===================================================================
--- linux-2.6.24-rc6-cp3.orig/mm/vmscan.c	2008-01-13 21:58:03.000000000 +0900
+++ linux-2.6.24-rc6-cp3/mm/vmscan.c	2008-01-13 22:30:27.000000000 +0900
@@ -446,13 +446,18 @@ static unsigned long shrink_page_list(st
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
 	unsigned long nr_reclaimed = 0;
+	unsigned long nr_scanned = 0;
+	LIST_HEAD(l_mapped_pages);
+	unsigned long nr_mapped_page_activate = 0;
+	struct page *page;
+	int reference_checked = 0;
 
 	cond_resched();
 
 	pagevec_init(&freed_pvec, 1);
+retry:
 	while (!list_empty(page_list)) {
 		struct address_space *mapping;
-		struct page *page;
 		int may_enter_fs;
 		int referenced;
 
@@ -466,6 +471,7 @@ static unsigned long shrink_page_list(st
 
 		VM_BUG_ON(PageActive(page));
 
+		nr_scanned++;
 		sc->nr_scanned++;
 
 		if (!sc->may_swap && page_mapped(page))
@@ -493,11 +499,17 @@ static unsigned long shrink_page_list(st
 				goto keep_locked;
 		}
 
-		referenced = page_referenced(page, 1);
-		/* In active use or really unfreeable?  Activate it. */
-		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
-					referenced && page_mapping_inuse(page))
-			goto activate_locked;
+		if (!reference_checked) {
+			referenced = page_referenced(page, 1);
+			/* In active use or really unfreeable?  Activate it. */
+			if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
+			    referenced && page_mapping_inuse(page)) {
+				nr_mapped_page_activate++;
+				unlock_page(page);
+				list_add(&page->lru, &l_mapped_pages);
+				continue;
+			}
+		}
 
 #ifdef CONFIG_SWAP
 		/*
@@ -604,7 +616,31 @@ keep:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page));
 	}
+
+	if (nr_scanned == nr_mapped_page_activate) {
+		/* may be under copy by mmap.
+		   ignore reference flag. */
+		reference_checked = 1;
+		list_splice(&l_mapped_pages, page_list);
+		goto retry;
+	} else {
+		/* move active list just now */
+		while (!list_empty(&l_mapped_pages)) {
+			page = lru_to_page(&l_mapped_pages);
+			list_del(&page->lru);
+			prefetchw_prev_lru_page(page, &l_mapped_pages, flags);
+
+			if (!TestSetPageLocked(page)) {
+				SetPageActive(page);
+				pgactivate++;
+				unlock_page(page);
+			}
+			list_add(&page->lru, &ret_pages);
+		}
+	}
+
 	list_splice(&ret_pages, page_list);
+
 	if (pagevec_count(&freed_pvec))
 		__pagevec_release_nonlru(&freed_pvec);
 	count_vm_events(PGACTIVATE, pgactivate);

Attachment: mmap-write.c
Description: Binary data

Attachment: read-write.c
Description: Binary data

Attachment: test.sh
Description: Binary data

Attachment: Makefile
Description: Binary data

Attachment: mmap-mmap.c
Description: Binary data