[PATCH] mm: tune the page allocator thresholds

without patch:
      pages_min   pages_low   pages_high
dma        4          8          12
normal   234        468         702
high     128        256         384

with patch:
      pages_min   pages_low   pages_high
dma       17         21          25
normal   939       1173        1408
high     128        160         192

without patch:
                             | GFP_KERNEL        | GFP_ATOMIC
allocate immediately         |   9 dma, 469 norm |  9 dma, 469 norm
allocate after waking kswapd |   5 dma, 234 norm |  3 dma,  88 norm
allocate after synch reclaim |   5 dma, 234 norm |  n/a

with patch:
                             | GFP_KERNEL         | GFP_ATOMIC
allocate immediately         |  22 dma, 1174 norm | 22 dma, 1174 norm
allocate after waking kswapd |  18 dma,  940 norm |  6 dma,  440 norm
allocate after synch reclaim |  18 dma,  940 norm |  n/a

So the buffer between GFP_KERNEL and GFP_ATOMIC allocations is:

2.6.8      | 465 dma, 117 norm, 582 tot = 2328K
2.6.10-rc  |   2 dma, 146 norm, 148 tot =  592K
patch      |  12 dma, 500 norm, 512 tot = 2048K

Which is getting pretty good.

kswap starts at:
2.6.8     477 dma, 496 norm, 973 total
2.6.10-rc   8 dma, 468 norm, 476 total
patched    17 dma, 939 norm, 956 total

So in terms of total pages, that's looking similar to 2.6.8.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

mm/page_alloc.c

@@ -1945,8 +1945,12 @@ static void setup_per_zone_pages_min(void)
 			                   lowmem_pages;
 		}
 
-		zone->pages_low = zone->pages_min * 2;
-		zone->pages_high = zone->pages_min * 3;
+		/*
+		 * When interpreting these watermarks, just keep in mind that:
+		 * zone->pages_min == (zone->pages_min * 4) / 4;
+		 */
+		zone->pages_low   = (zone->pages_min * 5) / 4;
+		zone->pages_high  = (zone->pages_min * 6) / 4;
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 	}
 }
@@ -1955,24 +1959,25 @@ static void setup_per_zone_pages_min(void)
  * Initialise min_free_kbytes.
  *
  * For small machines we want it small (128k min).  For large machines
- * we want it large (16MB max).  But it is not linear, because network
+ * we want it large (64MB max).  But it is not linear, because network
  * bandwidth does not increase linearly with machine size.  We use
  *
- *	min_free_kbytes = sqrt(lowmem_kbytes)
+ * 	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
+ *	min_free_kbytes = sqrt(lowmem_kbytes * 16)
  *
  * which yields
  *
- * 16MB:	128k
- * 32MB:	181k
- * 64MB:	256k
- * 128MB:	362k
- * 256MB:	512k
- * 512MB:	724k
- * 1024MB:	1024k
- * 2048MB:	1448k
- * 4096MB:	2048k
- * 8192MB:	2896k
- * 16384MB:	4096k
+ * 16MB:	512k
+ * 32MB:	724k
+ * 64MB:	1024k
+ * 128MB:	1448k
+ * 256MB:	2048k
+ * 512MB:	2896k
+ * 1024MB:	4096k
+ * 2048MB:	5792k
+ * 4096MB:	8192k
+ * 8192MB:	11584k
+ * 16384MB:	16384k
  */
 static int __init init_per_zone_pages_min(void)
 {
@@ -1980,11 +1985,11 @@ static int __init init_per_zone_pages_min(void)
 
 	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
 
-	min_free_kbytes = int_sqrt(lowmem_kbytes);
+	min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
 	if (min_free_kbytes < 128)
 		min_free_kbytes = 128;
-	if (min_free_kbytes > 16384)
-		min_free_kbytes = 16384;
+	if (min_free_kbytes > 65536)
+		min_free_kbytes = 65536;
 	setup_per_zone_pages_min();
 	setup_per_zone_protection();
 	return 0;