[patch 051/135] mm: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Jia He <jia.he@xxxxxxxxxxxxxxxx>
Subject: mm: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn

b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns where
possible") optimized the loop in memmap_init_zone().  But there is still
some room for improvement.

E.g.  if pfn and pfn+1 are in the same memblock region, we can simply
pfn++ instead of doing the binary search in memblock_next_valid_pfn.

Furthermore, if the pfn is in a gap of two memory region, skip to next
region directly if possible.

Attached the memblock region information in my server.
[    0.000000] Zone ranges:
[    0.000000]   DMA32    [mem 0x0000000000200000-0x00000000ffffffff]
[    0.000000]   Normal   [mem 0x0000000100000000-0x00000017ffffffff]
[    0.000000] Movable zone start for each node
[    0.000000] Early memory node ranges
[    0.000000]   node   0: [mem 0x0000000000200000-0x000000000021ffff]
[    0.000000]   node   0: [mem 0x0000000000820000-0x000000000307ffff]
[    0.000000]   node   0: [mem 0x0000000003080000-0x000000000308ffff]
[    0.000000]   node   0: [mem 0x0000000003090000-0x00000000031fffff]
[    0.000000]   node   0: [mem 0x0000000003200000-0x00000000033fffff]
[    0.000000]   node   0: [mem 0x0000000003410000-0x00000000034fffff]
[    0.000000]   node   0: [mem 0x0000000003500000-0x000000000351ffff]
[    0.000000]   node   0: [mem 0x0000000003520000-0x000000000353ffff]
[    0.000000]   node   0: [mem 0x0000000003540000-0x0000000003e3ffff]
[    0.000000]   node   0: [mem 0x0000000003e40000-0x0000000003e7ffff]
[    0.000000]   node   0: [mem 0x0000000003e80000-0x0000000003ecffff]
[    0.000000]   node   0: [mem 0x0000000003ed0000-0x0000000003ed5fff]
[    0.000000]   node   0: [mem 0x0000000003ed6000-0x0000000006eeafff]
[    0.000000]   node   0: [mem 0x0000000006eeb000-0x000000000710ffff]
[    0.000000]   node   0: [mem 0x0000000007110000-0x0000000007f0ffff]
[    0.000000]   node   0: [mem 0x0000000007f10000-0x0000000007faffff]
[    0.000000]   node   0: [mem 0x0000000007fb0000-0x000000000806ffff]
[    0.000000]   node   0: [mem 0x0000000008070000-0x00000000080affff]
[    0.000000]   node   0: [mem 0x00000000080b0000-0x000000000832ffff]
[    0.000000]   node   0: [mem 0x0000000008330000-0x000000000836ffff]
[    0.000000]   node   0: [mem 0x0000000008370000-0x000000000838ffff]
[    0.000000]   node   0: [mem 0x0000000008390000-0x00000000083a9fff]
[    0.000000]   node   0: [mem 0x00000000083aa000-0x00000000083bbfff]
[    0.000000]   node   0: [mem 0x00000000083bc000-0x00000000083fffff]
[    0.000000]   node   0: [mem 0x0000000008400000-0x000000000841ffff]
[    0.000000]   node   0: [mem 0x0000000008420000-0x000000000843ffff]
[    0.000000]   node   0: [mem 0x0000000008440000-0x000000000865ffff]
[    0.000000]   node   0: [mem 0x0000000008660000-0x000000000869ffff]
[    0.000000]   node   0: [mem 0x00000000086a0000-0x00000000086affff]
[    0.000000]   node   0: [mem 0x00000000086b0000-0x00000000086effff]
[    0.000000]   node   0: [mem 0x00000000086f0000-0x0000000008b6ffff]
[    0.000000]   node   0: [mem 0x0000000008b70000-0x0000000008bbffff]
[    0.000000]   node   0: [mem 0x0000000008bc0000-0x0000000008edffff]
[    0.000000]   node   0: [mem 0x0000000008ee0000-0x0000000008ee0fff]
[    0.000000]   node   0: [mem 0x0000000008ee1000-0x0000000008ee2fff]
[    0.000000]   node   0: [mem 0x0000000008ee3000-0x000000000decffff]
[    0.000000]   node   0: [mem 0x000000000ded0000-0x000000000defffff]
[    0.000000]   node   0: [mem 0x000000000df00000-0x000000000fffffff]
[    0.000000]   node   0: [mem 0x0000000010800000-0x0000000017feffff]
[    0.000000]   node   0: [mem 0x000000001c000000-0x000000001c00ffff]
[    0.000000]   node   0: [mem 0x000000001c010000-0x000000001c7fffff]
[    0.000000]   node   0: [mem 0x000000001c810000-0x000000007efbffff]
[    0.000000]   node   0: [mem 0x000000007efc0000-0x000000007efdffff]
[    0.000000]   node   0: [mem 0x000000007efe0000-0x000000007efeffff]
[    0.000000]   node   0: [mem 0x000000007eff0000-0x000000007effffff]
[    0.000000]   node   0: [mem 0x000000007f000000-0x00000017ffffffff]
[    0.000000] Initmem setup node 0 [mem
0x0000000000200000-0x00000017ffffffff]
[    0.000000] On node 0 totalpages: 25145296
[    0.000000]   DMA32 zone: 16376 pages used for memmap
[    0.000000]   DMA32 zone: 0 pages reserved
[    0.000000]   DMA32 zone: 1028048 pages, LIFO batch:31
[    0.000000]   Normal zone: 376832 pages used for memmap
[    0.000000]   Normal zone: 24117248 pages, LIFO batch:31

Link: http://lkml.kernel.org/r/1534907237-2982-4-git-send-email-jia.he@xxxxxxxxxxxxxxxx
Signed-off-by: Jia He <jia.he@xxxxxxxxxxxxxxxx>
Reviewed-by: Pavel Tatashin <pavel.tatashin@xxxxxxxxxxxxx>
Cc: AKASHI Takahiro <takahiro.akashi@xxxxxxxxxx>
Cc: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Cc: Daniel Vacek <neelx@xxxxxxxxxx>
Cc: Eugeniu Rosca <erosca@xxxxxxxxxxxxxx>
Cc: Gioh Kim <gi-oh.kim@xxxxxxxxxxxxxxxx>
Cc: James Morse <james.morse@xxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Kemi Wang <kemi.wang@xxxxxxxxx>
Cc: Laura Abbott <labbott@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Nikolay Borisov <nborisov@xxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Petr Tesarik <ptesarik@xxxxxxxx>
Cc: Philip Derrin <philip@cog.systems>
Cc: Russell King <linux@xxxxxxxxxxxxxxx>
Cc: Steve Capper <steve.capper@xxxxxxx>
Cc: Vladimir Murzin <vladimir.murzin@xxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Wei Yang <richard.weiyang@xxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: YASUAKI ISHIMATSU <yasu.isimatu@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

 mm/memblock.c |   33 +++++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

--- a/mm/memblock.c~mm-page_alloc-reduce-unnecessary-binary-search-in-memblock_next_valid_pfn
+++ a/mm/memblock.c
@@ -1235,28 +1235,49 @@ int __init_memblock memblock_set_node(ph
 unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
 {
 	struct memblock_type *type = &memblock.memory;
+	struct memblock_region *regions = type->regions;
 	unsigned int right = type->cnt;
 	unsigned int mid, left = 0;
+	unsigned long start_pfn, end_pfn, next_start_pfn;
 	phys_addr_t addr = PFN_PHYS(++pfn);
+	static int early_region_idx __initdata_memblock = -1;
 
+	/* fast path, return pfn+1 if next pfn is in the same region */
+	if (early_region_idx != -1) {
+		start_pfn = PFN_DOWN(regions[early_region_idx].base);
+		end_pfn = PFN_DOWN(regions[early_region_idx].base +
+				regions[early_region_idx].size);
+
+		if (pfn >= start_pfn && pfn < end_pfn)
+			return pfn;
+
+		early_region_idx++;
+		next_start_pfn = PFN_DOWN(regions[early_region_idx].base);
+
+		if (pfn >= end_pfn && pfn <= next_start_pfn)
+			return next_start_pfn;
+	}
+
+	/* slow path, do the binary searching */
 	do {
 		mid = (right + left) / 2;
 
-		if (addr < type->regions[mid].base)
+		if (addr < regions[mid].base)
 			right = mid;
-		else if (addr >= (type->regions[mid].base +
-				  type->regions[mid].size))
+		else if (addr >= (regions[mid].base + regions[mid].size))
 			left = mid + 1;
 		else {
-			/* addr is within the region, so pfn is valid */
+			early_region_idx = mid;
 			return pfn;
 		}
 	} while (left < right);
 
 	if (right == type->cnt)
 		return -1UL;
-	else
-		return PHYS_PFN(type->regions[right].base);
+
+	early_region_idx = right;
+
+	return PHYS_PFN(regions[early_region_idx].base);
 }
 EXPORT_SYMBOL(memblock_next_valid_pfn);
 #endif /*CONFIG_HAVE_MEMBLOCK_PFN_VALID*/
_



[Index of Archives]     [Kernel Archive]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]

  Powered by Linux