Re: [patch] mm: speedup in __early_pfn_to_nid

[Yinghai Lu <yinghai@kernel.org>]

[-- Attachment #1: Type: text/plain, Size: 4440 bytes --]

On Sat, Mar 23, 2013 at 8:29 AM, Russ Anderson <rja@sgi.com> wrote:
> On Fri, Mar 22, 2013 at 08:25:32AM +0100, Ingo Molnar wrote:
> ------------------------------------------------------------
> When booting on a large memory system, the kernel spends
> considerable time in memmap_init_zone() setting up memory zones.
> Analysis shows significant time spent in __early_pfn_to_nid().
>
> The routine memmap_init_zone() checks each PFN to verify the
> nid is valid.  __early_pfn_to_nid() sequentially scans the list of
> pfn ranges to find the right range and returns the nid.  This does
> not scale well.  On a 4 TB (single rack) system there are 308
> memory ranges to scan.  The higher the PFN the more time spent
> sequentially spinning through memory ranges.
>
> Since memmap_init_zone() increments pfn, it will almost always be
> looking for the same range as the previous pfn, so check that
> range first.  If it is in the same range, return that nid.
> If not, scan the list as before.
>
> A 4 TB (single rack) UV1 system takes 512 seconds to get through
> the zone code.  This performance optimization reduces the time
> by 189 seconds, a 36% improvement.
>
> A 2 TB (single rack) UV2 system goes from 212.7 seconds to 99.8 seconds,
> a 112.9 second (53%) reduction.

Interesting. but only have 308 entries in memblock...

Did you try to extend memblock_search() to search nid back?
Something like attached patch. That should save more time.

>
> Signed-off-by: Russ Anderson <rja@sgi.com>
> ---
>  arch/ia64/mm/numa.c |   15 ++++++++++++++-
>  mm/page_alloc.c     |   15 ++++++++++++++-
>  2 files changed, 28 insertions(+), 2 deletions(-)
>
> Index: linux/mm/page_alloc.c
> ===================================================================
> --- linux.orig/mm/page_alloc.c  2013-03-19 16:09:03.736450861 -0500
> +++ linux/mm/page_alloc.c       2013-03-22 17:07:43.895405617 -0500
> @@ -4161,10 +4161,23 @@ int __meminit __early_pfn_to_nid(unsigne
>  {
>         unsigned long start_pfn, end_pfn;
>         int i, nid;
> +       /*
> +          NOTE: The following SMP-unsafe globals are only used early
> +          in boot when the kernel is running single-threaded.
> +        */
> +       static unsigned long last_start_pfn, last_end_pfn;
> +       static int last_nid;
> +
> +       if (last_start_pfn <= pfn && pfn < last_end_pfn)
> +               return last_nid;
>
>         for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
> -               if (start_pfn <= pfn && pfn < end_pfn)
> +               if (start_pfn <= pfn && pfn < end_pfn) {
> +                       last_start_pfn = start_pfn;
> +                       last_end_pfn = end_pfn;
> +                       last_nid = nid;
>                         return nid;
> +               }
>         /* This is a memory hole */
>         return -1;
>  }
> Index: linux/arch/ia64/mm/numa.c
> ===================================================================
> --- linux.orig/arch/ia64/mm/numa.c      2013-02-25 15:49:44.000000000 -0600
> +++ linux/arch/ia64/mm/numa.c   2013-03-22 16:09:44.662268239 -0500
> @@ -61,13 +61,26 @@ paddr_to_nid(unsigned long paddr)
>  int __meminit __early_pfn_to_nid(unsigned long pfn)
>  {
>         int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
> +       /*
> +          NOTE: The following SMP-unsafe globals are only used early
> +          in boot when the kernel is running single-threaded.
> +       */
> +       static unsigned long last_start_pfn, last_end_pfn;

last_ssec, last_esec?


> +       static int last_nid;
> +
> +       if (section >= last_ssec && section < last_esec)
> +               return last_nid;
>
>         for (i = 0; i < num_node_memblks; i++) {
>                 ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
>                 esec = (node_memblk[i].start_paddr + node_memblk[i].size +
>                         ((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
> -               if (section >= ssec && section < esec)
> +               if (section >= ssec && section < esec) {
> +                       last_ssec = ssec;
> +                       last_esec = esec;
> +                       last_nid = node_memblk[i].nid
>                         return node_memblk[i].nid;
> +               }
>         }
>
>         return -1;
>

also looks like you forget to put IA maintainers in the To list.

may just put ia64 part in separated patch?

Thanks

Yinghai

[-- Attachment #2: memblock_search_pfn_nid.patch --]
[-- Type: application/octet-stream, Size: 2370 bytes --]

---
 include/linux/memblock.h |    2 ++
 mm/memblock.c            |   18 ++++++++++++++++++
 mm/page_alloc.c          |   14 ++++++++------
 3 files changed, 28 insertions(+), 6 deletions(-)

Index: linux-2.6/include/linux/memblock.h
===================================================================
--- linux-2.6.orig/include/linux/memblock.h
+++ linux-2.6/include/linux/memblock.h
@@ -60,6 +60,8 @@ int memblock_reserve(phys_addr_t base, p
 void memblock_trim_memory(phys_addr_t align);
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
+			    unsigned long  *end_pfn);
 void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 			  unsigned long *out_end_pfn, int *out_nid);
 
Index: linux-2.6/mm/memblock.c
===================================================================
--- linux-2.6.orig/mm/memblock.c
+++ linux-2.6/mm/memblock.c
@@ -910,6 +910,24 @@ int __init_memblock memblock_is_memory(p
 	return memblock_search(&memblock.memory, addr) != -1;
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
+			 unsigned long *start_pfn, unsigned long *end_pfn)
+{
+	struct memblock_type *type = &memblock.memory;
+	int mid = memblock_search(type, (phys_addr_t)pfn << PAGE_SHIFT);
+
+	if (mid == -1)
+		return -1;
+
+	*start_pfn = type->regions[mid].base >> PAGE_SHIFT;
+	*end_pfn = (type->regions[mid].base + type->regions[mid].size)
+			>> PAGE_SHIFT;
+
+	return type->regions[mid].nid;
+}
+#endif
+
 /**
  * memblock_is_region_memory - check if a region is a subset of memory
  * @base: base of region to check
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -4160,13 +4160,15 @@ int __meminit init_currently_empty_zone(
 int __meminit __early_pfn_to_nid(unsigned long pfn)
 {
 	unsigned long start_pfn, end_pfn;
-	int i, nid;
+	int nid;
 
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
-		if (start_pfn <= pfn && pfn < end_pfn)
-			return nid;
-	/* This is a memory hole */
-	return -1;
+	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+
+	if (nid != -1) {
+	/* save start_pfn, and end_pfn ?*/
+	}
+
+	return nid;
 }
 #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */