[PATCH] memblock, numa: Binary search node id

[PATCH] memblock, numa: Binary search node id

[Yinghai Lu]

Current early_pfn_to_nid() on arch that support memblock go
over memblock.memory one by one, so will take too many try
near the end.

We can use existing memblock_search to find the node id for
given pfn, that could save some time on bigger system that
have many entries memblock.memory array.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 include/linux/memblock.h |    2 ++
 mm/memblock.c            |   18 ++++++++++++++++++
 mm/page_alloc.c          |   19 +++++++++----------
 3 files changed, 29 insertions(+), 10 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
@@ -914,6 +914,24 @@ 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
@@ -4186,7 +4186,7 @@ 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;
 	/*
 	 * NOTE: The following SMP-unsafe globals are only used early in boot
 	 * when the kernel is running single-threaded.
@@ -4197,15 +4197,14 @@ int __meminit __early_pfn_to_nid(unsigne
 	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) {
-			last_start_pfn = start_pfn;
-			last_end_pfn = end_pfn;
-			last_nid = nid;
-			return nid;
-		}
-	/* This is a memory hole */
-	return -1;
+	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+	if (nid != -1) {
+		last_start_pfn = start_pfn;
+		last_end_pfn = end_pfn;
+		last_nid = nid;
+	}
+
+	return nid;
 }
 #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 

[PATCH] memblock, numa: Binary search node id

[Yinghai Lu]

Current early_pfn_to_nid() on arch that support memblock go
over memblock.memory one by one, so will take too many try
near the end.

We can use existing memblock_search to find the node id for
given pfn, that could save some time on bigger system that
have many entries memblock.memory array.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 include/linux/memblock.h |    2 ++
 mm/memblock.c            |   18 ++++++++++++++++++
 mm/page_alloc.c          |   19 +++++++++----------
 3 files changed, 29 insertions(+), 10 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
@@ -914,6 +914,24 @@ 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
@@ -4186,7 +4186,7 @@ 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;
 	/*
 	 * NOTE: The following SMP-unsafe globals are only used early in boot
 	 * when the kernel is running single-threaded.
@@ -4197,15 +4197,14 @@ int __meminit __early_pfn_to_nid(unsigne
 	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) {
-			last_start_pfn = start_pfn;
-			last_end_pfn = end_pfn;
-			last_nid = nid;
-			return nid;
-		}
-	/* This is a memory hole */
-	return -1;
+	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+	if (nid != -1) {
+		last_start_pfn = start_pfn;
+		last_end_pfn = end_pfn;
+		last_nid = nid;
+	}
+
+	return nid;
 }
 #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH] memblock, numa: Binary search node id

[Andrew Morton]

On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:

> Current early_pfn_to_nid() on arch that support memblock go
> over memblock.memory one by one, so will take too many try
> near the end.
> 
> We can use existing memblock_search to find the node id for
> given pfn, that could save some time on bigger system that
> have many entries memblock.memory array.

Looks nice.  I wonder how much difference it makes.
 
> ...
>
> --- 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
> @@ -914,6 +914,24 @@ 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

This function will have no callers if
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y.  That's not too bad as the
function is __init_memblock.  But this depends on
CONFIG_ARCH_DISCARD_MEMBLOCK.  Messy :(

Re: [PATCH] memblock, numa: Binary search node id

[Andrew Morton]

On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:

> Current early_pfn_to_nid() on arch that support memblock go
> over memblock.memory one by one, so will take too many try
> near the end.
> 
> We can use existing memblock_search to find the node id for
> given pfn, that could save some time on bigger system that
> have many entries memblock.memory array.

Looks nice.  I wonder how much difference it makes.
 
> ...
>
> --- 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
> @@ -914,6 +914,24 @@ 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

This function will have no callers if
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y.  That's not too bad as the
function is __init_memblock.  But this depends on
CONFIG_ARCH_DISCARD_MEMBLOCK.  Messy :(


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH] memblock, numa: Binary search node id

[Yinghai Lu]

On Thu, Aug 15, 2013 at 1:43 PM, Andrew Morton
<akpm@linux-foundation.org> wrote:
> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
>
>> Current early_pfn_to_nid() on arch that support memblock go
>> over memblock.memory one by one, so will take too many try
>> near the end.
>>
>> We can use existing memblock_search to find the node id for
>> given pfn, that could save some time on bigger system that
>> have many entries memblock.memory array.
>
> Looks nice.  I wonder how much difference it makes.

Russ said he would test on his 256 nodes system, but looks he never
got chance.

Thanks

Yinghai

Re: [PATCH] memblock, numa: Binary search node id

[Yinghai Lu]

On Thu, Aug 15, 2013 at 1:43 PM, Andrew Morton
<akpm@linux-foundation.org> wrote:
> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
>
>> Current early_pfn_to_nid() on arch that support memblock go
>> over memblock.memory one by one, so will take too many try
>> near the end.
>>
>> We can use existing memblock_search to find the node id for
>> given pfn, that could save some time on bigger system that
>> have many entries memblock.memory array.
>
> Looks nice.  I wonder how much difference it makes.

Russ said he would test on his 256 nodes system, but looks he never
got chance.

Thanks

Yinghai

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH] memblock, numa: Binary search node id

[Russ Anderson]

On Thu, Aug 15, 2013 at 02:06:44PM -0700, Yinghai Lu wrote:
> On Thu, Aug 15, 2013 at 1:43 PM, Andrew Morton
> <akpm@linux-foundation.org> wrote:
> > On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
> >
> >> Current early_pfn_to_nid() on arch that support memblock go
> >> over memblock.memory one by one, so will take too many try
> >> near the end.
> >>
> >> We can use existing memblock_search to find the node id for
> >> given pfn, that could save some time on bigger system that
> >> have many entries memblock.memory array.
> >
> > Looks nice.  I wonder how much difference it makes.
> 
> Russ said he would test on his 256 nodes system, but looks he never
> got chance.

I reserved time tonight on a couple big systems to measure
the performance difference.

Thanks,
-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

Re: [PATCH] memblock, numa: Binary search node id

[Russ Anderson]

On Thu, Aug 15, 2013 at 02:06:44PM -0700, Yinghai Lu wrote:
> On Thu, Aug 15, 2013 at 1:43 PM, Andrew Morton
> <akpm@linux-foundation.org> wrote:
> > On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
> >
> >> Current early_pfn_to_nid() on arch that support memblock go
> >> over memblock.memory one by one, so will take too many try
> >> near the end.
> >>
> >> We can use existing memblock_search to find the node id for
> >> given pfn, that could save some time on bigger system that
> >> have many entries memblock.memory array.
> >
> > Looks nice.  I wonder how much difference it makes.
> 
> Russ said he would test on his 256 nodes system, but looks he never
> got chance.

I reserved time tonight on a couple big systems to measure
the performance difference.

Thanks,
-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH] memblock, numa: Binary search node id

[Russ Anderson]

On Thu, Aug 15, 2013 at 01:43:48PM -0700, Andrew Morton wrote:
> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
> 
> > Current early_pfn_to_nid() on arch that support memblock go
> > over memblock.memory one by one, so will take too many try
> > near the end.
> > 
> > We can use existing memblock_search to find the node id for
> > given pfn, that could save some time on bigger system that
> > have many entries memblock.memory array.
> 
> Looks nice.  I wonder how much difference it makes.

Here are the timing differences for several machines.
In each case with the patch less time was spent in __early_pfn_to_nid().


                        3.11-rc5        with patch      difference (%)
                        --------        ----------      --------------
UV1: 256 nodes  9TB:     411.66          402.47         -9.19 (2.23%)
UV2: 255 nodes 16TB:    1141.02         1138.12         -2.90 (0.25%)
UV2:  64 nodes  2TB:     128.15          126.53         -1.62 (1.26%)
UV2:  32 nodes  2TB:     121.87          121.07         -0.80 (0.66%)
                        Time in seconds.

Acked-by: Russ Anderson <rja@sgi.com>
 
> > ...
> >
> > --- 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
> > @@ -914,6 +914,24 @@ 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
> 
> This function will have no callers if
> CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y.  That's not too bad as the
> function is __init_memblock.  But this depends on
> CONFIG_ARCH_DISCARD_MEMBLOCK.  Messy :(
> 

-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

Re: [PATCH] memblock, numa: Binary search node id

[Russ Anderson]

On Thu, Aug 15, 2013 at 01:43:48PM -0700, Andrew Morton wrote:
> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
> 
> > Current early_pfn_to_nid() on arch that support memblock go
> > over memblock.memory one by one, so will take too many try
> > near the end.
> > 
> > We can use existing memblock_search to find the node id for
> > given pfn, that could save some time on bigger system that
> > have many entries memblock.memory array.
> 
> Looks nice.  I wonder how much difference it makes.

Here are the timing differences for several machines.
In each case with the patch less time was spent in __early_pfn_to_nid().


                        3.11-rc5        with patch      difference (%)
                        --------        ----------      --------------
UV1: 256 nodes  9TB:     411.66          402.47         -9.19 (2.23%)
UV2: 255 nodes 16TB:    1141.02         1138.12         -2.90 (0.25%)
UV2:  64 nodes  2TB:     128.15          126.53         -1.62 (1.26%)
UV2:  32 nodes  2TB:     121.87          121.07         -0.80 (0.66%)
                        Time in seconds.

Acked-by: Russ Anderson <rja@sgi.com>
 
> > ...
> >
> > --- 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
> > @@ -914,6 +914,24 @@ 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
> 
> This function will have no callers if
> CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y.  That's not too bad as the
> function is __init_memblock.  But this depends on
> CONFIG_ARCH_DISCARD_MEMBLOCK.  Messy :(
> 

-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH] memblock, numa: Binary search node id

[Yinghai Lu]

On Fri, Aug 16, 2013 at 12:01 PM, Russ Anderson <rja@sgi.com> wrote:
> On Thu, Aug 15, 2013 at 01:43:48PM -0700, Andrew Morton wrote:
>> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
>>
>> > Current early_pfn_to_nid() on arch that support memblock go
>> > over memblock.memory one by one, so will take too many try
>> > near the end.
>> >
>> > We can use existing memblock_search to find the node id for
>> > given pfn, that could save some time on bigger system that
>> > have many entries memblock.memory array.
>>
>> Looks nice.  I wonder how much difference it makes.
>
> Here are the timing differences for several machines.
> In each case with the patch less time was spent in __early_pfn_to_nid().
>
>
>                         3.11-rc5        with patch      difference (%)
>                         --------        ----------      --------------
> UV1: 256 nodes  9TB:     411.66          402.47         -9.19 (2.23%)
> UV2: 255 nodes 16TB:    1141.02         1138.12         -2.90 (0.25%)
> UV2:  64 nodes  2TB:     128.15          126.53         -1.62 (1.26%)
> UV2:  32 nodes  2TB:     121.87          121.07         -0.80 (0.66%)
>                         Time in seconds.
>

Thanks.

9T one have more entries in memblock.memory?

Yinghai

Re: [PATCH] memblock, numa: Binary search node id

[Yinghai Lu]

On Fri, Aug 16, 2013 at 12:01 PM, Russ Anderson <rja@sgi.com> wrote:
> On Thu, Aug 15, 2013 at 01:43:48PM -0700, Andrew Morton wrote:
>> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
>>
>> > Current early_pfn_to_nid() on arch that support memblock go
>> > over memblock.memory one by one, so will take too many try
>> > near the end.
>> >
>> > We can use existing memblock_search to find the node id for
>> > given pfn, that could save some time on bigger system that
>> > have many entries memblock.memory array.
>>
>> Looks nice.  I wonder how much difference it makes.
>
> Here are the timing differences for several machines.
> In each case with the patch less time was spent in __early_pfn_to_nid().
>
>
>                         3.11-rc5        with patch      difference (%)
>                         --------        ----------      --------------
> UV1: 256 nodes  9TB:     411.66          402.47         -9.19 (2.23%)
> UV2: 255 nodes 16TB:    1141.02         1138.12         -2.90 (0.25%)
> UV2:  64 nodes  2TB:     128.15          126.53         -1.62 (1.26%)
> UV2:  32 nodes  2TB:     121.87          121.07         -0.80 (0.66%)
>                         Time in seconds.
>

Thanks.

9T one have more entries in memblock.memory?

Yinghai

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH] memblock, numa: Binary search node id

[Russ Anderson]

On Fri, Aug 16, 2013 at 12:15:21PM -0700, Yinghai Lu wrote:
> On Fri, Aug 16, 2013 at 12:01 PM, Russ Anderson <rja@sgi.com> wrote:
> > On Thu, Aug 15, 2013 at 01:43:48PM -0700, Andrew Morton wrote:
> >> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
> >>
> >> > Current early_pfn_to_nid() on arch that support memblock go
> >> > over memblock.memory one by one, so will take too many try
> >> > near the end.
> >> >
> >> > We can use existing memblock_search to find the node id for
> >> > given pfn, that could save some time on bigger system that
> >> > have many entries memblock.memory array.
> >>
> >> Looks nice.  I wonder how much difference it makes.
> >
> > Here are the timing differences for several machines.
> > In each case with the patch less time was spent in __early_pfn_to_nid().
> >
> >
> >                         3.11-rc5        with patch      difference (%)
> >                         --------        ----------      --------------
> > UV1: 256 nodes  9TB:     411.66          402.47         -9.19 (2.23%)
> > UV2: 255 nodes 16TB:    1141.02         1138.12         -2.90 (0.25%)
> > UV2:  64 nodes  2TB:     128.15          126.53         -1.62 (1.26%)
> > UV2:  32 nodes  2TB:     121.87          121.07         -0.80 (0.66%)
> >                         Time in seconds.
> >
> 
> Thanks.
> 
> 9T one have more entries in memblock.memory?

Yes.  It is older hardware with smaller DIMMs and more of them.

-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

Re: [PATCH] memblock, numa: Binary search node id

[Russ Anderson]

On Fri, Aug 16, 2013 at 12:15:21PM -0700, Yinghai Lu wrote:
> On Fri, Aug 16, 2013 at 12:01 PM, Russ Anderson <rja@sgi.com> wrote:
> > On Thu, Aug 15, 2013 at 01:43:48PM -0700, Andrew Morton wrote:
> >> On Wed, 14 Aug 2013 22:46:29 -0700 Yinghai Lu <yinghai@kernel.org> wrote:
> >>
> >> > Current early_pfn_to_nid() on arch that support memblock go
> >> > over memblock.memory one by one, so will take too many try
> >> > near the end.
> >> >
> >> > We can use existing memblock_search to find the node id for
> >> > given pfn, that could save some time on bigger system that
> >> > have many entries memblock.memory array.
> >>
> >> Looks nice.  I wonder how much difference it makes.
> >
> > Here are the timing differences for several machines.
> > In each case with the patch less time was spent in __early_pfn_to_nid().
> >
> >
> >                         3.11-rc5        with patch      difference (%)
> >                         --------        ----------      --------------
> > UV1: 256 nodes  9TB:     411.66          402.47         -9.19 (2.23%)
> > UV2: 255 nodes 16TB:    1141.02         1138.12         -2.90 (0.25%)
> > UV2:  64 nodes  2TB:     128.15          126.53         -1.62 (1.26%)
> > UV2:  32 nodes  2TB:     121.87          121.07         -0.80 (0.66%)
> >                         Time in seconds.
> >
> 
> Thanks.
> 
> 9T one have more entries in memblock.memory?

Yes.  It is older hardware with smaller DIMMs and more of them.

-- 
Russ Anderson, OS RAS/Partitioning Project Lead  
SGI - Silicon Graphics Inc          rja@sgi.com

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>