Skip to contentSkip to conversation

__alloc_bootmem_node should not panic when it fails

PATCH In review Anton Blanchard 5 participants 6 messages Jun 27, 2004 – Jun 28, 2004 Memory management

lore
Share & tools
lore

Anton Blanchard

author
#0 lore raw

PATCH 1/1 __alloc_bootmem_node should not panic when it fails

__alloc_bootmem_node currently panics if it cant satisfy an allocation for a particular node. Thats rather antisocial, we should at the very least return NULL and allow the caller to proceed (eg try another node).

A quick look at alloc_bootmem_node usage suggests we should fall back to allocating from other nodes if it fails (as arch/alpha/kernel/pci_iommu.c and arch/x86_64/kernel/setup64.c do).

The following patch does that. We fall back to the regular __alloc_bootmem when __alloc_bootmem_node fails, which means all other nodes are checked for available memory.

Signed-off-by Anton Blanchard <[email protected]>
mm/bootmem.c renamed from mm/bootmem.c~debugit +1 -6
diff -puN mm/bootmem.c~debugit mm/bootmem.c
@@ -371,11 +371,6 @@ void * __init __alloc_bootmem_node (pg_d
 	if (ptr)
 		return (ptr);
 
-	/*
-	 * Whoops, we cannot satisfy the allocation request.
-	 */
-	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
-	panic("Out of memory");
-	return NULL;
+	return __alloc_bootmem(size, align, goal);
 }

_

#1 lore raw

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Quoted 3 lines · Anton Blanchard

The following patch does that. We fall back to the regular __alloc_bootmem when __alloc_bootmem_node fails, which means all other nodes are checked for available memory.

But allocating from other nodes has performance implications, which might be quite big, depending on the specific architecture. So you should at least print an KERN_INFO or even KERN_WARNING message, if this happens.

mm/bootmem.c void * __init __alloc_bootmem_node (pg_d · line 377

Quoted 13 lines
Signed-off-by Anton Blanchard <[email protected]>

diff -puN mm/bootmem.c~debugit mm/bootmem.c

mm/bootmem.c renamed from mm/bootmem.c~debugit +0 -4
@@ -371,11 +371,6 @@ void * __init __alloc_bootmem_node (pg_d
 	if (ptr)
 		return (ptr);
 
-	/*
-	 * Whoops, we cannot satisfy the allocation request.
-	 */
-	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);

Maybe changing this message to:

	printk(KERN_WARNING "Failed to alloc %lu bytes from local node.\n"
	" Allocating from distant node instead. Performance may drop!\n", size);

mm/bootmem.c void * __init __alloc_bootmem_node (pg_d · line 375

Quoted 4 lines
mm/bootmem.c renamed from mm/bootmem.c~debugit +1 -2
-	panic("Out of memory");
-	return NULL;
+	return __alloc_bootmem(size, align, goal);
 }

So now the user knows what is going on and that this node might need more memory ;-)

Regards

Ingo Oeser

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)

iD8DBQFA3mjOU56oYWuOrkARAuQGAJ9lasSDYLgMDzAGnGYxnH4OpSHXNQCg0uy3 12GFsxYaaptUIZkYHYUw9Is=
=1ydw
-----END PGP SIGNATURE-----

author
#2 lore raw
Quoted 5 lines

But allocating from other nodes has performance implications, which might be quite big, depending on the specific architecture. So you should at least print an KERN_INFO or even KERN_WARNING message, if this happens.

...

Quoted 2 lines

So now the user knows what is going on and that this node might need more memory ;-)

Unfortunately nodes without memory is relatively common on ppc64, and I believe x86-64. From a ppc64 perspective Im fine with best effort, perhaps someone from the heavily NUMA camp (ia64?) could comment.

Anton

#3 lore raw
Quoted 4 lines · Anton Blanchard

Unfortunately nodes without memory is relatively common on ppc64, and I believe x86-64. From a ppc64 perspective Im fine with best effort, perhaps someone from the heavily NUMA camp (ia64?) could comment.

Does anyone make ia64 NUMA hardware where you can have memory-less nodes?

--cw

#4 lore raw
Quoted 11 lines · Chris Wedgwood
Quoted 6 lines · Anton Blanchard

Unfortunately nodes without memory is relatively common on ppc64, and I believe x86-64. From a ppc64 perspective Im fine with best effort, perhaps someone from the heavily NUMA camp (ia64?) could comment.

Quoted 8 lines

Does anyone make ia64 NUMA hardware where you can have memory-less nodes?

--cw

HP ships IA64 NUMA hardware where the default memory configuration is memory-less. There are N-1 cpu-nodes and 1 memory node.

Bob

#5 lore raw
In reply to Chris Wedgwood
Quoted 9 lines · Chris Wedgwood
Quoted 4 lines · Anton Blanchard

Unfortunately nodes without memory is relatively common on ppc64, and I believe x86-64. From a ppc64 perspective Im fine with best effort, perhaps someone from the heavily NUMA camp (ia64?) could comment.

Does anyone make ia64 NUMA hardware where you can have memory-less nodes?

Altix SN2 can have memoryless nodes

mh

Signature · 2 lines
Martin Hicks                Wild Open Source Inc.
[email protected]     613-266-2296