[PATCH 1/2] Documentation: mm: Add compact_node on Documentation/sysctl/vm.txt

[PATCH 1/2] Documentation: mm: Add compact_node on Documentation/sysctl/vm.txt

[Masanari Iida]

The Documentation/sysctl/vm.txt does include "compact_memory",
but it doesn't include "compact_node".

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
---
 Documentation/sysctl/vm.txt |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 9c11d97..c94acad 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -20,6 +20,7 @@ Currently, these files are in /proc/sys/vm:
 
 - block_dump
 - compact_memory
+- compact_node
 - dirty_background_bytes
 - dirty_background_ratio
 - dirty_bytes
@@ -76,6 +77,13 @@ huge pages although processes will also directly compact memory as required.
 
 ==============================================================
 
+compact_node
+
+Available only when CONFIG_COMPACTION is set and also the system is NUMA
+architecture. When a node number is written to the file, the kernel fixing
+the fragmented pages on the specified NUMA node. 
+
+==============================================================
 dirty_background_bytes
 
 Contains the amount of dirty memory at which the pdflush background writeback
-- 
1.7.10.rc4

[PATCH 1/2] Documentation: mm: Add compact_node on Documentation/sysctl/vm.txt

[Masanari Iida]

The Documentation/sysctl/vm.txt does include "compact_memory",
but it doesn't include "compact_node".

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
---
 Documentation/sysctl/vm.txt |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 9c11d97..c94acad 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -20,6 +20,7 @@ Currently, these files are in /proc/sys/vm:
 
 - block_dump
 - compact_memory
+- compact_node
 - dirty_background_bytes
 - dirty_background_ratio
 - dirty_bytes
@@ -76,6 +77,13 @@ huge pages although processes will also directly compact memory as required.
 
 ==============================================================
 
+compact_node
+
+Available only when CONFIG_COMPACTION is set and also the system is NUMA
+architecture. When a node number is written to the file, the kernel fixing
+the fragmented pages on the specified NUMA node. 
+
+==============================================================
 dirty_background_bytes
 
 Contains the amount of dirty memory at which the pdflush background writeback
-- 
1.7.10.rc4

--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/2] Documentation: mm: Fix path to extfrag_index in vm.txt

[Masanari Iida]

The path for extfrag_index has not been updated even after it moved
to under /sys. This patch fixed the path.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
---
 Documentation/sysctl/vm.txt |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index c94acad..9dd8555 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -166,11 +166,12 @@ user should run `sync' first.
 extfrag_threshold
 
 This parameter affects whether the kernel will compact memory or direct
-reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what
-the fragmentation index for each order is in each zone in the system. Values
-tending towards 0 imply allocations would fail due to lack of memory,
-values towards 1000 imply failures are due to fragmentation and -1 implies
-that the allocation will succeed as long as watermarks are met.
+reclaim to satisfy a high-order allocation. 
+/sys/kernel/debug/extfrag/extfrag_index shows what the fragmentation index 
+for each order is in each zone in the system. Values tending towards 0 
+imply allocations would fail due to lack of memory, values towards 1000 
+imply failures are due to fragmentation and -1 implies that the allocation 
+will succeed as long as watermarks are met.
 
 The kernel will not compact memory in a zone if the
 fragmentation index is <= extfrag_threshold. The default value is 500.
-- 
1.7.10.rc4

[PATCH 2/2] Documentation: mm: Fix path to extfrag_index in vm.txt

[Masanari Iida]

The path for extfrag_index has not been updated even after it moved
to under /sys. This patch fixed the path.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
---
 Documentation/sysctl/vm.txt |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index c94acad..9dd8555 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -166,11 +166,12 @@ user should run `sync' first.
 extfrag_threshold
 
 This parameter affects whether the kernel will compact memory or direct
-reclaim to satisfy a high-order allocation. /proc/extfrag_index shows what
-the fragmentation index for each order is in each zone in the system. Values
-tending towards 0 imply allocations would fail due to lack of memory,
-values towards 1000 imply failures are due to fragmentation and -1 implies
-that the allocation will succeed as long as watermarks are met.
+reclaim to satisfy a high-order allocation. 
+/sys/kernel/debug/extfrag/extfrag_index shows what the fragmentation index 
+for each order is in each zone in the system. Values tending towards 0 
+imply allocations would fail due to lack of memory, values towards 1000 
+imply failures are due to fragmentation and -1 implies that the allocation 
+will succeed as long as watermarks are met.
 
 The kernel will not compact memory in a zone if the
 fragmentation index is <= extfrag_threshold. The default value is 500.
-- 
1.7.10.rc4

--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 1/2] Documentation: mm: Add compact_node on Documentation/sysctl/vm.txt

[David Rientjes]

On Fri, 6 Apr 2012, Masanari Iida wrote:

> The Documentation/sysctl/vm.txt does include "compact_memory",
> but it doesn't include "compact_node".
> 

That's because /proc/sys/vm/compact_node doesn't exist.

The per-node compaction trigger is at 
/sys/device/system/node/nodeX/compact which is appropriately documented in 
Documentation/ABI/testing/sysfs-devices-node.

Re: [PATCH 1/2] Documentation: mm: Add compact_node on Documentation/sysctl/vm.txt

[David Rientjes]

On Fri, 6 Apr 2012, Masanari Iida wrote:

> The Documentation/sysctl/vm.txt does include "compact_memory",
> but it doesn't include "compact_node".
> 

That's because /proc/sys/vm/compact_node doesn't exist.

The per-node compaction trigger is at 
/sys/device/system/node/nodeX/compact which is appropriately documented in 
Documentation/ABI/testing/sysfs-devices-node.

--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/2] Documentation: mm: Fix path to extfrag_index in vm.txt

[David Rientjes]

On Fri, 6 Apr 2012, Masanari Iida wrote:

> The path for extfrag_index has not been updated even after it moved
> to under /sys. This patch fixed the path.
> 

The path looks good, but I think it would be better to also add that you 
must mount debugfs for this to be available there.

Re: [PATCH 2/2] Documentation: mm: Fix path to extfrag_index in vm.txt

[David Rientjes]

On Fri, 6 Apr 2012, Masanari Iida wrote:

> The path for extfrag_index has not been updated even after it moved
> to under /sys. This patch fixed the path.
> 

The path looks good, but I think it would be better to also add that you 
must mount debugfs for this to be available there.

--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>