* [PATCH 0/2] proc.5 modification
@ 2015-01-22 19:21 Elie De Brauwer
[not found] ` <1421954463-2853-1-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
0 siblings, 1 reply; 5+ messages in thread
From: Elie De Brauwer @ 2015-01-22 19:21 UTC (permalink / raw)
To: mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w
Cc: linux-man-u79uwXL29TY76Z2rM5mHXA, Elie De Brauwer
Hello Michael,
Two patches related to proc.5:
- the first patch adds an explanation of /proc/sys/vm/compact_memory
- the second patch fixes two typo's (of which I'm guilty myself) in the
buddyinfo section of proc.5
my 2 cents
E.
Elie De Brauwer (2):
proc.5: Explain /proc/sys/vm/compact_memory
proc.5: tfix
man5/proc.5 | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH 1/2] proc.5: Explain /proc/sys/vm/compact_memory
[not found] ` <1421954463-2853-1-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
@ 2015-01-22 19:21 ` Elie De Brauwer
[not found] ` <1421954463-2853-2-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-01-22 19:21 ` [PATCH 2/2] proc.5: tfix Elie De Brauwer
1 sibling, 1 reply; 5+ messages in thread
From: Elie De Brauwer @ 2015-01-22 19:21 UTC (permalink / raw)
To: mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w
Cc: linux-man-u79uwXL29TY76Z2rM5mHXA, Elie De Brauwer
Since 2.6.36 [1] CONFIG_COMPACTION is supported in Linux (for a
detailed explanation see [2]). But in essence the contents of /proc/buddyinfo
shows how much contiguous areas of a certain size are available. These
numbers are not actually up to date as the Linux kernel will implicitely
trigger compaction (+- defragmentation) when an allocation is done.
This makes it difficult since you can't predict upfront whether or not a
large allocation will succeed or not.
By using /proc/sys/vm/compact_memory you can explicitely trigger compaction
to occur and /proc/buddyinfo will give a more realistic view on the
available memory in contiguous areas.
This patch updates proc.5 to explain the usage of this file and is
inspired upon Documentation/systcl/vm.txt [3]
[1] http://kernelnewbies.org/Linux_2_6_35#head-9cb0a1275559d40296da42efb7977896ac9edab7
[2] http://lwn.net/Articles/368869/
[3] http://lxr.free-electrons.com/source/Documentation/sysctl/vm.txt#L100
Signed-off-by: Elie De Brauwer <eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
man5/proc.5 | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/man5/proc.5 b/man5/proc.5
index 860eb66..5bff2a0 100644
--- a/man5/proc.5
+++ b/man5/proc.5
@@ -3943,6 +3943,15 @@ On some systems, it is not present.
This directory contains files for memory management tuning, buffer and
cache management.
.TP
+.IR /proc/sys/vm/compact_memory " (since Linux 2.6.35)"
+When 1 is written to this file, all zones are compacted such that free
+memory is available in contiguous blocks where possible.
+The effect of this action can be seen by examining
+.IR /proc/buddyinfo .
+.IP
+Only present if the kernel was configured with
+.BR CONFIG_COMPACTION .
+.TP
.IR /proc/sys/vm/drop_caches " (since Linux 2.6.16)"
Writing to this file causes the kernel to drop clean caches, dentries, and
inodes from memory, causing that memory to become free.
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH 2/2] proc.5: tfix
[not found] ` <1421954463-2853-1-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-01-22 19:21 ` [PATCH 1/2] proc.5: Explain /proc/sys/vm/compact_memory Elie De Brauwer
@ 2015-01-22 19:21 ` Elie De Brauwer
[not found] ` <1421954463-2853-3-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
1 sibling, 1 reply; 5+ messages in thread
From: Elie De Brauwer @ 2015-01-22 19:21 UTC (permalink / raw)
To: mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w
Cc: linux-man-u79uwXL29TY76Z2rM5mHXA, Elie De Brauwer
Signed-off-by: Elie De Brauwer <eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
man5/proc.5 | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/man5/proc.5 b/man5/proc.5
index 5bff2a0..9138ead 100644
--- a/man5/proc.5
+++ b/man5/proc.5
@@ -1981,12 +1981,12 @@ Node 0, zone Normal 216 55 189 101 84 38 37 27 5 3 587
In this example, there is one node containing three zones and there
are 11 different chunk sizes.
-If the page size is 4 kilobyteis, then the first zone called
+If the page size is 4 kilobytes, then the first zone called
.I DMA
(on x86 the first 16 megabyte of memory) has 1 chunk of 4 kilobytes
(order 0) available and has 3 chunks of 4 megabytes (order 10) available.
-If the memory is heavily fragmentated, the counters for higher
+If the memory is heavily fragmented, the counters for higher
order chunks will be zero and allocation of large contiguous areas
will fail.
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH 1/2] proc.5: Explain /proc/sys/vm/compact_memory
[not found] ` <1421954463-2853-2-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
@ 2015-01-22 19:52 ` Michael Kerrisk (man-pages)
0 siblings, 0 replies; 5+ messages in thread
From: Michael Kerrisk (man-pages) @ 2015-01-22 19:52 UTC (permalink / raw)
To: Elie De Brauwer
Cc: mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w,
linux-man-u79uwXL29TY76Z2rM5mHXA
On 01/22/2015 08:21 PM, Elie De Brauwer wrote:
> Since 2.6.36 [1] CONFIG_COMPACTION is supported in Linux (for a
> detailed explanation see [2]). But in essence the contents of /proc/buddyinfo
> shows how much contiguous areas of a certain size are available. These
> numbers are not actually up to date as the Linux kernel will implicitely
> trigger compaction (+- defragmentation) when an allocation is done.
> This makes it difficult since you can't predict upfront whether or not a
> large allocation will succeed or not.
> By using /proc/sys/vm/compact_memory you can explicitely trigger compaction
> to occur and /proc/buddyinfo will give a more realistic view on the
> available memory in contiguous areas.
>
> This patch updates proc.5 to explain the usage of this file and is
> inspired upon Documentation/systcl/vm.txt [3]
>
> [1] http://kernelnewbies.org/Linux_2_6_35#head-9cb0a1275559d40296da42efb7977896ac9edab7
> [2] http://lwn.net/Articles/368869/
> [3] http://lxr.free-electrons.com/source/Documentation/sysctl/vm.txt#L100
Thanks, Elie. Applied.
Cheers,
Michael
> Signed-off-by: Elie De Brauwer <eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> ---
> man5/proc.5 | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/man5/proc.5 b/man5/proc.5
> index 860eb66..5bff2a0 100644
> --- a/man5/proc.5
> +++ b/man5/proc.5
> @@ -3943,6 +3943,15 @@ On some systems, it is not present.
> This directory contains files for memory management tuning, buffer and
> cache management.
> .TP
> +.IR /proc/sys/vm/compact_memory " (since Linux 2.6.35)"
> +When 1 is written to this file, all zones are compacted such that free
> +memory is available in contiguous blocks where possible.
> +The effect of this action can be seen by examining
> +.IR /proc/buddyinfo .
> +.IP
> +Only present if the kernel was configured with
> +.BR CONFIG_COMPACTION .
> +.TP
> .IR /proc/sys/vm/drop_caches " (since Linux 2.6.16)"
> Writing to this file causes the kernel to drop clean caches, dentries, and
> inodes from memory, causing that memory to become free.
>
--
Michael Kerrisk
Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
Linux/UNIX System Programming Training: http://man7.org/training/
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH 2/2] proc.5: tfix
[not found] ` <1421954463-2853-3-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
@ 2015-01-22 19:53 ` Michael Kerrisk (man-pages)
0 siblings, 0 replies; 5+ messages in thread
From: Michael Kerrisk (man-pages) @ 2015-01-22 19:53 UTC (permalink / raw)
To: Elie De Brauwer
Cc: mtk.manpages-Re5JQEeQqe8AvxtiuMwx3w,
linux-man-u79uwXL29TY76Z2rM5mHXA
Thanks Elie!
Applied.
Cheers,
Michael
On 01/22/2015 08:21 PM, Elie De Brauwer wrote:
> Signed-off-by: Elie De Brauwer <eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> ---
> man5/proc.5 | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/man5/proc.5 b/man5/proc.5
> index 5bff2a0..9138ead 100644
> --- a/man5/proc.5
> +++ b/man5/proc.5
> @@ -1981,12 +1981,12 @@ Node 0, zone Normal 216 55 189 101 84 38 37 27 5 3 587
>
> In this example, there is one node containing three zones and there
> are 11 different chunk sizes.
> -If the page size is 4 kilobyteis, then the first zone called
> +If the page size is 4 kilobytes, then the first zone called
> .I DMA
> (on x86 the first 16 megabyte of memory) has 1 chunk of 4 kilobytes
> (order 0) available and has 3 chunks of 4 megabytes (order 10) available.
>
> -If the memory is heavily fragmentated, the counters for higher
> +If the memory is heavily fragmented, the counters for higher
> order chunks will be zero and allocation of large contiguous areas
> will fail.
>
>
--
Michael Kerrisk
Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
Linux/UNIX System Programming Training: http://man7.org/training/
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2015-01-22 19:53 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-01-22 19:21 [PATCH 0/2] proc.5 modification Elie De Brauwer
[not found] ` <1421954463-2853-1-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-01-22 19:21 ` [PATCH 1/2] proc.5: Explain /proc/sys/vm/compact_memory Elie De Brauwer
[not found] ` <1421954463-2853-2-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-01-22 19:52 ` Michael Kerrisk (man-pages)
2015-01-22 19:21 ` [PATCH 2/2] proc.5: tfix Elie De Brauwer
[not found] ` <1421954463-2853-3-git-send-email-eliedebrauwer-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-01-22 19:53 ` Michael Kerrisk (man-pages)
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.