public inbox for linux-man@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH v3] man2: add MPOL_WEIGHTED_INTERLEAVE documentation
@ 2024-03-15 23:43 Svetly Todorov
  2024-03-15 23:52 ` Alejandro Colomar
  0 siblings, 1 reply; 4+ messages in thread
From: Svetly Todorov @ 2024-03-15 23:43 UTC (permalink / raw)
  To: alx; +Cc: linux-man, gregory.price, ying.huang, Svetly Todorov



---
Adding documentation for the new MPOL_WEIGHTED_INTERLEAVE mode in the same
manpages that mention MPOL_INTERLEAVE; namely, mbind(2), set_mempolicy(2),
and get_mempolicy(2).

Descriptions were based on the changes introduced in this patch: 
https://lore.kernel.org/all/20240202170238.90004-4-gregory.price@memverge.com/

Which was upstreamed to 6.9 here:
https://lore.kernel.org/linux-mm/20240313200532.34e4cff216acd3db8def4637@linux-foundation.org/

To: alx@kernel.org
Cc: linux-man@vger.kernel.org
Cc: gregory.price@memverge.com
Cc: ying.huang@intel.com
Signed-off-by: Svetly Todorov <svetly.todorov@memverge.com>

Changes in v3:
- italicize paths
- Link to v2: https://lore.kernel.org/r/20240315-weighted_interleave-v2-1-b742a48750b0@memverge.com

Changes in v2:
- make flag documentation implementation-agnostic
- Link to v1: https://lore.kernel.org/r/20240314-weighted_interleave-v1-1-ce85d64db0d4@memverge.com
---
 man2/get_mempolicy.2 |  8 ++++++--
 man2/mbind.2         | 17 +++++++++++++++++
 man2/set_mempolicy.2 | 17 +++++++++++++++++
 3 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/man2/get_mempolicy.2 b/man2/get_mempolicy.2
index 5248f04ba..03550331d 100644
--- a/man2/get_mempolicy.2
+++ b/man2/get_mempolicy.2
@@ -137,7 +137,9 @@ specifies
 but not
 .BR MPOL_F_ADDR ,
 and the thread's current policy is
-.BR MPOL_INTERLEAVE ,
+.BR MPOL_INTERLEAVE
+or
+.BR MPOL_WEIGHTED_INTERLEAVE ,
 then
 .BR get_mempolicy ()
 will return in the location pointed to by a non-NULL
@@ -206,7 +208,9 @@ specified
 but not
 .B MPOL_F_ADDR
 and the current thread policy is not
-.BR MPOL_INTERLEAVE .
+.BR MPOL_INTERLEAVE
+or
+.BR MPOL_WEIGHTED_INTERLEAVE .
 Or,
 .I flags
 specified
diff --git a/man2/mbind.2 b/man2/mbind.2
index b0e961f9c..6f85dec0e 100644
--- a/man2/mbind.2
+++ b/man2/mbind.2
@@ -105,6 +105,7 @@ argument must specify one of
 .BR MPOL_DEFAULT ,
 .BR MPOL_BIND ,
 .BR MPOL_INTERLEAVE ,
+.BR MPOL_WEIGHTED_INTERLEAVE ,
 .BR MPOL_PREFERRED ,
 or
 .B MPOL_LOCAL
@@ -243,6 +244,22 @@ at least 1\ MB or bigger with a fairly uniform access pattern.
 Accesses to a single page of the area will still be limited to
 the memory bandwidth of a single node.
 .TP
+.B MPOL_WEIGHTED_INTERLEAVE
+This mode interleaves page allocations across the nodes specified in
+.I nodemask
+according to the weights in
+.IR /sys/kernel/mm/mempolicy/weighted_interleave .
+For example, if bits 0, 2, and 5 are raised in
+.IR nodemask ,
+and the contents of
+.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
+.IR /sys/.../node2 ,
+and
+.I /sys/.../node5
+are 4, 7, and 9, respectively,
+then pages in this region will be allocated on nodes 0, 2, and 5
+in a 4:7:9 ratio.
+.TP
 .B MPOL_PREFERRED
 This mode sets the preferred node for allocation.
 The kernel will try to allocate pages from this
diff --git a/man2/set_mempolicy.2 b/man2/set_mempolicy.2
index fc3ad9df8..6b51cb376 100644
--- a/man2/set_mempolicy.2
+++ b/man2/set_mempolicy.2
@@ -63,6 +63,7 @@ argument must specify one of
 .BR MPOL_DEFAULT ,
 .BR MPOL_BIND ,
 .BR MPOL_INTERLEAVE ,
+.BR MPOL_WEIGHTED_INTERLEAVE ,
 .BR MPOL_PREFERRED ,
 or
 .B MPOL_LOCAL
@@ -199,6 +200,22 @@ the memory bandwidth of a single node.
 .\" To be effective the memory area should be fairly large,
 .\" at least 1 MB or bigger.
 .TP
+.B MPOL_WEIGHTED_INTERLEAVE
+This mode interleaves page allocations across the nodes specified in
+.I nodemask
+according to the weights in
+.IR /sys/kernel/mm/mempolicy/weighted_interleave .
+For example, if bits 0, 2, and 5 are raised in
+.IR nodemask ,
+and the contents of
+.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
+.IR /sys/.../node2 ,
+and
+.I /sys/.../node5
+are 4, 7, and 9, respectively,
+then pages in this region will be allocated on nodes 0, 2, and 5
+in a 4:7:9 ratio.
+.TP
 .B MPOL_PREFERRED
 This mode sets the preferred node for allocation.
 The kernel will try to allocate pages from this node first

---
base-commit: a4ea5f76215dcf1d8d017eb65ab12919ccf09f3f
change-id: 20240313-weighted_interleave-e8141ed754f9

Best regards,
-- 
Svetly Todorov <svetly.todorov@memverge.com>


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: [PATCH v3] man2: add MPOL_WEIGHTED_INTERLEAVE documentation
  2024-03-15 23:43 [PATCH v3] man2: add MPOL_WEIGHTED_INTERLEAVE documentation Svetly Todorov
@ 2024-03-15 23:52 ` Alejandro Colomar
  2024-03-16 19:21   ` Svetly Todorov
  0 siblings, 1 reply; 4+ messages in thread
From: Alejandro Colomar @ 2024-03-15 23:52 UTC (permalink / raw)
  To: Svetly Todorov; +Cc: linux-man, gregory.price, ying.huang

[-- Attachment #1: Type: text/plain, Size: 5248 bytes --]

Hi Svetly,

On Fri, Mar 15, 2024 at 04:43:36PM -0700, Svetly Todorov wrote:
> 
> 
> ---
> Adding documentation for the new MPOL_WEIGHTED_INTERLEAVE mode in the same
> manpages that mention MPOL_INTERLEAVE; namely, mbind(2), set_mempolicy(2),
> and get_mempolicy(2).
> 
> Descriptions were based on the changes introduced in this patch: 
> https://lore.kernel.org/all/20240202170238.90004-4-gregory.price@memverge.com/
> 
> Which was upstreamed to 6.9 here:
> https://lore.kernel.org/linux-mm/20240313200532.34e4cff216acd3db8def4637@linux-foundation.org/
> 
> To: alx@kernel.org
> Cc: linux-man@vger.kernel.org
> Cc: gregory.price@memverge.com
> Cc: ying.huang@intel.com

Please add those to the commit message.

Content-wise, the patch LGTM.  I have some comments about formatting.
Please see below.

Have a lovely night!
Alex

> Signed-off-by: Svetly Todorov <svetly.todorov@memverge.com>
> 
> Changes in v3:
> - italicize paths
> - Link to v2: https://lore.kernel.org/r/20240315-weighted_interleave-v2-1-b742a48750b0@memverge.com
> 
> Changes in v2:
> - make flag documentation implementation-agnostic
> - Link to v1: https://lore.kernel.org/r/20240314-weighted_interleave-v1-1-ce85d64db0d4@memverge.com
> ---
>  man2/get_mempolicy.2 |  8 ++++++--
>  man2/mbind.2         | 17 +++++++++++++++++
>  man2/set_mempolicy.2 | 17 +++++++++++++++++
>  3 files changed, 40 insertions(+), 2 deletions(-)
> 
> diff --git a/man2/get_mempolicy.2 b/man2/get_mempolicy.2
> index 5248f04ba..03550331d 100644
> --- a/man2/get_mempolicy.2
> +++ b/man2/get_mempolicy.2
> @@ -137,7 +137,9 @@ specifies
>  but not
>  .BR MPOL_F_ADDR ,
>  and the thread's current policy is
> -.BR MPOL_INTERLEAVE ,
> +.BR MPOL_INTERLEAVE

This should be B, not BR (BR is for alternating Bold and Roman).

> +or
> +.BR MPOL_WEIGHTED_INTERLEAVE ,
>  then
>  .BR get_mempolicy ()
>  will return in the location pointed to by a non-NULL
> @@ -206,7 +208,9 @@ specified
>  but not
>  .B MPOL_F_ADDR
>  and the current thread policy is not
> -.BR MPOL_INTERLEAVE .
> +.BR MPOL_INTERLEAVE
> +or
> +.BR MPOL_WEIGHTED_INTERLEAVE .
>  Or,
>  .I flags
>  specified
> diff --git a/man2/mbind.2 b/man2/mbind.2
> index b0e961f9c..6f85dec0e 100644
> --- a/man2/mbind.2
> +++ b/man2/mbind.2
> @@ -105,6 +105,7 @@ argument must specify one of
>  .BR MPOL_DEFAULT ,
>  .BR MPOL_BIND ,
>  .BR MPOL_INTERLEAVE ,
> +.BR MPOL_WEIGHTED_INTERLEAVE ,
>  .BR MPOL_PREFERRED ,
>  or
>  .B MPOL_LOCAL
> @@ -243,6 +244,22 @@ at least 1\ MB or bigger with a fairly uniform access pattern.
>  Accesses to a single page of the area will still be limited to
>  the memory bandwidth of a single node.
>  .TP
> +.B MPOL_WEIGHTED_INTERLEAVE
> +This mode interleaves page allocations across the nodes specified in
> +.I nodemask
> +according to the weights in
> +.IR /sys/kernel/mm/mempolicy/weighted_interleave .
> +For example, if bits 0, 2, and 5 are raised in
> +.IR nodemask ,
> +and the contents of
> +.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
> +.IR /sys/.../node2 ,

Since ... is variable stuff inside an italicised word, according to the
groff_man_style(7) paragraph I quoted, it should be in Roman.  So,

.IR /sys/ ... /node2 ,

Also, for better formatting of the '...', we use \| between the dots,
which on proportional fonts (in PDF, or HTML, for example) will produce
nicer elipses.  So,

.IR /sys/ .\|.\|. /node2 ,

> +and
> +.I /sys/.../node5
> +are 4, 7, and 9, respectively,
> +then pages in this region will be allocated on nodes 0, 2, and 5
> +in a 4:7:9 ratio.
> +.TP
>  .B MPOL_PREFERRED
>  This mode sets the preferred node for allocation.
>  The kernel will try to allocate pages from this
> diff --git a/man2/set_mempolicy.2 b/man2/set_mempolicy.2
> index fc3ad9df8..6b51cb376 100644
> --- a/man2/set_mempolicy.2
> +++ b/man2/set_mempolicy.2
> @@ -63,6 +63,7 @@ argument must specify one of
>  .BR MPOL_DEFAULT ,
>  .BR MPOL_BIND ,
>  .BR MPOL_INTERLEAVE ,
> +.BR MPOL_WEIGHTED_INTERLEAVE ,
>  .BR MPOL_PREFERRED ,
>  or
>  .B MPOL_LOCAL
> @@ -199,6 +200,22 @@ the memory bandwidth of a single node.
>  .\" To be effective the memory area should be fairly large,
>  .\" at least 1 MB or bigger.
>  .TP
> +.B MPOL_WEIGHTED_INTERLEAVE
> +This mode interleaves page allocations across the nodes specified in
> +.I nodemask
> +according to the weights in
> +.IR /sys/kernel/mm/mempolicy/weighted_interleave .
> +For example, if bits 0, 2, and 5 are raised in
> +.IR nodemask ,
> +and the contents of
> +.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
> +.IR /sys/.../node2 ,
> +and
> +.I /sys/.../node5
> +are 4, 7, and 9, respectively,
> +then pages in this region will be allocated on nodes 0, 2, and 5
> +in a 4:7:9 ratio.
> +.TP
>  .B MPOL_PREFERRED
>  This mode sets the preferred node for allocation.
>  The kernel will try to allocate pages from this node first
> 
> ---
> base-commit: a4ea5f76215dcf1d8d017eb65ab12919ccf09f3f
> change-id: 20240313-weighted_interleave-e8141ed754f9
> 
> Best regards,
> -- 
> Svetly Todorov <svetly.todorov@memverge.com>
> 
> 

-- 
<https://www.alejandro-colomar.es/>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v3] man2: add MPOL_WEIGHTED_INTERLEAVE documentation
  2024-03-15 23:52 ` Alejandro Colomar
@ 2024-03-16 19:21   ` Svetly Todorov
  2024-03-16 19:36     ` Alejandro Colomar
  0 siblings, 1 reply; 4+ messages in thread
From: Svetly Todorov @ 2024-03-16 19:21 UTC (permalink / raw)
  To: Alejandro Colomar; +Cc: linux-man@vger.kernel.org, Gregory Price, Huang, Ying

Hi Alex,

Happy Saturday.

>> diff --git a/man2/get_mempolicy.2 b/man2/get_mempolicy.2
>> index 5248f04ba..03550331d 100644
>> --- a/man2/get_mempolicy.2
>> +++ b/man2/get_mempolicy.2
>> @@ -137,7 +137,9 @@ specifies
>> but not
>> .BR MPOL_F_ADDR ,
>> and the thread's current policy is
>> -.BR MPOL_INTERLEAVE ,
>> +.BR MPOL_INTERLEAVE
> 
> This should be B, not BR (BR is for alternating Bold and Roman).

Can’t believe I missed that!

> Or,
>> 
>> .I flags
>> specified
>> diff --git a/man2/mbind.2 b/man2/mbind.2
>> index b0e961f9c..6f85dec0e 100644
>> --- a/man2/mbind.2
>> +++ b/man2/mbind.2
>> @@ -105,6 +105,7 @@ argument must specify one of
>> .BR MPOL_DEFAULT ,
>> .BR MPOL_BIND ,
>> .BR MPOL_INTERLEAVE ,
>> +.BR MPOL_WEIGHTED_INTERLEAVE ,
>> .BR MPOL_PREFERRED ,
>> or
>> .B MPOL_LOCAL
>> @@ -243,6 +244,22 @@ at least 1\ MB or bigger with a fairly uniform access pattern.
>> Accesses to a single page of the area will still be limited to
>> the memory bandwidth of a single node.
>> .TP
>> +.B MPOL_WEIGHTED_INTERLEAVE
>> +This mode interleaves page allocations across the nodes specified in
>> +.I nodemask
>> +according to the weights in
>> +.IR /sys/kernel/mm/mempolicy/weighted_interleave .
>> +For example, if bits 0, 2, and 5 are raised in
>> +.IR nodemask ,
>> +and the contents of
>> +.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
>> +.IR /sys/.../node2 ,
> 
> Since ... is variable stuff inside an italicised word, according to the
> groff_man_style(7) paragraph I quoted, it should be in Roman.  So,
> 
> .IR /sys/ ... /node2 ,
> 
> Also, for better formatting of the '...', we use \| between the dots,
> which on proportional fonts (in PDF, or HTML, for example) will produce
> nicer elipses.  So,
> 
> .IR /sys/ .\|.\|. /node2 ,

This I was more unsure about.
I saw the quoted portion of groff (7) but since
the ellipses are a stand-in 'kernel/mm/mempolicy’, I figured
they technically *weren’t* a variable region, so I left them italicized...

I dunno. I was pretty fried yesterday. I’ll follow your lead on this,
and thank you for the \| tip.

Svetly


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v3] man2: add MPOL_WEIGHTED_INTERLEAVE documentation
  2024-03-16 19:21   ` Svetly Todorov
@ 2024-03-16 19:36     ` Alejandro Colomar
  0 siblings, 0 replies; 4+ messages in thread
From: Alejandro Colomar @ 2024-03-16 19:36 UTC (permalink / raw)
  To: Svetly Todorov; +Cc: linux-man@vger.kernel.org, Gregory Price, Huang, Ying

[-- Attachment #1: Type: text/plain, Size: 2626 bytes --]

Hi Svetly,

On Sat, Mar 16, 2024 at 07:21:21PM +0000, Svetly Todorov wrote:
> Hi Alex,
> 
> Happy Saturday.

Have a lovely Saturday!

> >> diff --git a/man2/get_mempolicy.2 b/man2/get_mempolicy.2
> >> index 5248f04ba..03550331d 100644
> >> --- a/man2/get_mempolicy.2
> >> +++ b/man2/get_mempolicy.2
> >> @@ -137,7 +137,9 @@ specifies
> >> but not
> >> .BR MPOL_F_ADDR ,
> >> and the thread's current policy is
> >> -.BR MPOL_INTERLEAVE ,
> >> +.BR MPOL_INTERLEAVE
> > 
> > This should be B, not BR (BR is for alternating Bold and Roman).
> 
> Can’t believe I missed that!
> 
> > Or,
> >> 
> >> .I flags
> >> specified
> >> diff --git a/man2/mbind.2 b/man2/mbind.2
> >> index b0e961f9c..6f85dec0e 100644
> >> --- a/man2/mbind.2
> >> +++ b/man2/mbind.2
> >> @@ -105,6 +105,7 @@ argument must specify one of
> >> .BR MPOL_DEFAULT ,
> >> .BR MPOL_BIND ,
> >> .BR MPOL_INTERLEAVE ,
> >> +.BR MPOL_WEIGHTED_INTERLEAVE ,
> >> .BR MPOL_PREFERRED ,
> >> or
> >> .B MPOL_LOCAL
> >> @@ -243,6 +244,22 @@ at least 1\ MB or bigger with a fairly uniform access pattern.
> >> Accesses to a single page of the area will still be limited to
> >> the memory bandwidth of a single node.
> >> .TP
> >> +.B MPOL_WEIGHTED_INTERLEAVE
> >> +This mode interleaves page allocations across the nodes specified in
> >> +.I nodemask
> >> +according to the weights in
> >> +.IR /sys/kernel/mm/mempolicy/weighted_interleave .
> >> +For example, if bits 0, 2, and 5 are raised in
> >> +.IR nodemask ,
> >> +and the contents of
> >> +.IR /sys/kernel/mm/mempolicy/weighted_interleave/node0 ,
> >> +.IR /sys/.../node2 ,
> > 
> > Since ... is variable stuff inside an italicised word, according to the
> > groff_man_style(7) paragraph I quoted, it should be in Roman.  So,
> > 
> > .IR /sys/ ... /node2 ,
> > 
> > Also, for better formatting of the '...', we use \| between the dots,
> > which on proportional fonts (in PDF, or HTML, for example) will produce
> > nicer elipses.  So,
> > 
> > .IR /sys/ .\|.\|. /node2 ,
> 
> This I was more unsure about.
> I saw the quoted portion of groff (7) but since
> the ellipses are a stand-in 'kernel/mm/mempolicy’, I figured
> they technically *weren’t* a variable region, so I left them italicized...
> 
> I dunno. I was pretty fried yesterday. I’ll follow your lead on this,
> and thank you for the \| tip.

The rule I follow to not have to think too much about it is:
if the user can copy it verbatim, then it's not a variable; otherwise,
it is.  :)

Cheers,
Alex

> 
> Svetly
> 

-- 
<https://www.alejandro-colomar.es/>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2024-03-16 19:36 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-03-15 23:43 [PATCH v3] man2: add MPOL_WEIGHTED_INTERLEAVE documentation Svetly Todorov
2024-03-15 23:52 ` Alejandro Colomar
2024-03-16 19:21   ` Svetly Todorov
2024-03-16 19:36     ` Alejandro Colomar

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox