Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1205947 > unrolled thread

[PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled Mel Gorman <mgorman@techsingularity.net> - 2015-08-12 12:50 +0200
    Re: [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a  seqlock when cpusets are disabled David Rientjes <rientjes@google.com> - 2015-08-13 02:20 +0200
      Re: [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a  seqlock when cpusets are disabled Mel Gorman <mgorman@techsingularity.net> - 2015-08-17 14:00 +0200

#1205947 — [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled

There is a seqcounter that protects against spurious allocation failures
when a task is changing the allowed nodes in a cpuset. There is no need
to check the seqcounter until a cpuset exists.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/cpuset.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 1b357997cac5..6eb27cb480b7 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -104,6 +104,9 @@ extern void cpuset_print_task_mems_allowed(struct task_struct *p);
  */
 static inline unsigned int read_mems_allowed_begin(void)
 {
+	if (!cpusets_enabled())
+		return 0;
+
 	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
@@ -115,6 +118,9 @@ static inline unsigned int read_mems_allowed_begin(void)
  */
 static inline bool read_mems_allowed_retry(unsigned int seq)
 {
+	if (!cpusets_enabled())
+		return false;
+
 	return read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
-- 
2.4.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1206434 — Re: [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled

On Wed, 12 Aug 2015, Mel Gorman wrote:

> There is a seqcounter that protects against spurious allocation failures
> when a task is changing the allowed nodes in a cpuset. There is no need
> to check the seqcounter until a cpuset exists.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> Acked-by: David Rientjes <rientjes@google.com>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> ---
>  include/linux/cpuset.h | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
> index 1b357997cac5..6eb27cb480b7 100644
> --- a/include/linux/cpuset.h
> +++ b/include/linux/cpuset.h
> @@ -104,6 +104,9 @@ extern void cpuset_print_task_mems_allowed(struct task_struct *p);
>   */
>  static inline unsigned int read_mems_allowed_begin(void)
>  {
> +	if (!cpusets_enabled())
> +		return 0;
> +
>  	return read_seqcount_begin(&current->mems_allowed_seq);
>  }
>  
> @@ -115,6 +118,9 @@ static inline unsigned int read_mems_allowed_begin(void)
>   */
>  static inline bool read_mems_allowed_retry(unsigned int seq)
>  {
> +	if (!cpusets_enabled())
> +		return false;
> +
>  	return read_seqcount_retry(&current->mems_allowed_seq, seq);
>  }
>  

This patch is an obvious improvement, but I think it's also possible to 
change this to be

	if (nr_cpusets() <= 1)
		return false;

and likewise in the existing cpusets_enabled() check in 
get_page_from_freelist().  A root cpuset may not exclude mems on the 
system so, even if mounted, there's no need to check or be worried about 
concurrent change when there is only one cpuset.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1208554 — Re: [PATCH 04/10] mm, page_alloc: Remove unnecessary taking of a seqlock when cpusets are disabled

On Wed, Aug 12, 2015 at 05:16:50PM -0700, David Rientjes wrote:
> On Wed, 12 Aug 2015, Mel Gorman wrote:
> 
> > There is a seqcounter that protects against spurious allocation failures
> > when a task is changing the allowed nodes in a cpuset. There is no need
> > to check the seqcounter until a cpuset exists.
> > 
> > Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> > Acked-by: David Rientjes <rientjes@google.com>
> > Acked-by: Vlastimil Babka <vbabka@suse.cz>
> > ---
> >  include/linux/cpuset.h | 6 ++++++
> >  1 file changed, 6 insertions(+)
> > 
> > diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
> > index 1b357997cac5..6eb27cb480b7 100644
> > --- a/include/linux/cpuset.h
> > +++ b/include/linux/cpuset.h
> > @@ -104,6 +104,9 @@ extern void cpuset_print_task_mems_allowed(struct task_struct *p);
> >   */
> >  static inline unsigned int read_mems_allowed_begin(void)
> >  {
> > +	if (!cpusets_enabled())
> > +		return 0;
> > +
> >  	return read_seqcount_begin(&current->mems_allowed_seq);
> >  }
> >  
> > @@ -115,6 +118,9 @@ static inline unsigned int read_mems_allowed_begin(void)
> >   */
> >  static inline bool read_mems_allowed_retry(unsigned int seq)
> >  {
> > +	if (!cpusets_enabled())
> > +		return false;
> > +
> >  	return read_seqcount_retry(&current->mems_allowed_seq, seq);
> >  }
> >  
> 
> This patch is an obvious improvement, but I think it's also possible to 
> change this to be
> 
> 	if (nr_cpusets() <= 1)
> 		return false;
> 
> and likewise in the existing cpusets_enabled() check in 
> get_page_from_freelist().  A root cpuset may not exclude mems on the 
> system so, even if mounted, there's no need to check or be worried about 
> concurrent change when there is only one cpuset.

Good idea. I'll make this a separate patch on top and rename cpuset_enabled
to cpuset_mems_enabled to be clear about what it's checking.

Thanks.

-- 
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web