diff mbox series

[RFC,2/4] mm/vmstat: Move pgdemote_* to per-node stats

Message ID 20231102025648.1285477-3-lizhijian@fujitsu.com (mailing list archive)
State New
Headers show
Series [RFC,1/4] drivers/base/node: Add demotion_nodes sys infterface | expand

Commit Message

Zhijian Li (Fujitsu) Nov. 2, 2023, 2:56 a.m. UTC 
This is a prepare to improve the demotion profiling in the later
patches.

Per-node demotion stats help users to quickly identify which
node is in hige stree, and take some special operations if needed.

Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
 include/linux/mmzone.h        | 4 ++++
 include/linux/vm_event_item.h | 3 ---
 mm/vmscan.c                   | 3 ++-
 mm/vmstat.c                   | 6 +++---
 4 files changed, 9 insertions(+), 7 deletions(-)

Comments

Huang, Ying Nov. 2, 2023, 4:56 a.m. UTC | #1 
Li Zhijian <lizhijian@fujitsu.com> writes:

> This is a prepare to improve the demotion profiling in the later
> patches.

I think that this patch has its value even without the following
patches.  So, don't need to define it as preparation.

> Per-node demotion stats help users to quickly identify which
> node is in hige stree, and take some special operations if needed.

Better to add more description.  For example, memory pressure on one
node, etc.

> Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>

After addressing the comments above, feel free to add

Acked-by: "Huang, Ying" <ying.huang@intel.com>

--
Best Regards,
Huang, Ying

> ---
>  include/linux/mmzone.h        | 4 ++++
>  include/linux/vm_event_item.h | 3 ---
>  mm/vmscan.c                   | 3 ++-
>  mm/vmstat.c                   | 6 +++---
>  4 files changed, 9 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 4106fbc5b4b3..ad0309eea850 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -206,6 +206,10 @@ enum node_stat_item {
>  #ifdef CONFIG_NUMA_BALANCING
>  	PGPROMOTE_SUCCESS,	/* promote successfully */
>  	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
> +	/* PGDEMOTE_*: pages demoted */
> +	PGDEMOTE_KSWAPD,
> +	PGDEMOTE_DIRECT,
> +	PGDEMOTE_KHUGEPAGED,
>  #endif
>  	NR_VM_NODE_STAT_ITEMS
>  };
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> index 8abfa1240040..d1b847502f09 100644
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  		PGSTEAL_KSWAPD,
>  		PGSTEAL_DIRECT,
>  		PGSTEAL_KHUGEPAGED,
> -		PGDEMOTE_KSWAPD,
> -		PGDEMOTE_DIRECT,
> -		PGDEMOTE_KHUGEPAGED,
>  		PGSCAN_KSWAPD,
>  		PGSCAN_DIRECT,
>  		PGSCAN_KHUGEPAGED,
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6f13394b112e..2f1fb4ec3235 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1678,7 +1678,8 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
>  		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
>  		      &nr_succeeded);
>  
> -	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
> +	mod_node_page_state(NODE_DATA(target_nid),
> +		    PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
>  
>  	return nr_succeeded;
>  }
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 00e81e99c6ee..f141c48c39e4 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1244,6 +1244,9 @@ const char * const vmstat_text[] = {
>  #ifdef CONFIG_NUMA_BALANCING
>  	"pgpromote_success",
>  	"pgpromote_candidate",
> +	"pgdemote_kswapd",
> +	"pgdemote_direct",
> +	"pgdemote_khugepaged",
>  #endif
>  
>  	/* enum writeback_stat_item counters */
> @@ -1275,9 +1278,6 @@ const char * const vmstat_text[] = {
>  	"pgsteal_kswapd",
>  	"pgsteal_direct",
>  	"pgsteal_khugepaged",
> -	"pgdemote_kswapd",
> -	"pgdemote_direct",
> -	"pgdemote_khugepaged",
>  	"pgscan_kswapd",
>  	"pgscan_direct",
>  	"pgscan_khugepaged",
Huang, Ying Nov. 2, 2023, 5:43 a.m. UTC | #2 
Li Zhijian <lizhijian@fujitsu.com> writes:

> This is a prepare to improve the demotion profiling in the later
> patches.
>
> Per-node demotion stats help users to quickly identify which
> node is in hige stree, and take some special operations if needed.
>
> Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
> ---
>  include/linux/mmzone.h        | 4 ++++
>  include/linux/vm_event_item.h | 3 ---
>  mm/vmscan.c                   | 3 ++-
>  mm/vmstat.c                   | 6 +++---
>  4 files changed, 9 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 4106fbc5b4b3..ad0309eea850 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -206,6 +206,10 @@ enum node_stat_item {
>  #ifdef CONFIG_NUMA_BALANCING
>  	PGPROMOTE_SUCCESS,	/* promote successfully */
>  	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
> +	/* PGDEMOTE_*: pages demoted */
> +	PGDEMOTE_KSWAPD,
> +	PGDEMOTE_DIRECT,
> +	PGDEMOTE_KHUGEPAGED,
>  #endif
>  	NR_VM_NODE_STAT_ITEMS
>  };
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> index 8abfa1240040..d1b847502f09 100644
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  		PGSTEAL_KSWAPD,
>  		PGSTEAL_DIRECT,
>  		PGSTEAL_KHUGEPAGED,
> -		PGDEMOTE_KSWAPD,
> -		PGDEMOTE_DIRECT,
> -		PGDEMOTE_KHUGEPAGED,
>  		PGSCAN_KSWAPD,
>  		PGSCAN_DIRECT,
>  		PGSCAN_KHUGEPAGED,
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6f13394b112e..2f1fb4ec3235 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1678,7 +1678,8 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
>  		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
>  		      &nr_succeeded);
>  
> -	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
> +	mod_node_page_state(NODE_DATA(target_nid),
> +		    PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);

Think again.  It seems that it's better to count demotion event for the
source node.  Because demotion comes from the memory pressure of the
source node.  The target node isn't so important.  Do you agree?

--
Best Regards,
Huang, Ying

>  
>  	return nr_succeeded;
>  }
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index 00e81e99c6ee..f141c48c39e4 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1244,6 +1244,9 @@ const char * const vmstat_text[] = {
>  #ifdef CONFIG_NUMA_BALANCING
>  	"pgpromote_success",
>  	"pgpromote_candidate",
> +	"pgdemote_kswapd",
> +	"pgdemote_direct",
> +	"pgdemote_khugepaged",
>  #endif
>  
>  	/* enum writeback_stat_item counters */
> @@ -1275,9 +1278,6 @@ const char * const vmstat_text[] = {
>  	"pgsteal_kswapd",
>  	"pgsteal_direct",
>  	"pgsteal_khugepaged",
> -	"pgdemote_kswapd",
> -	"pgdemote_direct",
> -	"pgdemote_khugepaged",
>  	"pgscan_kswapd",
>  	"pgscan_direct",
>  	"pgscan_khugepaged",
Zhijian Li (Fujitsu) Nov. 2, 2023, 5:57 a.m. UTC | #3 
On 02/11/2023 13:43, Huang, Ying wrote:
> Li Zhijian <lizhijian@fujitsu.com> writes:
> 
>> This is a prepare to improve the demotion profiling in the later
>> patches.
>>
>> Per-node demotion stats help users to quickly identify which
>> node is in hige stree, and take some special operations if needed.
>>
>> Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
>> ---
>>   include/linux/mmzone.h        | 4 ++++
>>   include/linux/vm_event_item.h | 3 ---
>>   mm/vmscan.c                   | 3 ++-
>>   mm/vmstat.c                   | 6 +++---
>>   4 files changed, 9 insertions(+), 7 deletions(-)
>>
>> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
>> index 4106fbc5b4b3..ad0309eea850 100644
>> --- a/include/linux/mmzone.h
>> +++ b/include/linux/mmzone.h
>> @@ -206,6 +206,10 @@ enum node_stat_item {
>>   #ifdef CONFIG_NUMA_BALANCING
>>   	PGPROMOTE_SUCCESS,	/* promote successfully */
>>   	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
>> +	/* PGDEMOTE_*: pages demoted */
>> +	PGDEMOTE_KSWAPD,
>> +	PGDEMOTE_DIRECT,
>> +	PGDEMOTE_KHUGEPAGED,
>>   #endif
>>   	NR_VM_NODE_STAT_ITEMS
>>   };
>> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
>> index 8abfa1240040..d1b847502f09 100644
>> --- a/include/linux/vm_event_item.h
>> +++ b/include/linux/vm_event_item.h
>> @@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>>   		PGSTEAL_KSWAPD,
>>   		PGSTEAL_DIRECT,
>>   		PGSTEAL_KHUGEPAGED,
>> -		PGDEMOTE_KSWAPD,
>> -		PGDEMOTE_DIRECT,
>> -		PGDEMOTE_KHUGEPAGED,
>>   		PGSCAN_KSWAPD,
>>   		PGSCAN_DIRECT,
>>   		PGSCAN_KHUGEPAGED,
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 6f13394b112e..2f1fb4ec3235 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -1678,7 +1678,8 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
>>   		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
>>   		      &nr_succeeded);
>>   
>> -	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
>> +	mod_node_page_state(NODE_DATA(target_nid),
>> +		    PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
> 
> Think again.  It seems that it's better to count demotion event for the
> source node.  Because demotion comes from the memory pressure of the
> source node.  The target node isn't so important.  Do you agree?

Good idea, I will update it.



> 
> --
> Best Regards,
> Huang, Ying
> 
>>   
>>   	return nr_succeeded;
>>   }
>> diff --git a/mm/vmstat.c b/mm/vmstat.c
>> index 00e81e99c6ee..f141c48c39e4 100644
>> --- a/mm/vmstat.c
>> +++ b/mm/vmstat.c
>> @@ -1244,6 +1244,9 @@ const char * const vmstat_text[] = {
>>   #ifdef CONFIG_NUMA_BALANCING
>>   	"pgpromote_success",
>>   	"pgpromote_candidate",
>> +	"pgdemote_kswapd",
>> +	"pgdemote_direct",
>> +	"pgdemote_khugepaged",
>>   #endif
>>   
>>   	/* enum writeback_stat_item counters */
>> @@ -1275,9 +1278,6 @@ const char * const vmstat_text[] = {
>>   	"pgsteal_kswapd",
>>   	"pgsteal_direct",
>>   	"pgsteal_khugepaged",
>> -	"pgdemote_kswapd",
>> -	"pgdemote_direct",
>> -	"pgdemote_khugepaged",
>>   	"pgscan_kswapd",
>>   	"pgscan_direct",
>>   	"pgscan_khugepaged",
diff mbox series

Patch

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4106fbc5b4b3..ad0309eea850 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,6 +206,10 @@  enum node_stat_item {
 #ifdef CONFIG_NUMA_BALANCING
 	PGPROMOTE_SUCCESS,	/* promote successfully */
 	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
+	/* PGDEMOTE_*: pages demoted */
+	PGDEMOTE_KSWAPD,
+	PGDEMOTE_DIRECT,
+	PGDEMOTE_KHUGEPAGED,
 #endif
 	NR_VM_NODE_STAT_ITEMS
 };
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 8abfa1240040..d1b847502f09 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -41,9 +41,6 @@  enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGSTEAL_KSWAPD,
 		PGSTEAL_DIRECT,
 		PGSTEAL_KHUGEPAGED,
-		PGDEMOTE_KSWAPD,
-		PGDEMOTE_DIRECT,
-		PGDEMOTE_KHUGEPAGED,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
 		PGSCAN_KHUGEPAGED,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6f13394b112e..2f1fb4ec3235 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1678,7 +1678,8 @@  static unsigned int demote_folio_list(struct list_head *demote_folios,
 		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
 		      &nr_succeeded);
 
-	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
+	mod_node_page_state(NODE_DATA(target_nid),
+		    PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
 
 	return nr_succeeded;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 00e81e99c6ee..f141c48c39e4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1244,6 +1244,9 @@  const char * const vmstat_text[] = {
 #ifdef CONFIG_NUMA_BALANCING
 	"pgpromote_success",
 	"pgpromote_candidate",
+	"pgdemote_kswapd",
+	"pgdemote_direct",
+	"pgdemote_khugepaged",
 #endif
 
 	/* enum writeback_stat_item counters */
@@ -1275,9 +1278,6 @@  const char * const vmstat_text[] = {
 	"pgsteal_kswapd",
 	"pgsteal_direct",
 	"pgsteal_khugepaged",
-	"pgdemote_kswapd",
-	"pgdemote_direct",
-	"pgdemote_khugepaged",
 	"pgscan_kswapd",
 	"pgscan_direct",
 	"pgscan_khugepaged",