[PATCH resend] mm: compaction: optimize proactive compaction deferrals

[PATCH resend] mm: compaction: optimize proactive compaction deferrals

[Charan Teja Reddy]

Vlastimil Babka figured out that when fragmentation score didn't go down
across the proactive compaction i.e. when no progress is made, next wake
up for proactive compaction is deferred for 1 <<
COMPACT_MAX_DEFER_SHIFT, i.e. 64 times, with each wakeup interval of
HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500). In each of this wakeup, it just
decrement 'proactive_defer' counter and goes sleep i.e. it is getting
woken to just decrement a counter. The same deferral time can also
achieved by simply doing the HPAGE_FRAG_CHECK_INTERVAL_MSEC <<
COMPACT_MAX_DEFER_SHIFT thus unnecessary wakeup of kcompact thread is
avoided thus also removes the need of 'proactive_defer' thread counter.

Link: https://lore.kernel.org/linux-fsdevel/88abfdb6-2c13-b5a6-5b46-742d12d1c910@suse.cz/
Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>
---
 Changes in V1:
    o Removed the 'proactive_defer' thread counter by optimizing proactive
    o This is a resend as earlier it was clubbed with other changes posted
      at https://lore.kernel.org/patchwork/patch/1448789/	

 mm/compaction.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 621508e..db00dbf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2885,7 +2885,8 @@ static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t *)p;
 	struct task_struct *tsk = current;
-	unsigned int proactive_defer = 0;
+	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
+	long timeout = default_timeout;
 
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -2902,23 +2903,30 @@ static int kcompactd(void *p)
 
 		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
 		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
-			kcompactd_work_requested(pgdat),
-			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
+			kcompactd_work_requested(pgdat), timeout)) {
 
 			psi_memstall_enter(&pflags);
 			kcompactd_do_work(pgdat);
 			psi_memstall_leave(&pflags);
+			/*
+			 * Reset the timeout value. The defer timeout by
+			 * proactive compaction can effectively lost
+			 * here but that is fine as the condition of the
+			 * zone changed substantionally and carrying on
+			 * with the previous defer is not useful.
+			 */
+			timeout = default_timeout;
 			continue;
 		}
 
-		/* kcompactd wait timeout */
+		/*
+		 * Start the proactive work with default timeout. Based
+		 * on the fragmentation score, this timeout is updated.
+		 */
+		timeout = default_timeout;
 		if (should_proactive_compact_node(pgdat)) {
 			unsigned int prev_score, score;
 
-			if (proactive_defer) {
-				proactive_defer--;
-				continue;
-			}
 			prev_score = fragmentation_score_node(pgdat);
 			proactive_compact_node(pgdat);
 			score = fragmentation_score_node(pgdat);
@@ -2926,8 +2934,9 @@ static int kcompactd(void *p)
 			 * Defer proactive compaction if the fragmentation
 			 * score did not go down i.e. no progress made.
 			 */
-			proactive_defer = score < prev_score ?
-					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+			if (unlikely(score >= prev_score))
+				timeout =
+				   default_timeout << COMPACT_MAX_DEFER_SHIFT;
 		}
 	}
 
-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a
member of the Code Aurora Forum, hosted by The Linux Foundation

Re: [PATCH resend] mm: compaction: optimize proactive compaction deferrals

[Andrew Morton]

On Wed, 21 Jul 2021 17:43:19 +0530 Charan Teja Reddy <charante@codeaurora.org> wrote:

> Vlastimil Babka figured out that when fragmentation score didn't go down
> across the proactive compaction i.e. when no progress is made, next wake
> up for proactive compaction is deferred for 1 <<
> COMPACT_MAX_DEFER_SHIFT, i.e. 64 times, with each wakeup interval of
> HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500). In each of this wakeup, it just
> decrement 'proactive_defer' counter and goes sleep i.e. it is getting
> woken to just decrement a counter. The same deferral time can also
> achieved by simply doing the HPAGE_FRAG_CHECK_INTERVAL_MSEC <<
> COMPACT_MAX_DEFER_SHIFT thus unnecessary wakeup of kcompact thread is
> avoided thus also removes the need of 'proactive_defer' thread counter.
> 
> @@ -2902,23 +2903,30 @@ static int kcompactd(void *p)
>  
>  		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
>  		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
> -			kcompactd_work_requested(pgdat),
> -			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
> +			kcompactd_work_requested(pgdat), timeout)) {
>  
>  			psi_memstall_enter(&pflags);
>  			kcompactd_do_work(pgdat);
>  			psi_memstall_leave(&pflags);
> +			/*
> +			 * Reset the timeout value. The defer timeout by
> +			 * proactive compaction can effectively lost
> +			 * here but that is fine as the condition of the
> +			 * zone changed substantionally and carrying on
> +			 * with the previous defer is not useful.
> +			 */
> +			timeout = default_timeout;
>  			continue;

I find this comment hard to follow.  Is this better?

--- a/mm/compaction.c~mm-compaction-optimize-proactive-compaction-deferrals-fix
+++ a/mm/compaction.c
@@ -2909,11 +2909,11 @@ static int kcompactd(void *p)
 			kcompactd_do_work(pgdat);
 			psi_memstall_leave(&pflags);
 			/*
-			 * Reset the timeout value. The defer timeout by
-			 * proactive compaction can effectively lost
-			 * here but that is fine as the condition of the
-			 * zone changed substantionally and carrying on
-			 * with the previous defer is not useful.
+			 * Reset the timeout value. The defer timeout from
+			 * proactive compaction is lost here but that is fine
+			 * as the condition of the zone changing substantionally
+			 * then carrying on with the previous defer interval is
+			 * not useful.
 			 */
 			timeout = default_timeout;
 			continue;
_

Re: [PATCH resend] mm: compaction: optimize proactive compaction deferrals

[Vlastimil Babka]

On 7/21/21 10:18 PM, Andrew Morton wrote:
> On Wed, 21 Jul 2021 17:43:19 +0530 Charan Teja Reddy <charante@codeaurora.org> wrote:
> 
>> Vlastimil Babka figured out that when fragmentation score didn't go down
>> across the proactive compaction i.e. when no progress is made, next wake
>> up for proactive compaction is deferred for 1 <<
>> COMPACT_MAX_DEFER_SHIFT, i.e. 64 times, with each wakeup interval of
>> HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500). In each of this wakeup, it just
>> decrement 'proactive_defer' counter and goes sleep i.e. it is getting
>> woken to just decrement a counter. The same deferral time can also
>> achieved by simply doing the HPAGE_FRAG_CHECK_INTERVAL_MSEC <<
>> COMPACT_MAX_DEFER_SHIFT thus unnecessary wakeup of kcompact thread is
>> avoided thus also removes the need of 'proactive_defer' thread counter.

Acked-by: Vlastimil Babka <vbabka@suse.cz>

>>
>> @@ -2902,23 +2903,30 @@ static int kcompactd(void *p)
>>  
>>  		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
>>  		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
>> -			kcompactd_work_requested(pgdat),
>> -			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
>> +			kcompactd_work_requested(pgdat), timeout)) {
>>  
>>  			psi_memstall_enter(&pflags);
>>  			kcompactd_do_work(pgdat);
>>  			psi_memstall_leave(&pflags);
>> +			/*
>> +			 * Reset the timeout value. The defer timeout by
>> +			 * proactive compaction can effectively lost
>> +			 * here but that is fine as the condition of the
>> +			 * zone changed substantionally and carrying on
>> +			 * with the previous defer is not useful.
>> +			 */
>> +			timeout = default_timeout;
>>  			continue;
> 
> I find this comment hard to follow.  Is this better?

Yes, thanks.

> --- a/mm/compaction.c~mm-compaction-optimize-proactive-compaction-deferrals-fix
> +++ a/mm/compaction.c
> @@ -2909,11 +2909,11 @@ static int kcompactd(void *p)
>  			kcompactd_do_work(pgdat);
>  			psi_memstall_leave(&pflags);
>  			/*
> -			 * Reset the timeout value. The defer timeout by
> -			 * proactive compaction can effectively lost
> -			 * here but that is fine as the condition of the
> -			 * zone changed substantionally and carrying on
> -			 * with the previous defer is not useful.
> +			 * Reset the timeout value. The defer timeout from
> +			 * proactive compaction is lost here but that is fine
> +			 * as the condition of the zone changing substantionally
> +			 * then carrying on with the previous defer interval is
> +			 * not useful.
>  			 */
>  			timeout = default_timeout;
>  			continue;
> _
> 

Re: [PATCH resend] mm: compaction: optimize proactive compaction deferrals

[Khalid Aziz]

On 7/21/21 6:13 AM, Charan Teja Reddy wrote:
> Vlastimil Babka figured out that when fragmentation score didn't go down
> across the proactive compaction i.e. when no progress is made, next wake
> up for proactive compaction is deferred for 1 <<
> COMPACT_MAX_DEFER_SHIFT, i.e. 64 times, with each wakeup interval of
> HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500). In each of this wakeup, it just
> decrement 'proactive_defer' counter and goes sleep i.e. it is getting
> woken to just decrement a counter. The same deferral time can also
> achieved by simply doing the HPAGE_FRAG_CHECK_INTERVAL_MSEC <<
> COMPACT_MAX_DEFER_SHIFT thus unnecessary wakeup of kcompact thread is
> avoided thus also removes the need of 'proactive_defer' thread counter.
> 
> Link: https://lore.kernel.org/linux-fsdevel/88abfdb6-2c13-b5a6-5b46-742d12d1c910@suse.cz/
> Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>


Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>


> ---
>   Changes in V1:
>      o Removed the 'proactive_defer' thread counter by optimizing proactive
>      o This is a resend as earlier it was clubbed with other changes posted
>        at https://lore.kernel.org/patchwork/patch/1448789/	
> 
>   mm/compaction.c | 29 +++++++++++++++++++----------
>   1 file changed, 19 insertions(+), 10 deletions(-)
> 
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 621508e..db00dbf 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -2885,7 +2885,8 @@ static int kcompactd(void *p)
>   {
>   	pg_data_t *pgdat = (pg_data_t *)p;
>   	struct task_struct *tsk = current;
> -	unsigned int proactive_defer = 0;
> +	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
> +	long timeout = default_timeout;
>   
>   	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
>   
> @@ -2902,23 +2903,30 @@ static int kcompactd(void *p)
>   
>   		trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
>   		if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
> -			kcompactd_work_requested(pgdat),
> -			msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
> +			kcompactd_work_requested(pgdat), timeout)) {
>   
>   			psi_memstall_enter(&pflags);
>   			kcompactd_do_work(pgdat);
>   			psi_memstall_leave(&pflags);
> +			/*
> +			 * Reset the timeout value. The defer timeout by
> +			 * proactive compaction can effectively lost
> +			 * here but that is fine as the condition of the
> +			 * zone changed substantionally and carrying on
> +			 * with the previous defer is not useful.
> +			 */
> +			timeout = default_timeout;
>   			continue;
>   		}
>   
> -		/* kcompactd wait timeout */
> +		/*
> +		 * Start the proactive work with default timeout. Based
> +		 * on the fragmentation score, this timeout is updated.
> +		 */
> +		timeout = default_timeout;
>   		if (should_proactive_compact_node(pgdat)) {
>   			unsigned int prev_score, score;
>   
> -			if (proactive_defer) {
> -				proactive_defer--;
> -				continue;
> -			}
>   			prev_score = fragmentation_score_node(pgdat);
>   			proactive_compact_node(pgdat);
>   			score = fragmentation_score_node(pgdat);
> @@ -2926,8 +2934,9 @@ static int kcompactd(void *p)
>   			 * Defer proactive compaction if the fragmentation
>   			 * score did not go down i.e. no progress made.
>   			 */
> -			proactive_defer = score < prev_score ?
> -					0 : 1 << COMPACT_MAX_DEFER_SHIFT;
> +			if (unlikely(score >= prev_score))
> +				timeout =
> +				   default_timeout << COMPACT_MAX_DEFER_SHIFT;
>   		}
>   	}
>   
> 

Re: [PATCH resend] mm: compaction: optimize proactive compaction deferrals

[David Rientjes]

On Wed, 21 Jul 2021, Charan Teja Reddy wrote:

> Vlastimil Babka figured out that when fragmentation score didn't go down
> across the proactive compaction i.e. when no progress is made, next wake
> up for proactive compaction is deferred for 1 <<
> COMPACT_MAX_DEFER_SHIFT, i.e. 64 times, with each wakeup interval of
> HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500). In each of this wakeup, it just
> decrement 'proactive_defer' counter and goes sleep i.e. it is getting
> woken to just decrement a counter. The same deferral time can also
> achieved by simply doing the HPAGE_FRAG_CHECK_INTERVAL_MSEC <<
> COMPACT_MAX_DEFER_SHIFT thus unnecessary wakeup of kcompact thread is
> avoided thus also removes the need of 'proactive_defer' thread counter.
> 
> Link: https://lore.kernel.org/linux-fsdevel/88abfdb6-2c13-b5a6-5b46-742d12d1c910@suse.cz/
> Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>

With Andrew's comment fixup:

Acked-by: David Rientjes <rientjes@google.com>

Thanks, Charan.

Re: [PATCH resend] mm: compaction: optimize proactive compaction deferrals

[David Rientjes]

On Wed, 21 Jul 2021, Charan Teja Reddy wrote:

> Vlastimil Babka figured out that when fragmentation score didn't go down
> across the proactive compaction i.e. when no progress is made, next wake
> up for proactive compaction is deferred for 1 <<
> COMPACT_MAX_DEFER_SHIFT, i.e. 64 times, with each wakeup interval of
> HPAGE_FRAG_CHECK_INTERVAL_MSEC(=500). In each of this wakeup, it just
> decrement 'proactive_defer' counter and goes sleep i.e. it is getting
> woken to just decrement a counter. The same deferral time can also
> achieved by simply doing the HPAGE_FRAG_CHECK_INTERVAL_MSEC <<
> COMPACT_MAX_DEFER_SHIFT thus unnecessary wakeup of kcompact thread is
> avoided thus also removes the need of 'proactive_defer' thread counter.
> 
> Link: https://lore.kernel.org/linux-fsdevel/88abfdb6-2c13-b5a6-5b46-742d12d1c910@suse.cz/
> Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>

With Andrew's comment fixup:

Acked-by: David Rientjes <rientjes@google.com>

Thanks, Charan.