Re: [RFC PATCH 2/3] mm, thp: convert from optimistic to conservative

[Ebru Akagunduz <ebru.akagunduz@gmail.com>]

On Sat, Jun 11, 2016 at 10:16:00PM +0300, Ebru Akagunduz wrote:
> Currently, khugepaged collapses pages saying only
> a referenced page enough to create a THP.
> 
> This patch changes the design from optimistic to conservative.
> It gives a default threshold which is half of HPAGE_PMD_NR
> for referenced pages, also introduces a new sysfs knob.
> 
> Signed-off-by: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Suggested-by: Minchan Kim <minchan@kernel.org> 
> ---
Cc'ed Minchan Kim.
>  include/trace/events/huge_memory.h | 10 ++++----
>  mm/khugepaged.c                    | 50 +++++++++++++++++++++++++++++---------
>  2 files changed, 44 insertions(+), 16 deletions(-)
> 
> diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
> index 830d47d..5f14025 100644
> --- a/include/trace/events/huge_memory.h
> +++ b/include/trace/events/huge_memory.h
> @@ -13,7 +13,7 @@
>  	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
>  	EM( SCAN_PTE_NON_PRESENT,	"pte_non_present")		\
>  	EM( SCAN_PAGE_RO,		"no_writable_page")		\
> -	EM( SCAN_NO_REFERENCED_PAGE,	"no_referenced_page")		\
> +	EM( SCAN_LACK_REFERENCED_PAGE,	"lack_referenced_page")		\
>  	EM( SCAN_PAGE_NULL,		"page_null")			\
>  	EM( SCAN_SCAN_ABORT,		"scan_aborted")			\
>  	EM( SCAN_PAGE_COUNT,		"not_suitable_page_count")	\
> @@ -47,7 +47,7 @@ SCAN_STATUS
>  TRACE_EVENT(mm_khugepaged_scan_pmd,
>  
>  	TP_PROTO(struct mm_struct *mm, struct page *page, bool writable,
> -		 bool referenced, int none_or_zero, int status, int unmapped),
> +		 int referenced, int none_or_zero, int status, int unmapped),
>  
>  	TP_ARGS(mm, page, writable, referenced, none_or_zero, status, unmapped),
>  
> @@ -55,7 +55,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
>  		__field(struct mm_struct *, mm)
>  		__field(unsigned long, pfn)
>  		__field(bool, writable)
> -		__field(bool, referenced)
> +		__field(int, referenced)
>  		__field(int, none_or_zero)
>  		__field(int, status)
>  		__field(int, unmapped)
> @@ -108,14 +108,14 @@ TRACE_EVENT(mm_collapse_huge_page,
>  TRACE_EVENT(mm_collapse_huge_page_isolate,
>  
>  	TP_PROTO(struct page *page, int none_or_zero,
> -		 bool referenced, bool  writable, int status),
> +		 int referenced, bool  writable, int status),
>  
>  	TP_ARGS(page, none_or_zero, referenced, writable, status),
>  
>  	TP_STRUCT__entry(
>  		__field(unsigned long, pfn)
>  		__field(int, none_or_zero)
> -		__field(bool, referenced)
> +		__field(int, referenced)
>  		__field(bool, writable)
>  		__field(int, status)
>  	),
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index e3d8da7..43fc41e 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -27,7 +27,7 @@ enum scan_result {
>  	SCAN_EXCEED_NONE_PTE,
>  	SCAN_PTE_NON_PRESENT,
>  	SCAN_PAGE_RO,
> -	SCAN_NO_REFERENCED_PAGE,
> +	SCAN_LACK_REFERENCED_PAGE,
>  	SCAN_PAGE_NULL,
>  	SCAN_SCAN_ABORT,
>  	SCAN_PAGE_COUNT,
> @@ -68,6 +68,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
>   */
>  static unsigned int khugepaged_max_ptes_none __read_mostly;
>  static unsigned int khugepaged_max_ptes_swap __read_mostly;
> +static unsigned int khugepaged_min_ptes_young __read_mostly;
>  
>  static int khugepaged(void *none);
>  
> @@ -282,6 +283,32 @@ static struct kobj_attribute khugepaged_max_ptes_swap_attr =
>  	__ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show,
>  	       khugepaged_max_ptes_swap_store);
>  
> +static ssize_t khugepaged_min_ptes_young_show(struct kobject *kobj,
> +					      struct kobj_attribute *attr,
> +					      char *buf)
> +{
> +	return sprintf(buf, "%u\n", khugepaged_min_ptes_young);
> +}
> +
> +static ssize_t khugepaged_min_ptes_young_store(struct kobject *kobj,
> +					       struct kobj_attribute *attr,
> +					       const char *buf, size_t count)
> +{
> +	int err;
> +	unsigned long min_ptes_young;
> +	err  = kstrtoul(buf, 10, &min_ptes_young);
> +	if (err || min_ptes_young > HPAGE_PMD_NR-1)
> +		return -EINVAL;
> +
> +	khugepaged_min_ptes_young = min_ptes_young;
> +
> +	return count;
> +}
> +
> +static struct kobj_attribute khugepaged_min_ptes_young_attr =
> +		__ATTR(min_ptes_young, 0644, khugepaged_min_ptes_young_show,
> +		khugepaged_min_ptes_young_store);
> +
>  static struct attribute *khugepaged_attr[] = {
>  	&khugepaged_defrag_attr.attr,
>  	&khugepaged_max_ptes_none_attr.attr,
> @@ -291,6 +318,7 @@ static struct attribute *khugepaged_attr[] = {
>  	&scan_sleep_millisecs_attr.attr,
>  	&alloc_sleep_millisecs_attr.attr,
>  	&khugepaged_max_ptes_swap_attr.attr,
> +	&khugepaged_min_ptes_young_attr.attr,
>  	NULL,
>  };
>  
> @@ -502,8 +530,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>  {
>  	struct page *page = NULL;
>  	pte_t *_pte;
> -	int none_or_zero = 0, result = 0;
> -	bool referenced = false, writable = false;
> +	int none_or_zero = 0, result = 0, referenced = 0;
> +	bool writable = false;
>  
>  	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
>  	     _pte++, address += PAGE_SIZE) {
> @@ -582,14 +610,14 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>  		VM_BUG_ON_PAGE(!PageLocked(page), page);
>  		VM_BUG_ON_PAGE(PageLRU(page), page);
>  
> -		/* If there is no mapped pte young don't collapse the page */
> +		/* There should be enough young pte to collapse the page */
>  		if (pte_young(pteval) ||
>  		    page_is_young(page) || PageReferenced(page) ||
>  		    mmu_notifier_test_young(vma->vm_mm, address))
> -			referenced = true;
> +			referenced++;
>  	}
>  	if (likely(writable)) {
> -		if (likely(referenced)) {
> +		if (referenced >= khugepaged_min_ptes_young) {
>  			result = SCAN_SUCCEED;
>  			trace_mm_collapse_huge_page_isolate(page, none_or_zero,
>  							    referenced, writable, result);
> @@ -1082,11 +1110,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>  	pmd_t *pmd;
>  	pte_t *pte, *_pte;
>  	int ret = 0, none_or_zero = 0, result = 0;
> +	int node = NUMA_NO_NODE, unmapped = 0, referenced = 0;
>  	struct page *page = NULL;
>  	unsigned long _address;
>  	spinlock_t *ptl;
> -	int node = NUMA_NO_NODE, unmapped = 0;
> -	bool writable = false, referenced = false;
> +	bool writable = false;
>  
>  	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
>  
> @@ -1174,14 +1202,14 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
>  		if (pte_young(pteval) ||
>  		    page_is_young(page) || PageReferenced(page) ||
>  		    mmu_notifier_test_young(vma->vm_mm, address))
> -			referenced = true;
> +			referenced++;
>  	}
>  	if (writable) {
> -		if (referenced) {
> +		if (referenced >= khugepaged_min_ptes_young) {
>  			result = SCAN_SUCCEED;
>  			ret = 1;
>  		} else {
> -			result = SCAN_NO_REFERENCED_PAGE;
> +			result = SCAN_LACK_REFERENCED_PAGE;
>  		}
>  	} else {
>  		result = SCAN_PAGE_RO;
> -- 
> 1.9.1
> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>