[patch 1/2] mm, shmem: add vmstat for hugepage fallback

[patch 1/2] mm, shmem: add vmstat for hugepage fallback

[David Rientjes]

The existing thp_fault_fallback indicates when thp attempts to allocate a
hugepage but fails, or if the hugepage cannot be charged to the mem cgroup
hierarchy.

Extend this to shmem as well.  Adds a new thp_file_fallback to complement
thp_file_alloc that gets incremented when a hugepage is attempted to be
allocated but fails, or if it cannot be charged to the mem cgroup
hierarchy.

Additionally, remove the check for CONFIG_TRANSPARENT_HUGE_PAGECACHE from
shmem_alloc_hugepage() since it is only called with this configuration
option.

Signed-off-by: David Rientjes <rientjes@google.com>
---
 Documentation/admin-guide/mm/transhuge.rst |  4 ++++
 include/linux/vm_event_item.h              |  2 ++
 mm/shmem.c                                 | 10 ++++++----
 mm/vmstat.c                                |  1 +
 4 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -319,6 +319,10 @@ thp_file_alloc
 	is incremented every time a file huge page is successfully
 	allocated.
 
+thp_file_fallback
+	is incremented if a file huge page is attempted to be allocated
+	but fails and instead falls back to using small pages.
+
 thp_file_mapped
 	is incremented every time a file huge page is mapped into
 	user address space.
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -76,6 +76,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_COLLAPSE_ALLOC,
 		THP_COLLAPSE_ALLOC_FAILED,
 		THP_FILE_ALLOC,
+		THP_FILE_FALLBACK,
 		THP_FILE_MAPPED,
 		THP_SPLIT_PAGE,
 		THP_SPLIT_PAGE_FAILED,
@@ -115,6 +116,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
+#define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
 #define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
 #endif
 
diff --git a/mm/shmem.c b/mm/shmem.c
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1472,9 +1472,6 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 	pgoff_t hindex;
 	struct page *page;
 
-	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
-		return NULL;
-
 	hindex = round_down(index, HPAGE_PMD_NR);
 	if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1,
 								XA_PRESENT))
@@ -1486,6 +1483,8 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 	shmem_pseudo_vma_destroy(&pvma);
 	if (page)
 		prep_transhuge_page(page);
+	else
+		count_vm_event(THP_FILE_FALLBACK);
 	return page;
 }
 
@@ -1871,8 +1870,11 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 					    PageTransHuge(page));
-	if (error)
+	if (error) {
+		if (PageTransHuge(page))
+			count_vm_event(THP_FILE_FALLBACK);
 		goto unacct;
+	}
 	error = shmem_add_to_page_cache(page, mapping, hindex,
 					NULL, gfp & GFP_RECLAIM_MASK);
 	if (error) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1257,6 +1257,7 @@ const char * const vmstat_text[] = {
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
 	"thp_file_alloc",
+	"thp_file_fallback",
 	"thp_file_mapped",
 	"thp_split_page",
 	"thp_split_page_failed",

[patch 2/2] mm, thp: track fallbacks due to failed memcg charges separately

[David Rientjes]

The thp_fault_fallback and thp_file_fallback vmstats are incremented if
either the hugepage allocation fails through the page allocator or the
hugepage charge fails through mem cgroup.

This patch leaves this field untouched but adds two new fields,
thp_{fault,file}_fallback_charge, which is incremented only when the mem
cgroup charge fails.

This distinguishes between attempted hugepage allocations that fail due to
fragmentation (or low memory conditions) and those that fail due to mem
cgroup limits.  That can be used to determine the impact of fragmentation
on the system by excluding faults that failed due to memcg usage.

Signed-off-by: David Rientjes <rientjes@google.com>
---
 Documentation/admin-guide/mm/transhuge.rst | 10 ++++++++++
 include/linux/vm_event_item.h              |  3 +++
 mm/huge_memory.c                           |  2 ++
 mm/shmem.c                                 |  4 +++-
 mm/vmstat.c                                |  2 ++
 5 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -310,6 +310,11 @@ thp_fault_fallback
 	is incremented if a page fault fails to allocate
 	a huge page and instead falls back to using small pages.
 
+thp_fault_fallback_charge
+	is incremented if a page fault fails to charge a huge page and
+	instead falls back to using small pages even though the
+	allocation was successful.
+
 thp_collapse_alloc_failed
 	is incremented if khugepaged found a range
 	of pages that should be collapsed into one huge page but failed
@@ -323,6 +328,11 @@ thp_file_fallback
 	is incremented if a file huge page is attempted to be allocated
 	but fails and instead falls back to using small pages.
 
+thp_file_fallback_charge
+	is incremented if a file huge page cannot be charged and instead
+	falls back to using small pages even though the allocation was
+	successful.
+
 thp_file_mapped
 	is incremented every time a file huge page is mapped into
 	user address space.
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -73,10 +73,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		THP_FAULT_ALLOC,
 		THP_FAULT_FALLBACK,
+		THP_FAULT_FALLBACK_CHARGE,
 		THP_COLLAPSE_ALLOC,
 		THP_COLLAPSE_ALLOC_FAILED,
 		THP_FILE_ALLOC,
 		THP_FILE_FALLBACK,
+		THP_FILE_FALLBACK_CHARGE,
 		THP_FILE_MAPPED,
 		THP_SPLIT_PAGE,
 		THP_SPLIT_PAGE_FAILED,
@@ -117,6 +119,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
 #define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
+#define THP_FILE_FALLBACK_CHARGE ({ BUILD_BUG(); 0; })
 #define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
 #endif
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
 
@@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 			put_page(page);
 		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		goto out;
 	}
 
diff --git a/mm/shmem.c b/mm/shmem.c
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1871,8 +1871,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 					    PageTransHuge(page));
 	if (error) {
-		if (PageTransHuge(page))
+		if (PageTransHuge(page)) {
 			count_vm_event(THP_FILE_FALLBACK);
+			count_vm_event(THP_FILE_FALLBACK_CHARGE);
+		}
 		goto unacct;
 	}
 	error = shmem_add_to_page_cache(page, mapping, hindex,
diff --git a/mm/vmstat.c b/mm/vmstat.c
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1254,10 +1254,12 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	"thp_fault_alloc",
 	"thp_fault_fallback",
+	"thp_fault_fallback_charge",
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
 	"thp_file_alloc",
 	"thp_file_fallback",
+	"thp_file_fallback_charge",
 	"thp_file_mapped",
 	"thp_split_page",
 	"thp_split_page_failed",

Re: [patch 2/2] mm, thp: track fallbacks due to failed memcg charges separately

[Yang Shi]

On Fri, Mar 6, 2020 at 2:22 PM David Rientjes <rientjes@google.com> wrote:
>
> The thp_fault_fallback and thp_file_fallback vmstats are incremented if
> either the hugepage allocation fails through the page allocator or the
> hugepage charge fails through mem cgroup.
>
> This patch leaves this field untouched but adds two new fields,
> thp_{fault,file}_fallback_charge, which is incremented only when the mem
> cgroup charge fails.
>
> This distinguishes between attempted hugepage allocations that fail due to
> fragmentation (or low memory conditions) and those that fail due to mem
> cgroup limits.  That can be used to determine the impact of fragmentation
> on the system by excluding faults that failed due to memcg usage.

Yes, it makes sense to me.

Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com>

>
> Signed-off-by: David Rientjes <rientjes@google.com>
> ---
>  Documentation/admin-guide/mm/transhuge.rst | 10 ++++++++++
>  include/linux/vm_event_item.h              |  3 +++
>  mm/huge_memory.c                           |  2 ++
>  mm/shmem.c                                 |  4 +++-
>  mm/vmstat.c                                |  2 ++
>  5 files changed, 20 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -310,6 +310,11 @@ thp_fault_fallback
>         is incremented if a page fault fails to allocate
>         a huge page and instead falls back to using small pages.
>
> +thp_fault_fallback_charge
> +       is incremented if a page fault fails to charge a huge page and
> +       instead falls back to using small pages even though the
> +       allocation was successful.
> +
>  thp_collapse_alloc_failed
>         is incremented if khugepaged found a range
>         of pages that should be collapsed into one huge page but failed
> @@ -323,6 +328,11 @@ thp_file_fallback
>         is incremented if a file huge page is attempted to be allocated
>         but fails and instead falls back to using small pages.
>
> +thp_file_fallback_charge
> +       is incremented if a file huge page cannot be charged and instead
> +       falls back to using small pages even though the allocation was
> +       successful.
> +
>  thp_file_mapped
>         is incremented every time a file huge page is mapped into
>         user address space.
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -73,10 +73,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>                 THP_FAULT_ALLOC,
>                 THP_FAULT_FALLBACK,
> +               THP_FAULT_FALLBACK_CHARGE,
>                 THP_COLLAPSE_ALLOC,
>                 THP_COLLAPSE_ALLOC_FAILED,
>                 THP_FILE_ALLOC,
>                 THP_FILE_FALLBACK,
> +               THP_FILE_FALLBACK_CHARGE,
>                 THP_FILE_MAPPED,
>                 THP_SPLIT_PAGE,
>                 THP_SPLIT_PAGE_FAILED,
> @@ -117,6 +119,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  #ifndef CONFIG_TRANSPARENT_HUGEPAGE
>  #define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
>  #define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
> +#define THP_FILE_FALLBACK_CHARGE ({ BUILD_BUG(); 0; })
>  #define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
>  #endif
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
>         if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
>                 put_page(page);
>                 count_vm_event(THP_FAULT_FALLBACK);
> +               count_vm_event(THP_FAULT_FALLBACK_CHARGE);
>                 return VM_FAULT_FALLBACK;
>         }
>
> @@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
>                         put_page(page);
>                 ret |= VM_FAULT_FALLBACK;
>                 count_vm_event(THP_FAULT_FALLBACK);
> +               count_vm_event(THP_FAULT_FALLBACK_CHARGE);
>                 goto out;
>         }
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1871,8 +1871,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
>         error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
>                                             PageTransHuge(page));
>         if (error) {
> -               if (PageTransHuge(page))
> +               if (PageTransHuge(page)) {
>                         count_vm_event(THP_FILE_FALLBACK);
> +                       count_vm_event(THP_FILE_FALLBACK_CHARGE);
> +               }
>                 goto unacct;
>         }
>         error = shmem_add_to_page_cache(page, mapping, hindex,
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1254,10 +1254,12 @@ const char * const vmstat_text[] = {
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>         "thp_fault_alloc",
>         "thp_fault_fallback",
> +       "thp_fault_fallback_charge",
>         "thp_collapse_alloc",
>         "thp_collapse_alloc_failed",
>         "thp_file_alloc",
>         "thp_file_fallback",
> +       "thp_file_fallback_charge",
>         "thp_file_mapped",
>         "thp_split_page",
>         "thp_split_page_failed",

Re: [patch 2/2] mm, thp: track fallbacks due to failed memcg charges separately

[Kirill A. Shutemov]

On Fri, Mar 06, 2020 at 02:22:35PM -0800, David Rientjes wrote:
> The thp_fault_fallback and thp_file_fallback vmstats are incremented if
> either the hugepage allocation fails through the page allocator or the
> hugepage charge fails through mem cgroup.
> 
> This patch leaves this field untouched but adds two new fields,
> thp_{fault,file}_fallback_charge, which is incremented only when the mem
> cgroup charge fails.
> 
> This distinguishes between attempted hugepage allocations that fail due to
> fragmentation (or low memory conditions) and those that fail due to mem
> cgroup limits.  That can be used to determine the impact of fragmentation
> on the system by excluding faults that failed due to memcg usage.
> 
> Signed-off-by: David Rientjes <rientjes@google.com>

Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
>  Documentation/admin-guide/mm/transhuge.rst | 10 ++++++++++
>  include/linux/vm_event_item.h              |  3 +++
>  mm/huge_memory.c                           |  2 ++
>  mm/shmem.c                                 |  4 +++-
>  mm/vmstat.c                                |  2 ++
>  5 files changed, 20 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -310,6 +310,11 @@ thp_fault_fallback
>  	is incremented if a page fault fails to allocate
>  	a huge page and instead falls back to using small pages.
>  
> +thp_fault_fallback_charge
> +	is incremented if a page fault fails to charge a huge page and
> +	instead falls back to using small pages even though the
> +	allocation was successful.
> +
>  thp_collapse_alloc_failed
>  	is incremented if khugepaged found a range
>  	of pages that should be collapsed into one huge page but failed
> @@ -323,6 +328,11 @@ thp_file_fallback
>  	is incremented if a file huge page is attempted to be allocated
>  	but fails and instead falls back to using small pages.
>  
> +thp_file_fallback_charge
> +	is incremented if a file huge page cannot be charged and instead
> +	falls back to using small pages even though the allocation was
> +	successful.
> +
>  thp_file_mapped
>  	is incremented every time a file huge page is mapped into
>  	user address space.
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -73,10 +73,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  		THP_FAULT_ALLOC,
>  		THP_FAULT_FALLBACK,
> +		THP_FAULT_FALLBACK_CHARGE,
>  		THP_COLLAPSE_ALLOC,
>  		THP_COLLAPSE_ALLOC_FAILED,
>  		THP_FILE_ALLOC,
>  		THP_FILE_FALLBACK,
> +		THP_FILE_FALLBACK_CHARGE,
>  		THP_FILE_MAPPED,
>  		THP_SPLIT_PAGE,
>  		THP_SPLIT_PAGE_FAILED,
> @@ -117,6 +119,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  #ifndef CONFIG_TRANSPARENT_HUGEPAGE
>  #define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
>  #define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
> +#define THP_FILE_FALLBACK_CHARGE ({ BUILD_BUG(); 0; })
>  #define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
>  #endif
>  
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
>  	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
>  		put_page(page);
>  		count_vm_event(THP_FAULT_FALLBACK);
> +		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
>  		return VM_FAULT_FALLBACK;
>  	}
>  
> @@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
>  			put_page(page);
>  		ret |= VM_FAULT_FALLBACK;
>  		count_vm_event(THP_FAULT_FALLBACK);
> +		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
>  		goto out;
>  	}
>  
> diff --git a/mm/shmem.c b/mm/shmem.c
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1871,8 +1871,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
>  	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
>  					    PageTransHuge(page));
>  	if (error) {
> -		if (PageTransHuge(page))
> +		if (PageTransHuge(page)) {
>  			count_vm_event(THP_FILE_FALLBACK);
> +			count_vm_event(THP_FILE_FALLBACK_CHARGE);
> +		}
>  		goto unacct;
>  	}
>  	error = shmem_add_to_page_cache(page, mapping, hindex,
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1254,10 +1254,12 @@ const char * const vmstat_text[] = {
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  	"thp_fault_alloc",
>  	"thp_fault_fallback",
> +	"thp_fault_fallback_charge",
>  	"thp_collapse_alloc",
>  	"thp_collapse_alloc_failed",
>  	"thp_file_alloc",
>  	"thp_file_fallback",
> +	"thp_file_fallback_charge",
>  	"thp_file_mapped",
>  	"thp_split_page",
>  	"thp_split_page_failed",

-- 
 Kirill A. Shutemov

Re: [patch 1/2] mm, shmem: add vmstat for hugepage fallback

[Yang Shi]

On Fri, Mar 6, 2020 at 2:22 PM David Rientjes <rientjes@google.com> wrote:
>
> The existing thp_fault_fallback indicates when thp attempts to allocate a
> hugepage but fails, or if the hugepage cannot be charged to the mem cgroup
> hierarchy.
>
> Extend this to shmem as well.  Adds a new thp_file_fallback to complement
> thp_file_alloc that gets incremented when a hugepage is attempted to be
> allocated but fails, or if it cannot be charged to the mem cgroup
> hierarchy.
>
> Additionally, remove the check for CONFIG_TRANSPARENT_HUGE_PAGECACHE from
> shmem_alloc_hugepage() since it is only called with this configuration
> option.

Looks good to me. Thanks for taking this suggestion. Reviewed-by: Yang
Shi <yang.shi@linux.alibaba.com>

>
> Signed-off-by: David Rientjes <rientjes@google.com>
> ---
>  Documentation/admin-guide/mm/transhuge.rst |  4 ++++
>  include/linux/vm_event_item.h              |  2 ++
>  mm/shmem.c                                 | 10 ++++++----
>  mm/vmstat.c                                |  1 +
>  4 files changed, 13 insertions(+), 4 deletions(-)
>
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -319,6 +319,10 @@ thp_file_alloc
>         is incremented every time a file huge page is successfully
>         allocated.
>
> +thp_file_fallback
> +       is incremented if a file huge page is attempted to be allocated
> +       but fails and instead falls back to using small pages.
> +
>  thp_file_mapped
>         is incremented every time a file huge page is mapped into
>         user address space.
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -76,6 +76,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>                 THP_COLLAPSE_ALLOC,
>                 THP_COLLAPSE_ALLOC_FAILED,
>                 THP_FILE_ALLOC,
> +               THP_FILE_FALLBACK,
>                 THP_FILE_MAPPED,
>                 THP_SPLIT_PAGE,
>                 THP_SPLIT_PAGE_FAILED,
> @@ -115,6 +116,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>
>  #ifndef CONFIG_TRANSPARENT_HUGEPAGE
>  #define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
> +#define THP_FILE_FALLBACK ({ BUILD_BUG(); 0; })
>  #define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
>  #endif
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1472,9 +1472,6 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
>         pgoff_t hindex;
>         struct page *page;
>
> -       if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
> -               return NULL;
> -
>         hindex = round_down(index, HPAGE_PMD_NR);
>         if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1,
>                                                                 XA_PRESENT))
> @@ -1486,6 +1483,8 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
>         shmem_pseudo_vma_destroy(&pvma);
>         if (page)
>                 prep_transhuge_page(page);
> +       else
> +               count_vm_event(THP_FILE_FALLBACK);
>         return page;
>  }
>
> @@ -1871,8 +1870,11 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
>
>         error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
>                                             PageTransHuge(page));
> -       if (error)
> +       if (error) {
> +               if (PageTransHuge(page))
> +                       count_vm_event(THP_FILE_FALLBACK);
>                 goto unacct;
> +       }
>         error = shmem_add_to_page_cache(page, mapping, hindex,
>                                         NULL, gfp & GFP_RECLAIM_MASK);
>         if (error) {
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1257,6 +1257,7 @@ const char * const vmstat_text[] = {
>         "thp_collapse_alloc",
>         "thp_collapse_alloc_failed",
>         "thp_file_alloc",
> +       "thp_file_fallback",
>         "thp_file_mapped",
>         "thp_split_page",
>         "thp_split_page_failed",

Re: [patch 1/2] mm, shmem: add vmstat for hugepage fallback

[Kirill A. Shutemov]

On Fri, Mar 06, 2020 at 02:22:32PM -0800, David Rientjes wrote:
> The existing thp_fault_fallback indicates when thp attempts to allocate a
> hugepage but fails, or if the hugepage cannot be charged to the mem cgroup
> hierarchy.
> 
> Extend this to shmem as well.  Adds a new thp_file_fallback to complement
> thp_file_alloc that gets incremented when a hugepage is attempted to be
> allocated but fails, or if it cannot be charged to the mem cgroup
> hierarchy.
> 
> Additionally, remove the check for CONFIG_TRANSPARENT_HUGE_PAGECACHE from
> shmem_alloc_hugepage() since it is only called with this configuration
> option.
> 
> Signed-off-by: David Rientjes <rientjes@google.com>

Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

-- 
 Kirill A. Shutemov

[patch] mm, thp: track fallbacks due to failed memcg charges separately

[David Rientjes]

The thp_fault_fallback stat in either /proc/vmstat is incremented if 
either the hugepage allocation fails through the page allocator or the 
hugepage charge fails through mem cgroup.

This patch leaves this field untouched but adds a new field,
thp_fault_fallback_charge, which is incremented only when the mem cgroup
charge fails.

This distinguishes between faults that want to be backed by hugepages but
fail due to fragmentation (or low memory conditions) and those that fail
due to mem cgroup limits.  That can be used to determine the impact of 
fragmentation on the system by excluding faults that failed due to memcg 
usage.

Signed-off-by: David Rientjes <rientjes@google.com>
---
 Documentation/admin-guide/mm/transhuge.rst | 5 +++++
 include/linux/vm_event_item.h              | 1 +
 mm/huge_memory.c                           | 2 ++
 mm/vmstat.c                                | 1 +
 4 files changed, 9 insertions(+)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -310,6 +310,11 @@ thp_fault_fallback
 	is incremented if a page fault fails to allocate
 	a huge page and instead falls back to using small pages.
 
+thp_fault_fallback_charge
+	is incremented if a page fault fails to charge a huge page and
+	instead falls back to using small pages even through the
+	allocation was successful.
+
 thp_collapse_alloc_failed
 	is incremented if khugepaged found a range
 	of pages that should be collapsed into one huge page but failed
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -73,6 +73,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		THP_FAULT_ALLOC,
 		THP_FAULT_FALLBACK,
+		THP_FAULT_FALLBACK_CHARGE,
 		THP_COLLAPSE_ALLOC,
 		THP_COLLAPSE_ALLOC_FAILED,
 		THP_FILE_ALLOC,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
 
@@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 			put_page(page);
 		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		goto out;
 	}
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1254,6 +1254,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	"thp_fault_alloc",
 	"thp_fault_fallback",
+	"thp_fault_fallback_charge",
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
 	"thp_file_alloc",

[patch 1/2] mm, shmem: add thp fault alloc and fallback stats

[David Rientjes]

The thp_fault_alloc and thp_fault_fallback vmstats are incremented when a
hugepage is successfully or unsuccessfully allocated, respectively, during
a page fault for anonymous memory.

Extend this to shmem as well.  Note that care is taken to increment
thp_fault_alloc only when the fault succeeds; this is the same behavior as
anonymous thp.

Signed-off-by: David Rientjes <rientjes@google.com>
---
 mm/shmem.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1502,9 +1502,8 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 	return page;
 }
 
-static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
-		struct inode *inode,
-		pgoff_t index, bool huge)
+static struct page *shmem_alloc_and_acct_page(gfp_t gfp, struct inode *inode,
+		pgoff_t index, bool fault, bool huge)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct page *page;
@@ -1518,9 +1517,11 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
 	if (!shmem_inode_acct_block(inode, nr))
 		goto failed;
 
-	if (huge)
+	if (huge) {
 		page = shmem_alloc_hugepage(gfp, info, index);
-	else
+		if (!page && fault)
+			count_vm_event(THP_FAULT_FALLBACK);
+	} else
 		page = shmem_alloc_page(gfp, info, index);
 	if (page) {
 		__SetPageLocked(page);
@@ -1832,11 +1833,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	}
 
 alloc_huge:
-	page = shmem_alloc_and_acct_page(gfp, inode, index, true);
+	page = shmem_alloc_and_acct_page(gfp, inode, index, vmf, true);
 	if (IS_ERR(page)) {
 alloc_nohuge:
-		page = shmem_alloc_and_acct_page(gfp, inode,
-						 index, false);
+		page = shmem_alloc_and_acct_page(gfp, inode, index, vmf, false);
 	}
 	if (IS_ERR(page)) {
 		int retry = 5;
@@ -1871,8 +1871,11 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 					    PageTransHuge(page));
-	if (error)
+	if (error) {
+		if (vmf && PageTransHuge(page))
+			count_vm_event(THP_FAULT_FALLBACK);
 		goto unacct;
+	}
 	error = shmem_add_to_page_cache(page, mapping, hindex,
 					NULL, gfp & GFP_RECLAIM_MASK);
 	if (error) {
@@ -1883,6 +1886,8 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	mem_cgroup_commit_charge(page, memcg, false,
 				 PageTransHuge(page));
 	lru_cache_add_anon(page);
+	if (vmf && PageTransHuge(page))
+		count_vm_event(THP_FAULT_ALLOC);
 
 	spin_lock_irq(&info->lock);
 	info->alloced += compound_nr(page);

[patch 2/2] mm, thp: track fallbacks due to failed memcg charges separately

[David Rientjes]

The thp_fault_fallback stat in /proc/vmstat is incremented if either the
hugepage allocation fails through the page allocator or the hugepage
charge fails through mem cgroup.

This patch leaves this field untouched but adds a new field,
thp_fault_fallback_charge, which is incremented only when the mem cgroup
charge fails.

This distinguishes between faults that want to be backed by hugepages but
fail due to fragmentation (or low memory conditions) and those that fail
due to mem cgroup limits.  That can be used to determine the impact of
fragmentation on the system by excluding faults that failed due to memcg
usage.

Signed-off-by: David Rientjes <rientjes@google.com>
---
 v2:
  - supported for shmem faults as well per Kirill
  - fixed worked in documentation and commit description per Mike

 Documentation/admin-guide/mm/transhuge.rst | 5 +++++
 include/linux/vm_event_item.h              | 1 +
 mm/huge_memory.c                           | 2 ++
 mm/shmem.c                                 | 4 +++-
 mm/vmstat.c                                | 1 +
 5 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -310,6 +310,11 @@ thp_fault_fallback
 	is incremented if a page fault fails to allocate
 	a huge page and instead falls back to using small pages.
 
+thp_fault_fallback_charge
+	is incremented if a page fault fails to charge a huge page and
+	instead falls back to using small pages even though the
+	allocation was successful.
+
 thp_collapse_alloc_failed
 	is incremented if khugepaged found a range
 	of pages that should be collapsed into one huge page but failed
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -73,6 +73,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		THP_FAULT_ALLOC,
 		THP_FAULT_FALLBACK,
+		THP_FAULT_FALLBACK_CHARGE,
 		THP_COLLAPSE_ALLOC,
 		THP_COLLAPSE_ALLOC_FAILED,
 		THP_FILE_ALLOC,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
 
@@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 			put_page(page);
 		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		goto out;
 	}
 
diff --git a/mm/shmem.c b/mm/shmem.c
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1872,8 +1872,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 					    PageTransHuge(page));
 	if (error) {
-		if (vmf && PageTransHuge(page))
+		if (vmf && PageTransHuge(page)) {
 			count_vm_event(THP_FAULT_FALLBACK);
+			count_vm_event(THP_FAULT_FALLBACK_CHARGE);
+		}
 		goto unacct;
 	}
 	error = shmem_add_to_page_cache(page, mapping, hindex,
diff --git a/mm/vmstat.c b/mm/vmstat.c
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1254,6 +1254,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	"thp_fault_alloc",
 	"thp_fault_fallback",
+	"thp_fault_fallback_charge",
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
 	"thp_file_alloc",

Re: [patch 2/2] mm, thp: track fallbacks due to failed memcg charges separately

[Mike Rapoport]

On Tue, Feb 18, 2020 at 06:29:21PM -0800, David Rientjes wrote:
> The thp_fault_fallback stat in /proc/vmstat is incremented if either the
> hugepage allocation fails through the page allocator or the hugepage
> charge fails through mem cgroup.
> 
> This patch leaves this field untouched but adds a new field,
> thp_fault_fallback_charge, which is incremented only when the mem cgroup
> charge fails.
> 
> This distinguishes between faults that want to be backed by hugepages but
> fail due to fragmentation (or low memory conditions) and those that fail
> due to mem cgroup limits.  That can be used to determine the impact of
> fragmentation on the system by excluding faults that failed due to memcg
> usage.
> 
> Signed-off-by: David Rientjes <rientjes@google.com>

Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>	# Documentation

> ---
>  v2:
>   - supported for shmem faults as well per Kirill
>   - fixed worked in documentation and commit description per Mike
> 
>  Documentation/admin-guide/mm/transhuge.rst | 5 +++++
>  include/linux/vm_event_item.h              | 1 +
>  mm/huge_memory.c                           | 2 ++
>  mm/shmem.c                                 | 4 +++-
>  mm/vmstat.c                                | 1 +
>  5 files changed, 12 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -310,6 +310,11 @@ thp_fault_fallback
>  	is incremented if a page fault fails to allocate
>  	a huge page and instead falls back to using small pages.
>  
> +thp_fault_fallback_charge
> +	is incremented if a page fault fails to charge a huge page and
> +	instead falls back to using small pages even though the
> +	allocation was successful.
> +
>  thp_collapse_alloc_failed
>  	is incremented if khugepaged found a range
>  	of pages that should be collapsed into one huge page but failed
> diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
> --- a/include/linux/vm_event_item.h
> +++ b/include/linux/vm_event_item.h
> @@ -73,6 +73,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  		THP_FAULT_ALLOC,
>  		THP_FAULT_FALLBACK,
> +		THP_FAULT_FALLBACK_CHARGE,
>  		THP_COLLAPSE_ALLOC,
>  		THP_COLLAPSE_ALLOC_FAILED,
>  		THP_FILE_ALLOC,
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
>  	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
>  		put_page(page);
>  		count_vm_event(THP_FAULT_FALLBACK);
> +		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
>  		return VM_FAULT_FALLBACK;
>  	}
>  
> @@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
>  			put_page(page);
>  		ret |= VM_FAULT_FALLBACK;
>  		count_vm_event(THP_FAULT_FALLBACK);
> +		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
>  		goto out;
>  	}
>  
> diff --git a/mm/shmem.c b/mm/shmem.c
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1872,8 +1872,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
>  	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
>  					    PageTransHuge(page));
>  	if (error) {
> -		if (vmf && PageTransHuge(page))
> +		if (vmf && PageTransHuge(page)) {
>  			count_vm_event(THP_FAULT_FALLBACK);
> +			count_vm_event(THP_FAULT_FALLBACK_CHARGE);
> +		}
>  		goto unacct;
>  	}
>  	error = shmem_add_to_page_cache(page, mapping, hindex,
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1254,6 +1254,7 @@ const char * const vmstat_text[] = {
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  	"thp_fault_alloc",
>  	"thp_fault_fallback",
> +	"thp_fault_fallback_charge",
>  	"thp_collapse_alloc",
>  	"thp_collapse_alloc_failed",
>  	"thp_file_alloc",

-- 
Sincerely yours,
Mike.