| Message ID | 20240308085653.124180-1-21cnbao@gmail.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm: prohibit the last subpage from reusing the entire large folio | expand |
On 08.03.24 09:56, Barry Song wrote: > From: Barry Song <v-songbaohua@oppo.com> > > In a Copy-on-Write (CoW) scenario, the last subpage will reuse the entire > large folio, resulting in the waste of (nr_pages - 1) pages. This wasted > memory remains allocated until it is either unmapped or memory > reclamation occurs. > > The following small program can serve as evidence of this behavior > > main() > { > #define SIZE 1024 * 1024 * 1024UL > void *p = malloc(SIZE); > memset(p, 0x11, SIZE); > if (fork() == 0) > _exit(0); > memset(p, 0x12, SIZE); > printf("done\n"); > while(1); > } > > For example, using a 1024KiB mTHP by: > echo always > /sys/kernel/mm/transparent_hugepage/hugepages-1024kB/enabled > > (1) w/o the patch, it takes 2GiB, > > Before running the test program, > / # free -m > total used free shared buff/cache available > Mem: 5754 84 5692 0 17 5669 > Swap: 0 0 0 > > / # /a.out & > / # done > > After running the test program, > / # free -m > total used free shared buff/cache available > Mem: 5754 2149 3627 0 19 3605 > Swap: 0 0 0 > > (2) w/ the patch, it takes 1GiB only, > > Before running the test program, > / # free -m > total used free shared buff/cache available > Mem: 5754 89 5687 0 17 5664 > Swap: 0 0 0 > > / # /a.out & > / # done > > After running the test program, > / # free -m > total used free shared buff/cache available > Mem: 5754 1122 4655 0 17 4632 > Swap: 0 0 0 > > This patch migrates the last subpage to a small folio and immediately > returns the large folio to the system. It benefits both memory availability > and anti-fragmentation. > > Cc: David Hildenbrand <david@redhat.com> > Cc: Ryan Roberts <ryan.roberts@arm.com> > Cc: Lance Yang <ioworker0@gmail.com> > Signed-off-by: Barry Song <v-songbaohua@oppo.com> > --- > mm/memory.c | 8 ++++++++ > 1 file changed, 8 insertions(+) > > diff --git a/mm/memory.c b/mm/memory.c > index e17669d4f72f..0200bfc15f94 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -3523,6 +3523,14 @@ static bool wp_can_reuse_anon_folio(struct folio *folio, > folio_unlock(folio); > return false; > } > + /* > + * If the last subpage reuses the entire large folio, it would > + * result in a waste of (nr_pages - 1) pages > + */ > + if (folio_ref_count(folio) == 1 && folio_test_large(folio)) { > + folio_unlock(folio); > + return false; > + } > /* > * Ok, we've got the only folio reference from our mapping > * and the folio is locked, it's dark out, and we're wearing Why not simply: diff --git a/mm/memory.c b/mm/memory.c index e17669d4f72f7..46d286bd450c6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3498,6 +3498,10 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) static bool wp_can_reuse_anon_folio(struct folio *folio, struct vm_area_struct *vma) { + + if (folio_test_large(folio)) + return false; + /* * We have to verify under folio lock: these early checks are * just an optimization to avoid locking the folio and freeing We could only possibly succeed if we are the last one mapping a PTE either way. No we simply give up right away for the time being.
On Fri, Mar 8, 2024 at 10:03 PM David Hildenbrand <david@redhat.com> wrote: > > On 08.03.24 09:56, Barry Song wrote: > > From: Barry Song <v-songbaohua@oppo.com> > > > > In a Copy-on-Write (CoW) scenario, the last subpage will reuse the entire > > large folio, resulting in the waste of (nr_pages - 1) pages. This wasted > > memory remains allocated until it is either unmapped or memory > > reclamation occurs. > > > > The following small program can serve as evidence of this behavior > > > > main() > > { > > #define SIZE 1024 * 1024 * 1024UL > > void *p = malloc(SIZE); > > memset(p, 0x11, SIZE); > > if (fork() == 0) > > _exit(0); > > memset(p, 0x12, SIZE); > > printf("done\n"); > > while(1); > > } > > > > For example, using a 1024KiB mTHP by: > > echo always > /sys/kernel/mm/transparent_hugepage/hugepages-1024kB/enabled > > > > (1) w/o the patch, it takes 2GiB, > > > > Before running the test program, > > / # free -m > > total used free shared buff/cache available > > Mem: 5754 84 5692 0 17 5669 > > Swap: 0 0 0 > > > > / # /a.out & > > / # done > > > > After running the test program, > > / # free -m > > total used free shared buff/cache available > > Mem: 5754 2149 3627 0 19 3605 > > Swap: 0 0 0 > > > > (2) w/ the patch, it takes 1GiB only, > > > > Before running the test program, > > / # free -m > > total used free shared buff/cache available > > Mem: 5754 89 5687 0 17 5664 > > Swap: 0 0 0 > > > > / # /a.out & > > / # done > > > > After running the test program, > > / # free -m > > total used free shared buff/cache available > > Mem: 5754 1122 4655 0 17 4632 > > Swap: 0 0 0 > > > > This patch migrates the last subpage to a small folio and immediately > > returns the large folio to the system. It benefits both memory availability > > and anti-fragmentation. > > > > Cc: David Hildenbrand <david@redhat.com> > > Cc: Ryan Roberts <ryan.roberts@arm.com> > > Cc: Lance Yang <ioworker0@gmail.com> > > Signed-off-by: Barry Song <v-songbaohua@oppo.com> > > --- > > mm/memory.c | 8 ++++++++ > > 1 file changed, 8 insertions(+) > > > > diff --git a/mm/memory.c b/mm/memory.c > > index e17669d4f72f..0200bfc15f94 100644 > > --- a/mm/memory.c > > +++ b/mm/memory.c > > @@ -3523,6 +3523,14 @@ static bool wp_can_reuse_anon_folio(struct folio *folio, > > folio_unlock(folio); > > return false; > > } > > + /* > > + * If the last subpage reuses the entire large folio, it would > > + * result in a waste of (nr_pages - 1) pages > > + */ > > + if (folio_ref_count(folio) == 1 && folio_test_large(folio)) { > > + folio_unlock(folio); > > + return false; > > + } > > /* > > * Ok, we've got the only folio reference from our mapping > > * and the folio is locked, it's dark out, and we're wearing > > > Why not simply: > > diff --git a/mm/memory.c b/mm/memory.c > index e17669d4f72f7..46d286bd450c6 100644 > --- a/mm/memory.c > +++ b/mm/memory.c > @@ -3498,6 +3498,10 @@ static vm_fault_t wp_page_shared(struct vm_fault > *vmf, struct folio *folio) > static bool wp_can_reuse_anon_folio(struct folio *folio, > struct vm_area_struct *vma) > { > + > + if (folio_test_large(folio)) > + return false; > + > /* > * We have to verify under folio lock: these early checks are > * just an optimization to avoid locking the folio and freeing > > We could only possibly succeed if we are the last one mapping a PTE > either way. No we simply give up right away for the time being. nice ! > > -- > Cheers, > > David / dhildenb >
On 08.03.24 10:07, Barry Song wrote: > On Fri, Mar 8, 2024 at 10:03 PM David Hildenbrand <david@redhat.com> wrote: >> >> On 08.03.24 09:56, Barry Song wrote: >>> From: Barry Song <v-songbaohua@oppo.com> >>> >>> In a Copy-on-Write (CoW) scenario, the last subpage will reuse the entire >>> large folio, resulting in the waste of (nr_pages - 1) pages. This wasted >>> memory remains allocated until it is either unmapped or memory >>> reclamation occurs. >>> >>> The following small program can serve as evidence of this behavior >>> >>> main() >>> { >>> #define SIZE 1024 * 1024 * 1024UL >>> void *p = malloc(SIZE); >>> memset(p, 0x11, SIZE); >>> if (fork() == 0) >>> _exit(0); >>> memset(p, 0x12, SIZE); >>> printf("done\n"); >>> while(1); >>> } >>> >>> For example, using a 1024KiB mTHP by: >>> echo always > /sys/kernel/mm/transparent_hugepage/hugepages-1024kB/enabled >>> >>> (1) w/o the patch, it takes 2GiB, >>> >>> Before running the test program, >>> / # free -m >>> total used free shared buff/cache available >>> Mem: 5754 84 5692 0 17 5669 >>> Swap: 0 0 0 >>> >>> / # /a.out & >>> / # done >>> >>> After running the test program, >>> / # free -m >>> total used free shared buff/cache available >>> Mem: 5754 2149 3627 0 19 3605 >>> Swap: 0 0 0 >>> >>> (2) w/ the patch, it takes 1GiB only, >>> >>> Before running the test program, >>> / # free -m >>> total used free shared buff/cache available >>> Mem: 5754 89 5687 0 17 5664 >>> Swap: 0 0 0 >>> >>> / # /a.out & >>> / # done >>> >>> After running the test program, >>> / # free -m >>> total used free shared buff/cache available >>> Mem: 5754 1122 4655 0 17 4632 >>> Swap: 0 0 0 >>> >>> This patch migrates the last subpage to a small folio and immediately >>> returns the large folio to the system. It benefits both memory availability >>> and anti-fragmentation. >>> >>> Cc: David Hildenbrand <david@redhat.com> >>> Cc: Ryan Roberts <ryan.roberts@arm.com> >>> Cc: Lance Yang <ioworker0@gmail.com> >>> Signed-off-by: Barry Song <v-songbaohua@oppo.com> >>> --- >>> mm/memory.c | 8 ++++++++ >>> 1 file changed, 8 insertions(+) >>> >>> diff --git a/mm/memory.c b/mm/memory.c >>> index e17669d4f72f..0200bfc15f94 100644 >>> --- a/mm/memory.c >>> +++ b/mm/memory.c >>> @@ -3523,6 +3523,14 @@ static bool wp_can_reuse_anon_folio(struct folio *folio, >>> folio_unlock(folio); >>> return false; >>> } >>> + /* >>> + * If the last subpage reuses the entire large folio, it would >>> + * result in a waste of (nr_pages - 1) pages >>> + */ >>> + if (folio_ref_count(folio) == 1 && folio_test_large(folio)) { >>> + folio_unlock(folio); >>> + return false; >>> + } >>> /* >>> * Ok, we've got the only folio reference from our mapping >>> * and the folio is locked, it's dark out, and we're wearing >> >> >> Why not simply: >> >> diff --git a/mm/memory.c b/mm/memory.c >> index e17669d4f72f7..46d286bd450c6 100644 >> --- a/mm/memory.c >> +++ b/mm/memory.c >> @@ -3498,6 +3498,10 @@ static vm_fault_t wp_page_shared(struct vm_fault >> *vmf, struct folio *folio) >> static bool wp_can_reuse_anon_folio(struct folio *folio, >> struct vm_area_struct *vma) >> { >> + >> + if (folio_test_large(folio)) >> + return false; >> + >> /* >> * We have to verify under folio lock: these early checks are >> * just an optimization to avoid locking the folio and freeing >> >> We could only possibly succeed if we are the last one mapping a PTE >> either way. No we simply give up right away for the time being. > > nice ! ... of course, adding a comment like "We could currently only reuse a subpage of a large folio if no other subpages of the large folios are still mapped. However, let's just consistently not reuse subpages even if we could reuse in that scenario, and give back a large folio a bit sooner." The !fotk() case would be more tricky to handle, because the folio has PAE set and may be pinned or we might race with pinning. So this here is the low hanging fruit.
diff --git a/mm/memory.c b/mm/memory.c index e17669d4f72f..0200bfc15f94 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3523,6 +3523,14 @@ static bool wp_can_reuse_anon_folio(struct folio *folio, folio_unlock(folio); return false; } + /* + * If the last subpage reuses the entire large folio, it would + * result in a waste of (nr_pages - 1) pages + */ + if (folio_ref_count(folio) == 1 && folio_test_large(folio)) { + folio_unlock(folio); + return false; + } /* * Ok, we've got the only folio reference from our mapping * and the folio is locked, it's dark out, and we're wearing