summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorAaron Lu <aaron.lu@intel.com>2016-10-08 03:00:08 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-08 04:46:28 +0300
commit6fcb52a56ff60d240f06296b12827e7f20d45f63 (patch)
tree662e3a878be89475dc0bf52a85d5396191e2166d /include
parent0f30206bf2a42e278c2cec32e4b722626458c75b (diff)
downloadlinux-6fcb52a56ff60d240f06296b12827e7f20d45f63.tar.xz
thp: reduce usage of huge zero page's atomic counter
The global zero page is used to satisfy an anonymous read fault. If THP(Transparent HugePage) is enabled then the global huge zero page is used. The global huge zero page uses an atomic counter for reference counting and is allocated/freed dynamically according to its counter value. CPU time spent on that counter will greatly increase if there are a lot of processes doing anonymous read faults. This patch proposes a way to reduce the access to the global counter so that the CPU load can be reduced accordingly. To do this, a new flag of the mm_struct is introduced: MMF_USED_HUGE_ZERO_PAGE. With this flag, the process only need to touch the global counter in two cases: 1 The first time it uses the global huge zero page; 2 The time when mm_user of its mm_struct reaches zero. Note that right now, the huge zero page is eligible to be freed as soon as its last use goes away. With this patch, the page will not be eligible to be freed until the exit of the last process from which it was ever used. And with the use of mm_user, the kthread is not eligible to use huge zero page either. Since no kthread is using huge zero page today, there is no difference after applying this patch. But if that is not desired, I can change it to when mm_count reaches zero. Case used for test on Haswell EP: usemem -n 72 --readonly -j 0x200000 100G Which spawns 72 processes and each will mmap 100G anonymous space and then do read only access to that space sequentially with a step of 2MB. CPU cycles from perf report for base commit: 54.03% usemem [kernel.kallsyms] [k] get_huge_zero_page CPU cycles from perf report for this commit: 0.11% usemem [kernel.kallsyms] [k] mm_get_huge_zero_page Performance(throughput) of the workload for base commit: 1784430792 Performance(throughput) of the workload for this commit: 4726928591 164% increase. Runtime of the workload for base commit: 707592 us Runtime of the workload for this commit: 303970 us 50% drop. Link: http://lkml.kernel.org/r/fe51a88f-446a-4622-1363-ad1282d71385@intel.com Signed-off-by: Aaron Lu <aaron.lu@intel.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/huge_mm.h8
-rw-r--r--include/linux/sched.h1
2 files changed, 5 insertions, 4 deletions
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 4fca5263fd42..9b9f65d99873 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -156,8 +156,8 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
return is_huge_zero_page(pmd_page(pmd));
}
-struct page *get_huge_zero_page(void);
-void put_huge_zero_page(void);
+struct page *mm_get_huge_zero_page(struct mm_struct *mm);
+void mm_put_huge_zero_page(struct mm_struct *mm);
#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
@@ -220,9 +220,9 @@ static inline bool is_huge_zero_page(struct page *page)
return false;
}
-static inline void put_huge_zero_page(void)
+static inline void mm_put_huge_zero_page(struct mm_struct *mm)
{
- BUILD_BUG();
+ return;
}
static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6bee6f988912..348f51b0ec92 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -526,6 +526,7 @@ static inline int get_dumpable(struct mm_struct *mm)
#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */
#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */
#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */
+#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)