17 Dec
2021
17 Dec
'21
10:13 p.m.
From: Huang Ying <ying.huang(a)intel.com>
If the NUMA balancing isn't used to optimize the page placement among
sockets but only among memory types, the hot pages in the fast memory
node couldn't be migrated (promoted) to anywhere. So it's unnecessary
to scan the pages in the fast memory node via changing their PTE/PMD
mapping to be PROT_NONE. So that the page faults could be avoided
too.
In the test, if only the memory tiering NUMA balancing mode is enabled, the
number of the NUMA balancing hint faults for the DRAM node is reduced to
almost 0 with the patch. While the benchmark score doesn't change
visibly.
Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com>
Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: Andrew Morton <akpm(a)linux-foundation.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Rik van Riel <riel(a)surriel.com>
Cc: Mel Gorman <mgorman(a)techsingularity.net>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Yang Shi <shy828301(a)gmail.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: Wei Xu <weixugc(a)google.com>
Cc: osalvador <osalvador(a)suse.de>
Cc: Shakeel Butt <shakeelb(a)google.com>
Cc: Hasan Al Maruf <hasanalmaruf(a)fb.com>
Cc: linux-kernel(a)vger.kernel.org
Cc: linux-mm(a)kvack.org
Signed-off-by: zhongjiang-ali <zhongjiang-ali(a)linux.alibaba.com>
---
mm/huge_memory.c | 31 ++++++++++++++++++++++---------
mm/mprotect.c | 13 ++++++++++++-
2 files changed, 34 insertions(+), 10 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c3cac4f..6f11401 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -34,6 +34,7 @@
#include <linux/shmem_fs.h>
#include <linux/oom.h>
#include <linux/page_owner.h>
+#include <linux/sched/sysctl.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -2217,16 +2218,28 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
}
#endif
- /*
- * Avoid trapping faults against the zero page. The read-only
- * data is likely to be read-cached on the local CPU and
- * local/remote hits to the zero page are not interesting.
- */
- if (prot_numa && is_huge_zero_pmd(*pmd))
- goto unlock;
+ if (prot_numa) {
+ struct page *page;
+ /*
+ * Avoid trapping faults against the zero page. The read-only
+ * data is likely to be read-cached on the local CPU and
+ * local/remote hits to the zero page are not interesting.
+ */
+ if (is_huge_zero_pmd(*pmd))
+ goto unlock;
- if (prot_numa && pmd_protnone(*pmd))
- goto unlock;
+ if (pmd_protnone(*pmd))
+ goto unlock;
+
+ page = pmd_page(*pmd);
+ /*
+ * Skip scanning top tier node if normal numa
+ * balancing is disabled
+ */
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
+ node_is_toptier(page_to_nid(page)))
+ goto unlock;
+ }
/*
* In case prot_numa, we are under down_read(mmap_sem). It's critical
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 05b1f8b..fbdb09f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,6 +29,7 @@
#include <linux/uaccess.h>
#include <linux/mm_inline.h>
#include <asm/pgtable.h>
+#include <linux/sched/sysctl.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
@@ -80,6 +81,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t
*pmd,
*/
if (prot_numa) {
struct page *page;
+ int nid;
page = vm_normal_page(vma, addr, oldpte);
if (!page || PageKsm(page))
@@ -106,7 +108,16 @@ static unsigned long change_pte_range(struct vm_area_struct *vma,
pmd_t *pmd,
* Don't mess with PTEs if page is already on the node
* a single-threaded process is running on.
*/
- if (target_node == page_to_nid(page))
+ nid = page_to_nid(page);
+ if (target_node == nid)
+ continue;
+
+ /*
+ * Skip scanning top tier node if normal numa
+ * balancing is disabled
+ */
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
+ node_is_toptier(nid))
continue;
}
--
1.8.3.1