The patch titled
Subject: mm: add tracepoint for scanning pages
has been removed from the -mm tree. Its filename was
mm-add-tracepoint-for-scanning-pages.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Ebru Akagunduz <ebru.akagunduz@xxxxxxxxx>
Subject: mm: add tracepoint for scanning pages
This patch series makes swapin readahead up to a certain number to gain
more thp performance and adds tracepoint for khugepaged_scan_pmd,
collapse_huge_page, __collapse_huge_page_isolate.
This patch series was written to deal with programs that access most, but
not all, of their memory after they get swapped out. Currently these
programs do not get their memory collapsed into THPs after the system
swapped their memory out, while they would get THPs before swapping
happened.
This patch series was tested with a test program, it allocates 400MB of
memory, writes to it, and then sleeps. I force the system to swap out
all. Afterwards, the test program touches the area by writing and leaves
a piece of it without writing. This shows how much swap in readahead made
by the patch.
Test results:
After swapped out
-------------------------------------------------------------------
| Anonymous | AnonHugePages | Swap | Fraction |
-------------------------------------------------------------------
With patch | 90076 kB | 88064 kB | 309928 kB | %99 |
-------------------------------------------------------------------
Without patch | 194068 kB | 192512 kB | 205936 kB | %99 |
-------------------------------------------------------------------
After swapped in
-------------------------------------------------------------------
| Anonymous | AnonHugePages | Swap | Fraction |
-------------------------------------------------------------------
With patch | 201408 kB | 198656 kB | 198596 kB | %98 |
-------------------------------------------------------------------
Without patch | 292624 kB | 192512 kB | 107380 kB | %65 |
-------------------------------------------------------------------
This patch (of 3):
Using static tracepoints, data of functions is recorded. It is good to
automatize debugging without doing a lot of changes in the source code.
This patch adds tracepoint for khugepaged_scan_pmd, collapse_huge_page and
__collapse_huge_page_isolate.
[dan.carpenter@xxxxxxxxxx: add a missing tab]
Signed-off-by: Ebru Akagunduz <ebru.akagunduz@xxxxxxxxx>
Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Signed-off-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/trace/events/huge_memory.h | 137 ++++++++++++++++++++++
mm/huge_memory.c | 166 +++++++++++++++++++++------
2 files changed, 271 insertions(+), 32 deletions(-)
diff -puN /dev/null include/trace/events/huge_memory.h
--- /dev/null
+++ a/include/trace/events/huge_memory.h
@@ -0,0 +1,137 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM huge_memory
+
+#if !defined(__HUGE_MEMORY_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __HUGE_MEMORY_H
+
+#include <linux/tracepoint.h>
+
+#include <trace/events/gfpflags.h>
+
+#define SCAN_STATUS \
+ EM( SCAN_FAIL, "failed") \
+ EM( SCAN_SUCCEED, "succeeded") \
+ EM( SCAN_PMD_NULL, "pmd_null") \
+ 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_PAGE_NULL, "page_null") \
+ EM( SCAN_SCAN_ABORT, "scan_aborted") \
+ EM( SCAN_PAGE_COUNT, "not_suitable_page_count") \
+ EM( SCAN_PAGE_LRU, "page_not_in_lru") \
+ EM( SCAN_PAGE_LOCK, "page_locked") \
+ EM( SCAN_PAGE_ANON, "page_not_anon") \
+ EM( SCAN_ANY_PROCESS, "no_process_for_page") \
+ EM( SCAN_VMA_NULL, "vma_null") \
+ EM( SCAN_VMA_CHECK, "vma_check_failed") \
+ EM( SCAN_ADDRESS_RANGE, "not_suitable_address_range") \
+ EM( SCAN_SWAP_CACHE_PAGE, "page_swap_cache") \
+ EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\
+ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \
+ EMe( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed")
+
+#undef EM
+#undef EMe
+#define EM(a, b) TRACE_DEFINE_ENUM(a);
+#define EMe(a, b) TRACE_DEFINE_ENUM(a);
+
+SCAN_STATUS
+
+#undef EM
+#undef EMe
+#define EM(a, b) {a, b},
+#define EMe(a, b) {a, b}
+
+TRACE_EVENT(mm_khugepaged_scan_pmd,
+
+ TP_PROTO(struct mm_struct *mm, unsigned long pfn, bool writable,
+ bool referenced, int none_or_zero, int status),
+
+ TP_ARGS(mm, pfn, writable, referenced, none_or_zero, status),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ __field(unsigned long, pfn)
+ __field(bool, writable)
+ __field(bool, referenced)
+ __field(int, none_or_zero)
+ __field(int, status)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ __entry->pfn = pfn;
+ __entry->writable = writable;
+ __entry->referenced = referenced;
+ __entry->none_or_zero = none_or_zero;
+ __entry->status = status;
+ ),
+
+ TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s",
+ __entry->mm,
+ __entry->pfn,
+ __entry->writable,
+ __entry->referenced,
+ __entry->none_or_zero,
+ __print_symbolic(__entry->status, SCAN_STATUS))
+);
+
+TRACE_EVENT(mm_collapse_huge_page,
+
+ TP_PROTO(struct mm_struct *mm, int isolated, int status),
+
+ TP_ARGS(mm, isolated, status),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ __field(int, isolated)
+ __field(int, status)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ __entry->isolated = isolated;
+ __entry->status = status;
+ ),
+
+ TP_printk("mm=%p, isolated=%d, status=%s",
+ __entry->mm,
+ __entry->isolated,
+ __print_symbolic(__entry->status, SCAN_STATUS))
+);
+
+TRACE_EVENT(mm_collapse_huge_page_isolate,
+
+ TP_PROTO(unsigned long pfn, int none_or_zero,
+ bool referenced, bool writable, int status),
+
+ TP_ARGS(pfn, none_or_zero, referenced, writable, status),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, pfn)
+ __field(int, none_or_zero)
+ __field(bool, referenced)
+ __field(bool, writable)
+ __field(int, status)
+ ),
+
+ TP_fast_assign(
+ __entry->pfn = pfn;
+ __entry->none_or_zero = none_or_zero;
+ __entry->referenced = referenced;
+ __entry->writable = writable;
+ __entry->status = status;
+ ),
+
+ TP_printk("scan_pfn=0x%lx, none_or_zero=%d, referenced=%d, writable=%d, status=%s",
+ __entry->pfn,
+ __entry->none_or_zero,
+ __entry->referenced,
+ __entry->writable,
+ __print_symbolic(__entry->status, SCAN_STATUS))
+);
+
+#endif /* __HUGE_MEMORY_H */
+#include <trace/define_trace.h>
+
diff -puN mm/huge_memory.c~mm-add-tracepoint-for-scanning-pages mm/huge_memory.c
--- a/mm/huge_memory.c~mm-add-tracepoint-for-scanning-pages
+++ a/mm/huge_memory.c
@@ -31,6 +31,33 @@
#include <asm/pgalloc.h>
#include "internal.h"
+enum scan_result {
+ SCAN_FAIL,
+ SCAN_SUCCEED,
+ SCAN_PMD_NULL,
+ SCAN_EXCEED_NONE_PTE,
+ SCAN_PTE_NON_PRESENT,
+ SCAN_PAGE_RO,
+ SCAN_NO_REFERENCED_PAGE,
+ SCAN_PAGE_NULL,
+ SCAN_SCAN_ABORT,
+ SCAN_PAGE_COUNT,
+ SCAN_PAGE_LRU,
+ SCAN_PAGE_LOCK,
+ SCAN_PAGE_ANON,
+ SCAN_ANY_PROCESS,
+ SCAN_VMA_NULL,
+ SCAN_VMA_CHECK,
+ SCAN_ADDRESS_RANGE,
+ SCAN_SWAP_CACHE_PAGE,
+ SCAN_DEL_PAGE_LRU,
+ SCAN_ALLOC_HUGE_PAGE_FAIL,
+ SCAN_CGROUP_CHARGE_FAIL
+};
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/huge_memory.h>
+
/*
* By default transparent hugepage support is disabled in order that avoid
* to risk increase the memory footprint of applications without a guaranteed
@@ -2198,26 +2225,33 @@ static int __collapse_huge_page_isolate(
unsigned long address,
pte_t *pte)
{
- struct page *page;
+ struct page *page = NULL;
pte_t *_pte;
- int none_or_zero = 0;
+ int none_or_zero = 0, result = 0;
bool referenced = false, writable = false;
+
for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
_pte++, address += PAGE_SIZE) {
pte_t pteval = *_pte;
if (pte_none(pteval) || (pte_present(pteval) &&
is_zero_pfn(pte_pfn(pteval)))) {
if (!userfaultfd_armed(vma) &&
- ++none_or_zero <= khugepaged_max_ptes_none)
+ ++none_or_zero <= khugepaged_max_ptes_none) {
continue;
- else
+ } else {
+ result = SCAN_EXCEED_NONE_PTE;
goto out;
+ }
}
- if (!pte_present(pteval))
+ if (!pte_present(pteval)) {
+ result = SCAN_PTE_NON_PRESENT;
goto out;
+ }
page = vm_normal_page(vma, address, pteval);
- if (unlikely(!page))
+ if (unlikely(!page)) {
+ result = SCAN_PAGE_NULL;
goto out;
+ }
VM_BUG_ON_PAGE(PageCompound(page), page);
VM_BUG_ON_PAGE(!PageAnon(page), page);
@@ -2229,8 +2263,10 @@ static int __collapse_huge_page_isolate(
* is needed to serialize against split_huge_page
* when invoked from the VM.
*/
- if (!trylock_page(page))
+ if (!trylock_page(page)) {
+ result = SCAN_PAGE_LOCK;
goto out;
+ }
/*
* cannot use mapcount: can't collapse if there's a gup pin.
@@ -2239,6 +2275,7 @@ static int __collapse_huge_page_isolate(
*/
if (page_count(page) != 1 + !!PageSwapCache(page)) {
unlock_page(page);
+ result = SCAN_PAGE_COUNT;
goto out;
}
if (pte_write(pteval)) {
@@ -2246,6 +2283,7 @@ static int __collapse_huge_page_isolate(
} else {
if (PageSwapCache(page) && !reuse_swap_page(page)) {
unlock_page(page);
+ result = SCAN_SWAP_CACHE_PAGE;
goto out;
}
/*
@@ -2260,6 +2298,7 @@ static int __collapse_huge_page_isolate(
*/
if (isolate_lru_page(page)) {
unlock_page(page);
+ result = SCAN_DEL_PAGE_LRU;
goto out;
}
/* 0 stands for page_is_file_cache(page) == false */
@@ -2273,10 +2312,21 @@ static int __collapse_huge_page_isolate(
mmu_notifier_test_young(vma->vm_mm, address))
referenced = true;
}
- if (likely(referenced && writable))
- return 1;
+ if (likely(writable)) {
+ if (likely(referenced)) {
+ result = SCAN_SUCCEED;
+ trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero,
+ referenced, writable, result);
+ return 1;
+ }
+ } else {
+ result = SCAN_PAGE_RO;
+ }
+
out:
release_pte_pages(pte, _pte);
+ trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero,
+ referenced, writable, result);
return 0;
}
@@ -2513,7 +2563,7 @@ static void collapse_huge_page(struct mm
pgtable_t pgtable;
struct page *new_page;
spinlock_t *pmd_ptl, *pte_ptl;
- int isolated;
+ int isolated, result = 0;
unsigned long hstart, hend;
struct mem_cgroup *memcg;
unsigned long mmun_start; /* For mmu_notifiers */
@@ -2528,12 +2578,15 @@ static void collapse_huge_page(struct mm
/* release the mmap_sem read lock. */
new_page = khugepaged_alloc_page(hpage, gfp, mm, address, node);
- if (!new_page)
- return;
+ if (!new_page) {
+ result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+ goto out_nolock;
+ }
- if (unlikely(mem_cgroup_try_charge(new_page, mm,
- gfp, &memcg)))
- return;
+ if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) {
+ result = SCAN_CGROUP_CHARGE_FAIL;
+ goto out_nolock;
+ }
/*
* Prevent all access to pagetables with the exception of
@@ -2541,21 +2594,31 @@ static void collapse_huge_page(struct mm
* handled by the anon_vma lock + PG_lock.
*/
down_write(&mm->mmap_sem);
- if (unlikely(khugepaged_test_exit(mm)))
+ if (unlikely(khugepaged_test_exit(mm))) {
+ result = SCAN_ANY_PROCESS;
goto out;
+ }
vma = find_vma(mm, address);
- if (!vma)
+ if (!vma) {
+ result = SCAN_VMA_NULL;
goto out;
+ }
hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = vma->vm_end & HPAGE_PMD_MASK;
- if (address < hstart || address + HPAGE_PMD_SIZE > hend)
+ if (address < hstart || address + HPAGE_PMD_SIZE > hend) {
+ result = SCAN_ADDRESS_RANGE;
goto out;
- if (!hugepage_vma_check(vma))
+ }
+ if (!hugepage_vma_check(vma)) {
+ result = SCAN_VMA_CHECK;
goto out;
+ }
pmd = mm_find_pmd(mm, address);
- if (!pmd)
+ if (!pmd) {
+ result = SCAN_PMD_NULL;
goto out;
+ }
anon_vma_lock_write(vma->anon_vma);
@@ -2592,6 +2655,7 @@ static void collapse_huge_page(struct mm
pmd_populate(mm, pmd, pmd_pgtable(_pmd));
spin_unlock(pmd_ptl);
anon_vma_unlock_write(vma->anon_vma);
+ result = SCAN_FAIL;
goto out;
}
@@ -2629,10 +2693,15 @@ static void collapse_huge_page(struct mm
*hpage = NULL;
khugepaged_pages_collapsed++;
+ result = SCAN_SUCCEED;
out_up_write:
up_write(&mm->mmap_sem);
+ trace_mm_collapse_huge_page(mm, isolated, result);
return;
+out_nolock:
+ trace_mm_collapse_huge_page(mm, isolated, result);
+ return;
out:
mem_cgroup_cancel_charge(new_page, memcg);
goto out_up_write;
@@ -2645,8 +2714,8 @@ static int khugepaged_scan_pmd(struct mm
{
pmd_t *pmd;
pte_t *pte, *_pte;
- int ret = 0, none_or_zero = 0;
- struct page *page;
+ int ret = 0, none_or_zero = 0, result = 0;
+ struct page *page = NULL;
unsigned long _address;
spinlock_t *ptl;
int node = NUMA_NO_NODE;
@@ -2655,8 +2724,10 @@ static int khugepaged_scan_pmd(struct mm
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
pmd = mm_find_pmd(mm, address);
- if (!pmd)
+ if (!pmd) {
+ result = SCAN_PMD_NULL;
goto out;
+ }
memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
@@ -2665,19 +2736,25 @@ static int khugepaged_scan_pmd(struct mm
pte_t pteval = *_pte;
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
if (!userfaultfd_armed(vma) &&
- ++none_or_zero <= khugepaged_max_ptes_none)
+ ++none_or_zero <= khugepaged_max_ptes_none) {
continue;
- else
+ } else {
+ result = SCAN_EXCEED_NONE_PTE;
goto out_unmap;
+ }
}
- if (!pte_present(pteval))
+ if (!pte_present(pteval)) {
+ result = SCAN_PTE_NON_PRESENT;
goto out_unmap;
+ }
if (pte_write(pteval))
writable = true;
page = vm_normal_page(vma, _address, pteval);
- if (unlikely(!page))
+ if (unlikely(!page)) {
+ result = SCAN_PAGE_NULL;
goto out_unmap;
+ }
/*
* Record which node the original page is from and save this
* information to khugepaged_node_load[].
@@ -2685,26 +2762,49 @@ static int khugepaged_scan_pmd(struct mm
* hit record.
*/
node = page_to_nid(page);
- if (khugepaged_scan_abort(node))
+ if (khugepaged_scan_abort(node)) {
+ result = SCAN_SCAN_ABORT;
goto out_unmap;
+ }
khugepaged_node_load[node]++;
VM_BUG_ON_PAGE(PageCompound(page), page);
- if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
+ if (!PageLRU(page)) {
+ result = SCAN_SCAN_ABORT;
+ goto out_unmap;
+ }
+ if (PageLocked(page)) {
+ result = SCAN_PAGE_LOCK;
goto out_unmap;
+ }
+ if (!PageAnon(page)) {
+ result = SCAN_PAGE_ANON;
+ goto out_unmap;
+ }
+
/*
* cannot use mapcount: can't collapse if there's a gup pin.
* The page must only be referenced by the scanned process
* and page swap cache.
*/
- if (page_count(page) != 1 + !!PageSwapCache(page))
+ if (page_count(page) != 1 + !!PageSwapCache(page)) {
+ result = SCAN_PAGE_COUNT;
goto out_unmap;
+ }
if (pte_young(pteval) ||
page_is_young(page) || PageReferenced(page) ||
mmu_notifier_test_young(vma->vm_mm, address))
referenced = true;
}
- if (referenced && writable)
- ret = 1;
+ if (writable) {
+ if (referenced) {
+ result = SCAN_SUCCEED;
+ ret = 1;
+ } else {
+ result = SCAN_NO_REFERENCED_PAGE;
+ }
+ } else {
+ result = SCAN_PAGE_RO;
+ }
out_unmap:
pte_unmap_unlock(pte, ptl);
if (ret) {
@@ -2713,6 +2813,8 @@ out_unmap:
collapse_huge_page(mm, address, hpage, vma, node);
}
out:
+ trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced,
+ none_or_zero, result);
return ret;
}
_
Patches currently in -mm which might be from ebru.akagunduz@xxxxxxxxx are
mm-make-optimistic-check-for-swapin-readahead.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
