The patch titled
Subject: mm: move lazily freed pages to inactive list
has been added to the -mm tree. Its filename is
mm-move-lazy-free-pages-to-inactive-list.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-move-lazy-free-pages-to-inactive-list.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-move-lazy-free-pages-to-inactive-list.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Minchan Kim <minchan@xxxxxxxxxx>
Subject: mm: move lazily freed pages to inactive list
MADV_FREE is a hint that it's okay to discard pages if there is memory
pressure and we use reclaimers(ie, kswapd and direct reclaim) to free them
so there is no value keeping them in the active anonymous LRU so this
patch moves them to inactive LRU list's head.
This means that MADV_FREE-ed pages which were living on the inactive list
are reclaimed first because they are more likely to be cold rather than
recently active pages.
An arguable issue for the approach would be whether we should put the page
to the head or tail of the inactive list. I chose head because the kernel
cannot make sure it's really cold or warm for every MADV_FREE usecase but
at least we know it's not *hot*, so landing of inactive head would be a
comprimise for various usecases.
This fixes suboptimal behavior of MADV_FREE when pages living on the
active list will sit there for a long time even under memory pressure
while the inactive list is reclaimed heavily. This basically breaks the
whole purpose of using MADV_FREE to help the system to free memory which
is might not be used.
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Wang, Yalin <Yalin.Wang@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/swap.h | 1 +
mm/madvise.c | 2 ++
mm/swap.c | 35 +++++++++++++++++++++++++++++++++++
3 files changed, 38 insertions(+)
diff -puN include/linux/swap.h~mm-move-lazy-free-pages-to-inactive-list include/linux/swap.h
--- a/include/linux/swap.h~mm-move-lazy-free-pages-to-inactive-list
+++ a/include/linux/swap.h
@@ -308,6 +308,7 @@ extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
+extern void deactivate_page(struct page *page);
extern void swap_setup(void);
extern void add_page_to_unevictable_list(struct page *page);
diff -puN mm/madvise.c~mm-move-lazy-free-pages-to-inactive-list mm/madvise.c
--- a/mm/madvise.c~mm-move-lazy-free-pages-to-inactive-list
+++ a/mm/madvise.c
@@ -340,6 +340,8 @@ static int madvise_free_pte_range(pmd_t
ptent = pte_mkold(ptent);
ptent = pte_mkclean(ptent);
set_pte_at(mm, addr, pte, ptent);
+ if (PageActive(page))
+ deactivate_page(page);
tlb_remove_tlb_entry(tlb, pte, addr);
}
diff -puN mm/swap.c~mm-move-lazy-free-pages-to-inactive-list mm/swap.c
--- a/mm/swap.c~mm-move-lazy-free-pages-to-inactive-list
+++ a/mm/swap.c
@@ -43,6 +43,7 @@ int page_cluster;
static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
/*
* This path almost never happens for VM activity - pages are normally
@@ -789,6 +790,23 @@ static void lru_deactivate_file_fn(struc
update_page_reclaim_stat(lruvec, file, 0);
}
+
+static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
+ void *arg)
+{
+ if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+ int file = page_is_file_cache(page);
+ int lru = page_lru_base_type(page);
+
+ del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
+ ClearPageActive(page);
+ add_page_to_lru_list(page, lruvec, lru);
+
+ __count_vm_event(PGDEACTIVATE);
+ update_page_reclaim_stat(lruvec, file, 0);
+ }
+}
+
/*
* Drain pages out of the cpu's pagevecs.
* Either "cpu" is the current CPU, and preemption has already been
@@ -815,6 +833,10 @@ void lru_add_drain_cpu(int cpu)
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
+ pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+ if (pagevec_count(pvec))
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
activate_page_drain(cpu);
}
@@ -844,6 +866,18 @@ void deactivate_file_page(struct page *p
}
}
+void deactivate_page(struct page *page)
+{
+ if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+ struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+
+ page_cache_get(page);
+ if (!pagevec_add(pvec, page))
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+ put_cpu_var(lru_deactivate_pvecs);
+ }
+}
+
void lru_add_drain(void)
{
lru_add_drain_cpu(get_cpu());
@@ -873,6 +907,7 @@ void lru_add_drain_all(void)
if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
+ pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
schedule_work_on(cpu, work);
_
Patches currently in -mm which might be from minchan@xxxxxxxxxx are
mm-change-deactivate_page-with-deactivate_file_page.patch
mm-vmscan-fix-the-page-state-calculation-in-too_many_isolated.patch
mm-page_isolation-check-pfn-validity-before-access.patch
mm-support-madvisemadv_free.patch
mm-support-madvisemadv_free-fix.patch
mm-support-madvisemadv_free-fix-2.patch
mm-dont-split-thp-page-when-syscall-is-called.patch
mm-dont-split-thp-page-when-syscall-is-called-fix.patch
mm-dont-split-thp-page-when-syscall-is-called-fix-2.patch
mm-free-swp_entry-in-madvise_free.patch
mm-move-lazy-free-pages-to-inactive-list.patch
x86-add-pmd_-for-thp.patch
x86-add-pmd_-for-thp-fix.patch
sparc-add-pmd_-for-thp.patch
sparc-add-pmd_-for-thp-fix.patch
powerpc-add-pmd_-for-thp.patch
arm-add-pmd_mkclean-for-thp.patch
arm64-add-pmd_-for-thp.patch
zram-cosmetic-zram_attr_ro-code-formatting-tweak.patch
zram-use-idr-instead-of-zram_devices-array.patch
zram-factor-out-device-reset-from-reset_store.patch
zram-reorganize-code-layout.patch
zram-add-dynamic-device-add-remove-functionality.patch
zram-add-dynamic-device-add-remove-functionality-fix.patch
zram-remove-max_num_devices-limitation.patch
zram-report-every-added-and-removed-device.patch
zram-trivial-correct-flag-operations-comment.patch
zram-return-zram-device_id-value-from-zram_add.patch
zram-introduce-automatic-device_id-generation.patch
zram-introduce-automatic-device_id-generation-fix.patch
zram-do-not-let-user-enforce-new-device-dev_id.patch
zsmalloc-decouple-handle-and-object.patch
zsmalloc-factor-out-obj_.patch
zsmalloc-support-compaction.patch
zsmalloc-support-compaction-fix.patch
zsmalloc-adjust-zs_almost_full.patch
zram-support-compaction.patch
zsmalloc-record-handle-in-page-private-for-huge-object.patch
zsmalloc-add-fullness-into-stat.patch
zsmalloc-zsmalloc-documentation.patch
mm-zsmallocc-fix-comment-for-get_pages_per_zspage.patch
zram-remove-num_migrated-device-attr.patch
zram-move-compact_store-to-sysfs-functions-area.patch
zram-use-generic-start-end-io-accounting.patch
zram-describe-device-attrs-in-documentation.patch
zram-export-new-io_stat-sysfs-attrs.patch
zram-export-new-mm_stat-sysfs-attrs.patch
zram-deprecate-zram-attrs-sysfs-nodes.patch
linux-next.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
