vmscan: split LRU lists into anon & file sets
Split the LRU lists in two, one set for pages that are backed by real file
systems ("file") and one for pages that are backed by memory and swap
("anon"). The latter includes tmpfs.
The advantage of doing this is that the VM will not have to scan over lots
of anonymous pages (which we generally do not want to swap out), just to
find the page cache pages that it should evict.
This patch has the infrastructure and a basic policy to balance how much
we scan the anon lists and how much we scan the file lists. The big
policy changes are in separate patches.
[lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset]
[kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru]
[kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page]
[hugh@veritas.com: memcg swapbacked pages active]
[hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED]
[akpm@linux-foundation.org: fix /proc/vmstat units]
[nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration]
[kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo]
[kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 5116b78..fc7e9bf 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -61,34 +61,44 @@
si_meminfo_node(&i, nid);
n = sprintf(buf, "\n"
- "Node %d MemTotal: %8lu kB\n"
- "Node %d MemFree: %8lu kB\n"
- "Node %d MemUsed: %8lu kB\n"
- "Node %d Active: %8lu kB\n"
- "Node %d Inactive: %8lu kB\n"
+ "Node %d MemTotal: %8lu kB\n"
+ "Node %d MemFree: %8lu kB\n"
+ "Node %d MemUsed: %8lu kB\n"
+ "Node %d Active: %8lu kB\n"
+ "Node %d Inactive: %8lu kB\n"
+ "Node %d Active(anon): %8lu kB\n"
+ "Node %d Inactive(anon): %8lu kB\n"
+ "Node %d Active(file): %8lu kB\n"
+ "Node %d Inactive(file): %8lu kB\n"
#ifdef CONFIG_HIGHMEM
- "Node %d HighTotal: %8lu kB\n"
- "Node %d HighFree: %8lu kB\n"
- "Node %d LowTotal: %8lu kB\n"
- "Node %d LowFree: %8lu kB\n"
+ "Node %d HighTotal: %8lu kB\n"
+ "Node %d HighFree: %8lu kB\n"
+ "Node %d LowTotal: %8lu kB\n"
+ "Node %d LowFree: %8lu kB\n"
#endif
- "Node %d Dirty: %8lu kB\n"
- "Node %d Writeback: %8lu kB\n"
- "Node %d FilePages: %8lu kB\n"
- "Node %d Mapped: %8lu kB\n"
- "Node %d AnonPages: %8lu kB\n"
- "Node %d PageTables: %8lu kB\n"
- "Node %d NFS_Unstable: %8lu kB\n"
- "Node %d Bounce: %8lu kB\n"
- "Node %d WritebackTmp: %8lu kB\n"
- "Node %d Slab: %8lu kB\n"
- "Node %d SReclaimable: %8lu kB\n"
- "Node %d SUnreclaim: %8lu kB\n",
+ "Node %d Dirty: %8lu kB\n"
+ "Node %d Writeback: %8lu kB\n"
+ "Node %d FilePages: %8lu kB\n"
+ "Node %d Mapped: %8lu kB\n"
+ "Node %d AnonPages: %8lu kB\n"
+ "Node %d PageTables: %8lu kB\n"
+ "Node %d NFS_Unstable: %8lu kB\n"
+ "Node %d Bounce: %8lu kB\n"
+ "Node %d WritebackTmp: %8lu kB\n"
+ "Node %d Slab: %8lu kB\n"
+ "Node %d SReclaimable: %8lu kB\n"
+ "Node %d SUnreclaim: %8lu kB\n",
nid, K(i.totalram),
nid, K(i.freeram),
nid, K(i.totalram - i.freeram),
- nid, K(node_page_state(nid, NR_ACTIVE)),
- nid, K(node_page_state(nid, NR_INACTIVE)),
+ nid, K(node_page_state(nid, NR_ACTIVE_ANON) +
+ node_page_state(nid, NR_ACTIVE_FILE)),
+ nid, K(node_page_state(nid, NR_INACTIVE_ANON) +
+ node_page_state(nid, NR_INACTIVE_FILE)),
+ nid, K(node_page_state(nid, NR_ACTIVE_ANON)),
+ nid, K(node_page_state(nid, NR_INACTIVE_ANON)),
+ nid, K(node_page_state(nid, NR_ACTIVE_FILE)),
+ nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
#ifdef CONFIG_HIGHMEM
nid, K(i.totalhigh),
nid, K(i.freehigh),
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index c4a8a06..62d8bd8 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1791,7 +1791,7 @@
SetPageUptodate(page);
unlock_page(page);
if (!pagevec_add(plru_pvec, page))
- __pagevec_lru_add(plru_pvec);
+ __pagevec_lru_add_file(plru_pvec);
data += PAGE_CACHE_SIZE;
}
return;
@@ -1925,7 +1925,7 @@
bytes_read = 0;
}
- pagevec_lru_add(&lru_pvec);
+ pagevec_lru_add_file(&lru_pvec);
/* need to free smb_read_data buf before exit */
if (smb_read_data) {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2ab70d4..efdba2e 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1517,7 +1517,7 @@
if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
GFP_KERNEL)) {
pagevec_add(&lru_pvec, page);
- pagevec_lru_add(&lru_pvec);
+ pagevec_lru_add_file(&lru_pvec);
SetPageUptodate(page);
unlock_page(page);
} else
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index d020866..3140a44 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -439,7 +439,7 @@
pages[nr] = *cached_page;
page_cache_get(*cached_page);
if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
- __pagevec_lru_add(lru_pvec);
+ __pagevec_lru_add_file(lru_pvec);
*cached_page = NULL;
}
index++;
@@ -2084,7 +2084,7 @@
OSYNC_METADATA|OSYNC_DATA);
}
}
- pagevec_lru_add(&lru_pvec);
+ pagevec_lru_add_file(&lru_pvec);
ntfs_debug("Done. Returning %s (written 0x%lx, status %li).",
written ? "written" : "status", (unsigned long)written,
(long)status);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 59ea42e..b8edb28 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -136,6 +136,8 @@
unsigned long allowed;
struct vmalloc_info vmi;
long cached;
+ unsigned long pages[NR_LRU_LISTS];
+ int lru;
/*
* display in kilobytes.
@@ -154,51 +156,62 @@
get_vmalloc_info(&vmi);
+ for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+ pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
/*
* Tagged format, for easy grepping and expansion.
*/
len = sprintf(page,
- "MemTotal: %8lu kB\n"
- "MemFree: %8lu kB\n"
- "Buffers: %8lu kB\n"
- "Cached: %8lu kB\n"
- "SwapCached: %8lu kB\n"
- "Active: %8lu kB\n"
- "Inactive: %8lu kB\n"
+ "MemTotal: %8lu kB\n"
+ "MemFree: %8lu kB\n"
+ "Buffers: %8lu kB\n"
+ "Cached: %8lu kB\n"
+ "SwapCached: %8lu kB\n"
+ "Active: %8lu kB\n"
+ "Inactive: %8lu kB\n"
+ "Active(anon): %8lu kB\n"
+ "Inactive(anon): %8lu kB\n"
+ "Active(file): %8lu kB\n"
+ "Inactive(file): %8lu kB\n"
#ifdef CONFIG_HIGHMEM
- "HighTotal: %8lu kB\n"
- "HighFree: %8lu kB\n"
- "LowTotal: %8lu kB\n"
- "LowFree: %8lu kB\n"
+ "HighTotal: %8lu kB\n"
+ "HighFree: %8lu kB\n"
+ "LowTotal: %8lu kB\n"
+ "LowFree: %8lu kB\n"
#endif
- "SwapTotal: %8lu kB\n"
- "SwapFree: %8lu kB\n"
- "Dirty: %8lu kB\n"
- "Writeback: %8lu kB\n"
- "AnonPages: %8lu kB\n"
- "Mapped: %8lu kB\n"
- "Slab: %8lu kB\n"
- "SReclaimable: %8lu kB\n"
- "SUnreclaim: %8lu kB\n"
- "PageTables: %8lu kB\n"
+ "SwapTotal: %8lu kB\n"
+ "SwapFree: %8lu kB\n"
+ "Dirty: %8lu kB\n"
+ "Writeback: %8lu kB\n"
+ "AnonPages: %8lu kB\n"
+ "Mapped: %8lu kB\n"
+ "Slab: %8lu kB\n"
+ "SReclaimable: %8lu kB\n"
+ "SUnreclaim: %8lu kB\n"
+ "PageTables: %8lu kB\n"
#ifdef CONFIG_QUICKLIST
- "Quicklists: %8lu kB\n"
+ "Quicklists: %8lu kB\n"
#endif
- "NFS_Unstable: %8lu kB\n"
- "Bounce: %8lu kB\n"
- "WritebackTmp: %8lu kB\n"
- "CommitLimit: %8lu kB\n"
- "Committed_AS: %8lu kB\n"
- "VmallocTotal: %8lu kB\n"
- "VmallocUsed: %8lu kB\n"
- "VmallocChunk: %8lu kB\n",
+ "NFS_Unstable: %8lu kB\n"
+ "Bounce: %8lu kB\n"
+ "WritebackTmp: %8lu kB\n"
+ "CommitLimit: %8lu kB\n"
+ "Committed_AS: %8lu kB\n"
+ "VmallocTotal: %8lu kB\n"
+ "VmallocUsed: %8lu kB\n"
+ "VmallocChunk: %8lu kB\n",
K(i.totalram),
K(i.freeram),
K(i.bufferram),
K(cached),
K(total_swapcache_pages),
- K(global_page_state(NR_ACTIVE)),
- K(global_page_state(NR_INACTIVE)),
+ K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]),
+ K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+ K(pages[LRU_ACTIVE_ANON]),
+ K(pages[LRU_INACTIVE_ANON]),
+ K(pages[LRU_ACTIVE_FILE]),
+ K(pages[LRU_INACTIVE_FILE]),
#ifdef CONFIG_HIGHMEM
K(i.totalhigh),
K(i.freehigh),
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 5145cb9..76acdbc 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -112,12 +112,12 @@
goto add_error;
if (!pagevec_add(&lru_pvec, page))
- __pagevec_lru_add(&lru_pvec);
+ __pagevec_lru_add_file(&lru_pvec);
unlock_page(page);
}
- pagevec_lru_add(&lru_pvec);
+ pagevec_lru_add_file(&lru_pvec);
return 0;
fsize_exceeded:
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0a24d55..bee52ab 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -175,6 +175,8 @@
* BDI_CAP_READ_MAP: Can be mapped for reading
* BDI_CAP_WRITE_MAP: Can be mapped for writing
* BDI_CAP_EXEC_MAP: Can be mapped for execution
+ *
+ * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
@@ -184,6 +186,7 @@
#define BDI_CAP_WRITE_MAP 0x00000020
#define BDI_CAP_EXEC_MAP 0x00000040
#define BDI_CAP_NO_ACCT_WB 0x00000080
+#define BDI_CAP_SWAP_BACKED 0x00000100
#define BDI_CAP_VMFLAGS \
(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
@@ -248,6 +251,11 @@
BDI_CAP_NO_WRITEBACK));
}
+static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
+{
+ return bdi->capabilities & BDI_CAP_SWAP_BACKED;
+}
+
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -258,4 +266,9 @@
return bdi_cap_account_dirty(mapping->backing_dev_info);
}
+static inline bool mapping_cap_swap_backed(struct address_space *mapping)
+{
+ return bdi_cap_swap_backed(mapping->backing_dev_info);
+}
+
#endif /* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a6ac0d4..8d8f05c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -44,7 +44,7 @@
unsigned long *scanned, int order,
int mode, struct zone *z,
struct mem_cgroup *mem_cont,
- int active);
+ int active, int file);
extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 96e9704..2eb5994 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -5,7 +5,7 @@
* page_is_file_cache - should the page be on a file LRU or anon LRU?
* @page: the page to test
*
- * Returns !0 if @page is page cache page backed by a regular filesystem,
+ * Returns LRU_FILE if @page is page cache page backed by a regular filesystem,
* or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed.
* Used by functions that manipulate the LRU lists, to sort a page
* onto the right LRU list.
@@ -20,7 +20,7 @@
return 0;
/* The page is page cache backed by a normal filesystem. */
- return 1;
+ return LRU_FILE;
}
static inline void
@@ -38,39 +38,64 @@
}
static inline void
-add_page_to_active_list(struct zone *zone, struct page *page)
+add_page_to_inactive_anon_list(struct zone *zone, struct page *page)
{
- add_page_to_lru_list(zone, page, LRU_ACTIVE);
+ add_page_to_lru_list(zone, page, LRU_INACTIVE_ANON);
}
static inline void
-add_page_to_inactive_list(struct zone *zone, struct page *page)
+add_page_to_active_anon_list(struct zone *zone, struct page *page)
{
- add_page_to_lru_list(zone, page, LRU_INACTIVE);
+ add_page_to_lru_list(zone, page, LRU_ACTIVE_ANON);
}
static inline void
-del_page_from_active_list(struct zone *zone, struct page *page)
+add_page_to_inactive_file_list(struct zone *zone, struct page *page)
{
- del_page_from_lru_list(zone, page, LRU_ACTIVE);
+ add_page_to_lru_list(zone, page, LRU_INACTIVE_FILE);
}
static inline void
-del_page_from_inactive_list(struct zone *zone, struct page *page)
+add_page_to_active_file_list(struct zone *zone, struct page *page)
{
- del_page_from_lru_list(zone, page, LRU_INACTIVE);
+ add_page_to_lru_list(zone, page, LRU_ACTIVE_FILE);
+}
+
+static inline void
+del_page_from_inactive_anon_list(struct zone *zone, struct page *page)
+{
+ del_page_from_lru_list(zone, page, LRU_INACTIVE_ANON);
+}
+
+static inline void
+del_page_from_active_anon_list(struct zone *zone, struct page *page)
+{
+ del_page_from_lru_list(zone, page, LRU_ACTIVE_ANON);
+}
+
+static inline void
+del_page_from_inactive_file_list(struct zone *zone, struct page *page)
+{
+ del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
+}
+
+static inline void
+del_page_from_active_file_list(struct zone *zone, struct page *page)
+{
+ del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
}
static inline void
del_page_from_lru(struct zone *zone, struct page *page)
{
- enum lru_list l = LRU_INACTIVE;
+ enum lru_list l = LRU_BASE;
list_del(&page->lru);
if (PageActive(page)) {
__ClearPageActive(page);
- l = LRU_ACTIVE;
+ l += LRU_ACTIVE;
}
+ l += page_is_file_cache(page);
__dec_zone_state(zone, NR_LRU_BASE + l);
}
@@ -87,6 +112,7 @@
if (PageActive(page))
lru += LRU_ACTIVE;
+ lru += page_is_file_cache(page);
return lru;
}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 156e18f..59a4c8f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -82,21 +82,23 @@
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
NR_LRU_BASE,
- NR_INACTIVE = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
- NR_ACTIVE, /* " " " " " */
+ NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+ NR_ACTIVE_ANON, /* " " " " " */
+ NR_INACTIVE_FILE, /* " " " " " */
+ NR_ACTIVE_FILE, /* " " " " " */
NR_ANON_PAGES, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
NR_FILE_PAGES,
NR_FILE_DIRTY,
NR_WRITEBACK,
- /* Second 128 byte cacheline */
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
NR_PAGETABLE, /* used for pagetables */
NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_BOUNCE,
NR_VMSCAN_WRITE,
+ /* Second 128 byte cacheline */
NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */
#ifdef CONFIG_NUMA
NUMA_HIT, /* allocated in intended node */
@@ -108,17 +110,36 @@
#endif
NR_VM_ZONE_STAT_ITEMS };
+/*
+ * We do arithmetic on the LRU lists in various places in the code,
+ * so it is important to keep the active lists LRU_ACTIVE higher in
+ * the array than the corresponding inactive lists, and to keep
+ * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists.
+ *
+ * This has to be kept in sync with the statistics in zone_stat_item
+ * above and the descriptions in vmstat_text in mm/vmstat.c
+ */
+#define LRU_BASE 0
+#define LRU_ACTIVE 1
+#define LRU_FILE 2
+
enum lru_list {
- LRU_BASE,
- LRU_INACTIVE=LRU_BASE, /* must match order of NR_[IN]ACTIVE */
- LRU_ACTIVE, /* " " " " " */
+ LRU_INACTIVE_ANON = LRU_BASE,
+ LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
+ LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
+ LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
NR_LRU_LISTS };
#define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
+static inline int is_file_lru(enum lru_list l)
+{
+ return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE);
+}
+
static inline int is_active_lru(enum lru_list l)
{
- return (l == LRU_ACTIVE);
+ return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE);
}
struct per_cpu_pages {
@@ -269,6 +290,18 @@
struct list_head list;
unsigned long nr_scan;
} lru[NR_LRU_LISTS];
+
+ /*
+ * The pageout code in vmscan.c keeps track of how many of the
+ * mem/swap backed and file backed pages are refeferenced.
+ * The higher the rotated/scanned ratio, the more valuable
+ * that cache is.
+ *
+ * The anon LRU stats live in [0], file LRU stats in [1]
+ */
+ unsigned long recent_rotated[2];
+ unsigned long recent_scanned[2];
+
unsigned long pages_scanned; /* since last reclaim */
unsigned long flags; /* zone flags, see below */
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index fea3a98..5fc96a4 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -81,20 +81,37 @@
__pagevec_free(pvec);
}
-static inline void __pagevec_lru_add(struct pagevec *pvec)
+static inline void __pagevec_lru_add_anon(struct pagevec *pvec)
{
- ____pagevec_lru_add(pvec, LRU_INACTIVE);
+ ____pagevec_lru_add(pvec, LRU_INACTIVE_ANON);
}
-static inline void __pagevec_lru_add_active(struct pagevec *pvec)
+static inline void __pagevec_lru_add_active_anon(struct pagevec *pvec)
{
- ____pagevec_lru_add(pvec, LRU_ACTIVE);
+ ____pagevec_lru_add(pvec, LRU_ACTIVE_ANON);
}
-static inline void pagevec_lru_add(struct pagevec *pvec)
+static inline void __pagevec_lru_add_file(struct pagevec *pvec)
+{
+ ____pagevec_lru_add(pvec, LRU_INACTIVE_FILE);
+}
+
+static inline void __pagevec_lru_add_active_file(struct pagevec *pvec)
+{
+ ____pagevec_lru_add(pvec, LRU_ACTIVE_FILE);
+}
+
+
+static inline void pagevec_lru_add_file(struct pagevec *pvec)
{
if (pagevec_count(pvec))
- __pagevec_lru_add(pvec);
+ __pagevec_lru_add_file(pvec);
+}
+
+static inline void pagevec_lru_add_anon(struct pagevec *pvec)
+{
+ if (pagevec_count(pvec))
+ __pagevec_lru_add_anon(pvec);
}
#endif /* _LINUX_PAGEVEC_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 833be56..7d09d79 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -184,14 +184,24 @@
* lru_cache_add: add a page to the page lists
* @page: the page to add
*/
-static inline void lru_cache_add(struct page *page)
+static inline void lru_cache_add_anon(struct page *page)
{
- __lru_cache_add(page, LRU_INACTIVE);
+ __lru_cache_add(page, LRU_INACTIVE_ANON);
}
-static inline void lru_cache_add_active(struct page *page)
+static inline void lru_cache_add_active_anon(struct page *page)
{
- __lru_cache_add(page, LRU_ACTIVE);
+ __lru_cache_add(page, LRU_ACTIVE_ANON);
+}
+
+static inline void lru_cache_add_file(struct page *page)
+{
+ __lru_cache_add(page, LRU_INACTIVE_FILE);
+}
+
+static inline void lru_cache_add_active_file(struct page *page)
+{
+ __lru_cache_add(page, LRU_ACTIVE_FILE);
}
/* linux/mm/vmscan.c */
@@ -199,7 +209,7 @@
gfp_t gfp_mask);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
gfp_t gfp_mask);
-extern int __isolate_lru_page(struct page *page, int mode);
+extern int __isolate_lru_page(struct page *page, int mode, int file);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
extern int remove_mapping(struct address_space *mapping, struct page *page);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 58334d4..ff5179f 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -159,6 +159,16 @@
return x;
}
+extern unsigned long global_lru_pages(void);
+
+static inline unsigned long zone_lru_pages(struct zone *zone)
+{
+ return (zone_page_state(zone, NR_ACTIVE_ANON)
+ + zone_page_state(zone, NR_ACTIVE_FILE)
+ + zone_page_state(zone, NR_INACTIVE_ANON)
+ + zone_page_state(zone, NR_INACTIVE_FILE));
+}
+
#ifdef CONFIG_NUMA
/*
* Determine the per node value of a stat item. This function
diff --git a/mm/filemap.c b/mm/filemap.c
index 903bf31..a1ddd25 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -33,6 +33,7 @@
#include <linux/cpuset.h>
#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
#include <linux/memcontrol.h>
+#include <linux/mm_inline.h> /* for page_is_file_cache() */
#include "internal.h"
/*
@@ -492,9 +493,24 @@
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
- int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
- if (ret == 0)
- lru_cache_add(page);
+ int ret;
+
+ /*
+ * Splice_read and readahead add shmem/tmpfs pages into the page cache
+ * before shmem_readpage has a chance to mark them as SwapBacked: they
+ * need to go on the active_anon lru below, and mem_cgroup_cache_charge
+ * (called in add_to_page_cache) needs to know where they're going too.
+ */
+ if (mapping_cap_swap_backed(mapping))
+ SetPageSwapBacked(page);
+
+ ret = add_to_page_cache(page, mapping, offset, gfp_mask);
+ if (ret == 0) {
+ if (page_is_file_cache(page))
+ lru_cache_add_file(page);
+ else
+ lru_cache_add_active_anon(page);
+ }
return ret;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3863386..2fc7fdd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1459,11 +1459,11 @@
{
struct hstate *h = &default_hstate;
return sprintf(buf,
- "HugePages_Total: %5lu\n"
- "HugePages_Free: %5lu\n"
- "HugePages_Rsvd: %5lu\n"
- "HugePages_Surp: %5lu\n"
- "Hugepagesize: %5lu kB\n",
+ "HugePages_Total: %5lu\n"
+ "HugePages_Free: %5lu\n"
+ "HugePages_Rsvd: %5lu\n"
+ "HugePages_Surp: %5lu\n"
+ "Hugepagesize: %8lu kB\n",
h->nr_huge_pages,
h->free_huge_pages,
h->resv_huge_pages,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c0cbd77..27e9e75 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -162,6 +162,7 @@
};
#define PAGE_CGROUP_FLAG_CACHE (0x1) /* charged as cache */
#define PAGE_CGROUP_FLAG_ACTIVE (0x2) /* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE (0x4) /* page is file system backed */
static int page_cgroup_nid(struct page_cgroup *pc)
{
@@ -177,6 +178,7 @@
MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
MEM_CGROUP_CHARGE_TYPE_MAPPED,
MEM_CGROUP_CHARGE_TYPE_FORCE, /* used by force_empty */
+ MEM_CGROUP_CHARGE_TYPE_SHMEM, /* used by page migration of shmem */
};
/*
@@ -288,8 +290,12 @@
static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
- int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
- int lru = !!from;
+ int lru = LRU_BASE;
+
+ if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ lru += LRU_ACTIVE;
+ if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+ lru += LRU_FILE;
MEM_CGROUP_ZSTAT(mz, lru) -= 1;
@@ -300,10 +306,12 @@
static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
- int lru = LRU_INACTIVE;
+ int lru = LRU_BASE;
if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
lru += LRU_ACTIVE;
+ if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+ lru += LRU_FILE;
MEM_CGROUP_ZSTAT(mz, lru) += 1;
list_add(&pc->lru, &mz->lists[lru]);
@@ -314,10 +322,9 @@
static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
{
struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
- int lru = LRU_INACTIVE;
-
- if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
- lru += LRU_ACTIVE;
+ int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+ int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
+ int lru = LRU_FILE * !!file + !!from;
MEM_CGROUP_ZSTAT(mz, lru) -= 1;
@@ -326,7 +333,7 @@
else
pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
- lru = !!active;
+ lru = LRU_FILE * !!file + !!active;
MEM_CGROUP_ZSTAT(mz, lru) += 1;
list_move(&pc->lru, &mz->lists[lru]);
}
@@ -391,21 +398,6 @@
}
/*
- * This function is called from vmscan.c. In page reclaiming loop. balance
- * between active and inactive list is calculated. For memory controller
- * page reclaiming, we should use using mem_cgroup's imbalance rather than
- * zone's global lru imbalance.
- */
-long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
-{
- unsigned long active, inactive;
- /* active and inactive are the number of pages. 'long' is ok.*/
- active = mem_cgroup_get_all_zonestat(mem, LRU_ACTIVE);
- inactive = mem_cgroup_get_all_zonestat(mem, LRU_INACTIVE);
- return (long) (active / (inactive + 1));
-}
-
-/*
* prev_priority control...this will be used in memory reclaim path.
*/
int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
@@ -450,7 +442,7 @@
unsigned long *scanned, int order,
int mode, struct zone *z,
struct mem_cgroup *mem_cont,
- int active)
+ int active, int file)
{
unsigned long nr_taken = 0;
struct page *page;
@@ -461,7 +453,7 @@
int nid = z->zone_pgdat->node_id;
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
- int lru = !!active;
+ int lru = LRU_FILE * !!file + !!active;
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
@@ -477,6 +469,9 @@
if (unlikely(!PageLRU(page)))
continue;
+ /*
+ * TODO: play better with lumpy reclaim, grabbing anything.
+ */
if (PageActive(page) && !active) {
__mem_cgroup_move_lists(pc, true);
continue;
@@ -489,7 +484,7 @@
scan++;
list_move(&pc->lru, &pc_list);
- if (__isolate_lru_page(page, mode) == 0) {
+ if (__isolate_lru_page(page, mode, file) == 0) {
list_move(&page->lru, dst);
nr_taken++;
}
@@ -575,10 +570,16 @@
* If a page is accounted as a page cache, insert to inactive list.
* If anon, insert to active list.
*/
- if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
+ if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
pc->flags = PAGE_CGROUP_FLAG_CACHE;
- else
+ if (page_is_file_cache(page))
+ pc->flags |= PAGE_CGROUP_FLAG_FILE;
+ else
+ pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+ } else if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
+ else /* MEM_CGROUP_CHARGE_TYPE_SHMEM */
+ pc->flags = PAGE_CGROUP_FLAG_CACHE | PAGE_CGROUP_FLAG_ACTIVE;
lock_page_cgroup(page);
if (unlikely(page_get_page_cgroup(page))) {
@@ -737,8 +738,12 @@
if (pc) {
mem = pc->mem_cgroup;
css_get(&mem->css);
- if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
- ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+ if (pc->flags & PAGE_CGROUP_FLAG_CACHE) {
+ if (page_is_file_cache(page))
+ ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+ else
+ ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+ }
}
unlock_page_cgroup(page);
if (mem) {
@@ -982,14 +987,21 @@
}
/* showing # of active pages */
{
- unsigned long active, inactive;
+ unsigned long active_anon, inactive_anon;
+ unsigned long active_file, inactive_file;
- inactive = mem_cgroup_get_all_zonestat(mem_cont,
- LRU_INACTIVE);
- active = mem_cgroup_get_all_zonestat(mem_cont,
- LRU_ACTIVE);
- cb->fill(cb, "active", (active) * PAGE_SIZE);
- cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
+ inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
+ LRU_INACTIVE_ANON);
+ active_anon = mem_cgroup_get_all_zonestat(mem_cont,
+ LRU_ACTIVE_ANON);
+ inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
+ LRU_INACTIVE_FILE);
+ active_file = mem_cgroup_get_all_zonestat(mem_cont,
+ LRU_ACTIVE_FILE);
+ cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
+ cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
+ cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
+ cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
}
return 0;
}
diff --git a/mm/memory.c b/mm/memory.c
index 7512933..71cdefd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1889,7 +1889,7 @@
set_pte_at(mm, address, page_table, entry);
update_mmu_cache(vma, address, entry);
SetPageSwapBacked(new_page);
- lru_cache_add_active(new_page);
+ lru_cache_add_active_anon(new_page);
page_add_new_anon_rmap(new_page, vma, address);
if (old_page) {
@@ -2384,7 +2384,7 @@
goto release;
inc_mm_counter(mm, anon_rss);
SetPageSwapBacked(page);
- lru_cache_add_active(page);
+ lru_cache_add_active_anon(page);
page_add_new_anon_rmap(page, vma, address);
set_pte_at(mm, address, page_table, entry);
@@ -2526,7 +2526,7 @@
if (anon) {
inc_mm_counter(mm, anon_rss);
SetPageSwapBacked(page);
- lru_cache_add_active(page);
+ lru_cache_add_active_anon(page);
page_add_new_anon_rmap(page, vma, address);
} else {
inc_mm_counter(mm, file_rss);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b40f6d5..2970e35 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -329,9 +329,7 @@
struct zone *z =
&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
- x += zone_page_state(z, NR_FREE_PAGES)
- + zone_page_state(z, NR_INACTIVE)
- + zone_page_state(z, NR_ACTIVE);
+ x += zone_page_state(z, NR_FREE_PAGES) + zone_lru_pages(z);
}
/*
* Make sure that the number of highmem pages is never larger
@@ -355,9 +353,7 @@
{
unsigned long x;
- x = global_page_state(NR_FREE_PAGES)
- + global_page_state(NR_INACTIVE)
- + global_page_state(NR_ACTIVE);
+ x = global_page_state(NR_FREE_PAGES) + global_lru_pages();
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2099904..740a16a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1864,10 +1864,13 @@
}
}
- printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu\n"
+ printk("Active_anon:%lu active_file:%lu inactive_anon%lu\n"
+ " inactive_file:%lu dirty:%lu writeback:%lu unstable:%lu\n"
" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
- global_page_state(NR_ACTIVE),
- global_page_state(NR_INACTIVE),
+ global_page_state(NR_ACTIVE_ANON),
+ global_page_state(NR_ACTIVE_FILE),
+ global_page_state(NR_INACTIVE_ANON),
+ global_page_state(NR_INACTIVE_FILE),
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
@@ -1890,8 +1893,10 @@
" min:%lukB"
" low:%lukB"
" high:%lukB"
- " active:%lukB"
- " inactive:%lukB"
+ " active_anon:%lukB"
+ " inactive_anon:%lukB"
+ " active_file:%lukB"
+ " inactive_file:%lukB"
" present:%lukB"
" pages_scanned:%lu"
" all_unreclaimable? %s"
@@ -1901,8 +1906,10 @@
K(zone->pages_min),
K(zone->pages_low),
K(zone->pages_high),
- K(zone_page_state(zone, NR_ACTIVE)),
- K(zone_page_state(zone, NR_INACTIVE)),
+ K(zone_page_state(zone, NR_ACTIVE_ANON)),
+ K(zone_page_state(zone, NR_INACTIVE_ANON)),
+ K(zone_page_state(zone, NR_ACTIVE_FILE)),
+ K(zone_page_state(zone, NR_INACTIVE_FILE)),
K(zone->present_pages),
zone->pages_scanned,
(zone_is_all_unreclaimable(zone) ? "yes" : "no")
@@ -3472,6 +3479,10 @@
INIT_LIST_HEAD(&zone->lru[l].list);
zone->lru[l].nr_scan = 0;
}
+ zone->recent_rotated[0] = 0;
+ zone->recent_rotated[1] = 0;
+ zone->recent_scanned[0] = 0;
+ zone->recent_scanned[1] = 0;
zap_zone_vm_stats(zone);
zone->flags = 0;
if (!size)
diff --git a/mm/readahead.c b/mm/readahead.c
index 6cbd9a7..bec83c1 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -229,7 +229,7 @@
*/
unsigned long max_sane_readahead(unsigned long nr)
{
- return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE)
+ return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
}
diff --git a/mm/shmem.c b/mm/shmem.c
index fd421ed..fc2ccf7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -199,7 +199,7 @@
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = default_unplug_io_fn,
};
diff --git a/mm/swap.c b/mm/swap.c
index 88a3948..0b1974a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -116,7 +116,8 @@
spin_lock(&zone->lru_lock);
}
if (PageLRU(page) && !PageActive(page)) {
- list_move_tail(&page->lru, &zone->lru[LRU_INACTIVE].list);
+ int lru = page_is_file_cache(page);
+ list_move_tail(&page->lru, &zone->lru[lru].list);
pgmoved++;
}
}
@@ -157,11 +158,18 @@
spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && !PageActive(page)) {
- del_page_from_inactive_list(zone, page);
+ int file = page_is_file_cache(page);
+ int lru = LRU_BASE + file;
+ del_page_from_lru_list(zone, page, lru);
+
SetPageActive(page);
- add_page_to_active_list(zone, page);
+ lru += LRU_ACTIVE;
+ add_page_to_lru_list(zone, page, lru);
__count_vm_event(PGACTIVATE);
mem_cgroup_move_lists(page, true);
+
+ zone->recent_rotated[!!file]++;
+ zone->recent_scanned[!!file]++;
}
spin_unlock_irq(&zone->lru_lock);
}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7a3ece0..ea62084 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -33,7 +33,7 @@
};
static struct backing_dev_info swap_backing_dev_info = {
- .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = swap_unplug_io_fn,
};
@@ -310,7 +310,7 @@
/*
* Initiate read into locked page and return.
*/
- lru_cache_add_active(new_page);
+ lru_cache_add_active_anon(new_page);
swap_readpage(NULL, new_page);
return new_page;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e656035..d10d2f9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -78,7 +78,7 @@
unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
unsigned long *scanned, int order, int mode,
struct zone *z, struct mem_cgroup *mem_cont,
- int active);
+ int active, int file);
};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
@@ -680,7 +680,7 @@
*
* returns 0 on success, -ve errno on failure.
*/
-int __isolate_lru_page(struct page *page, int mode)
+int __isolate_lru_page(struct page *page, int mode, int file)
{
int ret = -EINVAL;
@@ -696,6 +696,9 @@
if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
return ret;
+ if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
+ return ret;
+
ret = -EBUSY;
if (likely(get_page_unless_zero(page))) {
/*
@@ -726,12 +729,13 @@
* @scanned: The number of pages that were scanned.
* @order: The caller's attempted allocation order
* @mode: One of the LRU isolation modes
+ * @file: True [1] if isolating file [!anon] pages
*
* returns how many pages were moved onto *@dst.
*/
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct list_head *src, struct list_head *dst,
- unsigned long *scanned, int order, int mode)
+ unsigned long *scanned, int order, int mode, int file)
{
unsigned long nr_taken = 0;
unsigned long scan;
@@ -748,7 +752,7 @@
VM_BUG_ON(!PageLRU(page));
- switch (__isolate_lru_page(page, mode)) {
+ switch (__isolate_lru_page(page, mode, file)) {
case 0:
list_move(&page->lru, dst);
nr_taken++;
@@ -791,10 +795,11 @@
break;
cursor_page = pfn_to_page(pfn);
+
/* Check that we have not crossed a zone boundary. */
if (unlikely(page_zone_id(cursor_page) != zone_id))
continue;
- switch (__isolate_lru_page(cursor_page, mode)) {
+ switch (__isolate_lru_page(cursor_page, mode, file)) {
case 0:
list_move(&cursor_page->lru, dst);
nr_taken++;
@@ -819,30 +824,37 @@
unsigned long *scanned, int order,
int mode, struct zone *z,
struct mem_cgroup *mem_cont,
- int active)
+ int active, int file)
{
+ int lru = LRU_BASE;
if (active)
- return isolate_lru_pages(nr, &z->lru[LRU_ACTIVE].list, dst,
- scanned, order, mode);
- else
- return isolate_lru_pages(nr, &z->lru[LRU_INACTIVE].list, dst,
- scanned, order, mode);
+ lru += LRU_ACTIVE;
+ if (file)
+ lru += LRU_FILE;
+ return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
+ mode, !!file);
}
/*
* clear_active_flags() is a helper for shrink_active_list(), clearing
* any active bits from the pages in the list.
*/
-static unsigned long clear_active_flags(struct list_head *page_list)
+static unsigned long clear_active_flags(struct list_head *page_list,
+ unsigned int *count)
{
int nr_active = 0;
+ int lru;
struct page *page;
- list_for_each_entry(page, page_list, lru)
+ list_for_each_entry(page, page_list, lru) {
+ lru = page_is_file_cache(page);
if (PageActive(page)) {
+ lru += LRU_ACTIVE;
ClearPageActive(page);
nr_active++;
}
+ count[lru]++;
+ }
return nr_active;
}
@@ -880,12 +892,12 @@
spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && get_page_unless_zero(page)) {
+ int lru = LRU_BASE;
ret = 0;
ClearPageLRU(page);
- if (PageActive(page))
- del_page_from_active_list(zone, page);
- else
- del_page_from_inactive_list(zone, page);
+
+ lru += page_is_file_cache(page) + !!PageActive(page);
+ del_page_from_lru_list(zone, page, lru);
}
spin_unlock_irq(&zone->lru_lock);
}
@@ -897,7 +909,7 @@
* of reclaimed pages
*/
static unsigned long shrink_inactive_list(unsigned long max_scan,
- struct zone *zone, struct scan_control *sc)
+ struct zone *zone, struct scan_control *sc, int file)
{
LIST_HEAD(page_list);
struct pagevec pvec;
@@ -914,20 +926,32 @@
unsigned long nr_scan;
unsigned long nr_freed;
unsigned long nr_active;
+ unsigned int count[NR_LRU_LISTS] = { 0, };
+ int mode = (sc->order > PAGE_ALLOC_COSTLY_ORDER) ?
+ ISOLATE_BOTH : ISOLATE_INACTIVE;
nr_taken = sc->isolate_pages(sc->swap_cluster_max,
- &page_list, &nr_scan, sc->order,
- (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
- ISOLATE_BOTH : ISOLATE_INACTIVE,
- zone, sc->mem_cgroup, 0);
- nr_active = clear_active_flags(&page_list);
+ &page_list, &nr_scan, sc->order, mode,
+ zone, sc->mem_cgroup, 0, file);
+ nr_active = clear_active_flags(&page_list, count);
__count_vm_events(PGDEACTIVATE, nr_active);
- __mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
- __mod_zone_page_state(zone, NR_INACTIVE,
- -(nr_taken - nr_active));
- if (scan_global_lru(sc))
+ __mod_zone_page_state(zone, NR_ACTIVE_FILE,
+ -count[LRU_ACTIVE_FILE]);
+ __mod_zone_page_state(zone, NR_INACTIVE_FILE,
+ -count[LRU_INACTIVE_FILE]);
+ __mod_zone_page_state(zone, NR_ACTIVE_ANON,
+ -count[LRU_ACTIVE_ANON]);
+ __mod_zone_page_state(zone, NR_INACTIVE_ANON,
+ -count[LRU_INACTIVE_ANON]);
+
+ if (scan_global_lru(sc)) {
zone->pages_scanned += nr_scan;
+ zone->recent_scanned[0] += count[LRU_INACTIVE_ANON];
+ zone->recent_scanned[0] += count[LRU_ACTIVE_ANON];
+ zone->recent_scanned[1] += count[LRU_INACTIVE_FILE];
+ zone->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+ }
spin_unlock_irq(&zone->lru_lock);
nr_scanned += nr_scan;
@@ -947,7 +971,7 @@
* The attempt at page out may have made some
* of the pages active, mark them inactive again.
*/
- nr_active = clear_active_flags(&page_list);
+ nr_active = clear_active_flags(&page_list, count);
count_vm_events(PGDEACTIVATE, nr_active);
nr_freed += shrink_page_list(&page_list, sc,
@@ -977,6 +1001,10 @@
SetPageLRU(page);
list_del(&page->lru);
add_page_to_lru_list(zone, page, page_lru(page));
+ if (PageActive(page) && scan_global_lru(sc)) {
+ int file = !!page_is_file_cache(page);
+ zone->recent_rotated[file]++;
+ }
if (!pagevec_add(&pvec, page)) {
spin_unlock_irq(&zone->lru_lock);
__pagevec_release(&pvec);
@@ -1007,115 +1035,7 @@
static inline int zone_is_near_oom(struct zone *zone)
{
- return zone->pages_scanned >= (zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE))*3;
-}
-
-/*
- * Determine we should try to reclaim mapped pages.
- * This is called only when sc->mem_cgroup is NULL.
- */
-static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
- int priority)
-{
- long mapped_ratio;
- long distress;
- long swap_tendency;
- long imbalance;
- int reclaim_mapped = 0;
- int prev_priority;
-
- if (scan_global_lru(sc) && zone_is_near_oom(zone))
- return 1;
- /*
- * `distress' is a measure of how much trouble we're having
- * reclaiming pages. 0 -> no problems. 100 -> great trouble.
- */
- if (scan_global_lru(sc))
- prev_priority = zone->prev_priority;
- else
- prev_priority = mem_cgroup_get_reclaim_priority(sc->mem_cgroup);
-
- distress = 100 >> min(prev_priority, priority);
-
- /*
- * The point of this algorithm is to decide when to start
- * reclaiming mapped memory instead of just pagecache. Work out
- * how much memory
- * is mapped.
- */
- if (scan_global_lru(sc))
- mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
- global_page_state(NR_ANON_PAGES)) * 100) /
- vm_total_pages;
- else
- mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup);
-
- /*
- * Now decide how much we really want to unmap some pages. The
- * mapped ratio is downgraded - just because there's a lot of
- * mapped memory doesn't necessarily mean that page reclaim
- * isn't succeeding.
- *
- * The distress ratio is important - we don't want to start
- * going oom.
- *
- * A 100% value of vm_swappiness overrides this algorithm
- * altogether.
- */
- swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
-
- /*
- * If there's huge imbalance between active and inactive
- * (think active 100 times larger than inactive) we should
- * become more permissive, or the system will take too much
- * cpu before it start swapping during memory pressure.
- * Distress is about avoiding early-oom, this is about
- * making swappiness graceful despite setting it to low
- * values.
- *
- * Avoid div by zero with nr_inactive+1, and max resulting
- * value is vm_total_pages.
- */
- if (scan_global_lru(sc)) {
- imbalance = zone_page_state(zone, NR_ACTIVE);
- imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
- } else
- imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup);
-
- /*
- * Reduce the effect of imbalance if swappiness is low,
- * this means for a swappiness very low, the imbalance
- * must be much higher than 100 for this logic to make
- * the difference.
- *
- * Max temporary value is vm_total_pages*100.
- */
- imbalance *= (vm_swappiness + 1);
- imbalance /= 100;
-
- /*
- * If not much of the ram is mapped, makes the imbalance
- * less relevant, it's high priority we refill the inactive
- * list with mapped pages only in presence of high ratio of
- * mapped pages.
- *
- * Max temporary value is vm_total_pages*100.
- */
- imbalance *= mapped_ratio;
- imbalance /= 100;
-
- /* apply imbalance feedback to swap_tendency */
- swap_tendency += imbalance;
-
- /*
- * Now use this metric to decide whether to start moving mapped
- * memory onto the inactive list.
- */
- if (swap_tendency >= 100)
- reclaim_mapped = 1;
-
- return reclaim_mapped;
+ return zone->pages_scanned >= (zone_lru_pages(zone) * 3);
}
/*
@@ -1138,7 +1058,7 @@
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
- struct scan_control *sc, int priority)
+ struct scan_control *sc, int priority, int file)
{
unsigned long pgmoved;
int pgdeactivate = 0;
@@ -1148,43 +1068,42 @@
LIST_HEAD(l_inactive);
struct page *page;
struct pagevec pvec;
- int reclaim_mapped = 0;
-
- if (sc->may_swap)
- reclaim_mapped = calc_reclaim_mapped(sc, zone, priority);
+ enum lru_list lru;
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
ISOLATE_ACTIVE, zone,
- sc->mem_cgroup, 1);
+ sc->mem_cgroup, 1, file);
/*
* zone->pages_scanned is used for detect zone's oom
* mem_cgroup remembers nr_scan by itself.
*/
- if (scan_global_lru(sc))
+ if (scan_global_lru(sc)) {
zone->pages_scanned += pgscanned;
+ zone->recent_scanned[!!file] += pgmoved;
+ }
- __mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
+ if (file)
+ __mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
+ else
+ __mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
list_del(&page->lru);
- if (page_mapped(page)) {
- if (!reclaim_mapped ||
- (total_swap_pages == 0 && PageAnon(page)) ||
- page_referenced(page, 0, sc->mem_cgroup)) {
- list_add(&page->lru, &l_active);
- continue;
- }
- }
list_add(&page->lru, &l_inactive);
}
+ /*
+ * Now put the pages back on the appropriate [file or anon] inactive
+ * and active lists.
+ */
pagevec_init(&pvec, 1);
pgmoved = 0;
+ lru = LRU_BASE + file * LRU_FILE;
spin_lock_irq(&zone->lru_lock);
while (!list_empty(&l_inactive)) {
page = lru_to_page(&l_inactive);
@@ -1194,11 +1113,11 @@
VM_BUG_ON(!PageActive(page));
ClearPageActive(page);
- list_move(&page->lru, &zone->lru[LRU_INACTIVE].list);
+ list_move(&page->lru, &zone->lru[lru].list);
mem_cgroup_move_lists(page, false);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
spin_unlock_irq(&zone->lru_lock);
pgdeactivate += pgmoved;
pgmoved = 0;
@@ -1208,7 +1127,7 @@
spin_lock_irq(&zone->lru_lock);
}
}
- __mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
pgdeactivate += pgmoved;
if (buffer_heads_over_limit) {
spin_unlock_irq(&zone->lru_lock);
@@ -1217,6 +1136,7 @@
}
pgmoved = 0;
+ lru = LRU_ACTIVE + file * LRU_FILE;
while (!list_empty(&l_active)) {
page = lru_to_page(&l_active);
prefetchw_prev_lru_page(page, &l_active, flags);
@@ -1224,11 +1144,11 @@
SetPageLRU(page);
VM_BUG_ON(!PageActive(page));
- list_move(&page->lru, &zone->lru[LRU_ACTIVE].list);
+ list_move(&page->lru, &zone->lru[lru].list);
mem_cgroup_move_lists(page, true);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
pgmoved = 0;
spin_unlock_irq(&zone->lru_lock);
if (vm_swap_full())
@@ -1237,7 +1157,8 @@
spin_lock_irq(&zone->lru_lock);
}
}
- __mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
+ __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+ zone->recent_rotated[!!file] += pgmoved;
__count_zone_vm_events(PGREFILL, zone, pgscanned);
__count_vm_events(PGDEACTIVATE, pgdeactivate);
@@ -1248,17 +1169,104 @@
pagevec_release(&pvec);
}
-static unsigned long shrink_list(enum lru_list l, unsigned long nr_to_scan,
+static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct zone *zone, struct scan_control *sc, int priority)
{
- if (l == LRU_ACTIVE) {
- shrink_active_list(nr_to_scan, zone, sc, priority);
+ int file = is_file_lru(lru);
+
+ if (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE) {
+ shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
- return shrink_inactive_list(nr_to_scan, zone, sc);
+ return shrink_inactive_list(nr_to_scan, zone, sc, file);
}
/*
+ * Determine how aggressively the anon and file LRU lists should be
+ * scanned. The relative value of each set of LRU lists is determined
+ * by looking at the fraction of the pages scanned we did rotate back
+ * onto the active list instead of evict.
+ *
+ * percent[0] specifies how much pressure to put on ram/swap backed
+ * memory, while percent[1] determines pressure on the file LRUs.
+ */
+static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
+ unsigned long *percent)
+{
+ unsigned long anon, file, free;
+ unsigned long anon_prio, file_prio;
+ unsigned long ap, fp;
+
+ anon = zone_page_state(zone, NR_ACTIVE_ANON) +
+ zone_page_state(zone, NR_INACTIVE_ANON);
+ file = zone_page_state(zone, NR_ACTIVE_FILE) +
+ zone_page_state(zone, NR_INACTIVE_FILE);
+ free = zone_page_state(zone, NR_FREE_PAGES);
+
+ /* If we have no swap space, do not bother scanning anon pages. */
+ if (nr_swap_pages <= 0) {
+ percent[0] = 0;
+ percent[1] = 100;
+ return;
+ }
+
+ /* If we have very few page cache pages, force-scan anon pages. */
+ if (unlikely(file + free <= zone->pages_high)) {
+ percent[0] = 100;
+ percent[1] = 0;
+ return;
+ }
+
+ /*
+ * OK, so we have swap space and a fair amount of page cache
+ * pages. We use the recently rotated / recently scanned
+ * ratios to determine how valuable each cache is.
+ *
+ * Because workloads change over time (and to avoid overflow)
+ * we keep these statistics as a floating average, which ends
+ * up weighing recent references more than old ones.
+ *
+ * anon in [0], file in [1]
+ */
+ if (unlikely(zone->recent_scanned[0] > anon / 4)) {
+ spin_lock_irq(&zone->lru_lock);
+ zone->recent_scanned[0] /= 2;
+ zone->recent_rotated[0] /= 2;
+ spin_unlock_irq(&zone->lru_lock);
+ }
+
+ if (unlikely(zone->recent_scanned[1] > file / 4)) {
+ spin_lock_irq(&zone->lru_lock);
+ zone->recent_scanned[1] /= 2;
+ zone->recent_rotated[1] /= 2;
+ spin_unlock_irq(&zone->lru_lock);
+ }
+
+ /*
+ * With swappiness at 100, anonymous and file have the same priority.
+ * This scanning priority is essentially the inverse of IO cost.
+ */
+ anon_prio = sc->swappiness;
+ file_prio = 200 - sc->swappiness;
+
+ /*
+ * anon recent_rotated[0]
+ * %anon = 100 * ----------- / ----------------- * IO cost
+ * anon + file rotate_sum
+ */
+ ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
+ ap /= zone->recent_rotated[0] + 1;
+
+ fp = (file_prio + 1) * (zone->recent_scanned[1] + 1);
+ fp /= zone->recent_rotated[1] + 1;
+
+ /* Normalize to percentages */
+ percent[0] = 100 * ap / (ap + fp + 1);
+ percent[1] = 100 - percent[0];
+}
+
+
+/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
static unsigned long shrink_zone(int priority, struct zone *zone,
@@ -1267,36 +1275,43 @@
unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
unsigned long nr_reclaimed = 0;
+ unsigned long percent[2]; /* anon @ 0; file @ 1 */
enum lru_list l;
- if (scan_global_lru(sc)) {
- /*
- * Add one to nr_to_scan just to make sure that the kernel
- * will slowly sift through the active list.
- */
- for_each_lru(l) {
- zone->lru[l].nr_scan += (zone_page_state(zone,
- NR_LRU_BASE + l) >> priority) + 1;
+ get_scan_ratio(zone, sc, percent);
+
+ for_each_lru(l) {
+ if (scan_global_lru(sc)) {
+ int file = is_file_lru(l);
+ int scan;
+ /*
+ * Add one to nr_to_scan just to make sure that the
+ * kernel will slowly sift through each list.
+ */
+ scan = zone_page_state(zone, NR_LRU_BASE + l);
+ if (priority) {
+ scan >>= priority;
+ scan = (scan * percent[file]) / 100;
+ }
+ zone->lru[l].nr_scan += scan + 1;
nr[l] = zone->lru[l].nr_scan;
if (nr[l] >= sc->swap_cluster_max)
zone->lru[l].nr_scan = 0;
else
nr[l] = 0;
+ } else {
+ /*
+ * This reclaim occurs not because zone memory shortage
+ * but because memory controller hits its limit.
+ * Don't modify zone reclaim related data.
+ */
+ nr[l] = mem_cgroup_calc_reclaim(sc->mem_cgroup, zone,
+ priority, l);
}
- } else {
- /*
- * This reclaim occurs not because zone memory shortage but
- * because memory controller hits its limit.
- * Then, don't modify zone reclaim related data.
- */
- nr[LRU_ACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
- zone, priority, LRU_ACTIVE);
-
- nr[LRU_INACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
- zone, priority, LRU_INACTIVE);
}
- while (nr[LRU_ACTIVE] || nr[LRU_INACTIVE]) {
+ while (nr[LRU_ACTIVE_ANON] || nr[LRU_INACTIVE_ANON] ||
+ nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) {
for_each_lru(l) {
if (nr[l]) {
nr_to_scan = min(nr[l],
@@ -1369,7 +1384,7 @@
return nr_reclaimed;
}
-
+
/*
* This is the main entry point to direct page reclaim.
*
@@ -1412,8 +1427,7 @@
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- lru_pages += zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE);
+ lru_pages += zone_lru_pages(zone);
}
}
@@ -1615,8 +1629,7 @@
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
- lru_pages += zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE);
+ lru_pages += zone_lru_pages(zone);
}
/*
@@ -1660,8 +1673,7 @@
if (zone_is_all_unreclaimable(zone))
continue;
if (nr_slab == 0 && zone->pages_scanned >=
- (zone_page_state(zone, NR_ACTIVE)
- + zone_page_state(zone, NR_INACTIVE)) * 6)
+ (zone_lru_pages(zone) * 6))
zone_set_flag(zone,
ZONE_ALL_UNRECLAIMABLE);
/*
@@ -1715,7 +1727,7 @@
/*
* The background pageout daemon, started as a kernel thread
- * from the init process.
+ * from the init process.
*
* This basically trickles out pages so that we have _some_
* free memory available even if there is no other activity
@@ -1809,6 +1821,14 @@
wake_up_interruptible(&pgdat->kswapd_wait);
}
+unsigned long global_lru_pages(void)
+{
+ return global_page_state(NR_ACTIVE_ANON)
+ + global_page_state(NR_ACTIVE_FILE)
+ + global_page_state(NR_INACTIVE_ANON)
+ + global_page_state(NR_INACTIVE_FILE);
+}
+
#ifdef CONFIG_PM
/*
* Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages
@@ -1834,7 +1854,8 @@
for_each_lru(l) {
/* For pass = 0 we don't shrink the active list */
- if (pass == 0 && l == LRU_ACTIVE)
+ if (pass == 0 &&
+ (l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
continue;
zone->lru[l].nr_scan +=
@@ -1856,11 +1877,6 @@
return ret;
}
-static unsigned long count_lru_pages(void)
-{
- return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
-}
-
/*
* Try to free `nr_pages' of memory, system-wide, and return the number of
* freed pages.
@@ -1886,7 +1902,7 @@
current->reclaim_state = &reclaim_state;
- lru_pages = count_lru_pages();
+ lru_pages = global_lru_pages();
nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
/* If slab caches are huge, it's better to hit them first */
while (nr_slab >= lru_pages) {
@@ -1929,7 +1945,7 @@
reclaim_state.reclaimed_slab = 0;
shrink_slab(sc.nr_scanned, sc.gfp_mask,
- count_lru_pages());
+ global_lru_pages());
ret += reclaim_state.reclaimed_slab;
if (ret >= nr_pages)
goto out;
@@ -1946,7 +1962,7 @@
if (!ret) {
do {
reclaim_state.reclaimed_slab = 0;
- shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
+ shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
ret += reclaim_state.reclaimed_slab;
} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 52c0335..27400b7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -619,8 +619,10 @@
static const char * const vmstat_text[] = {
/* Zoned VM counters */
"nr_free_pages",
- "nr_inactive",
- "nr_active",
+ "nr_inactive_anon",
+ "nr_active_anon",
+ "nr_inactive_file",
+ "nr_active_file",
"nr_anon_pages",
"nr_mapped",
"nr_file_pages",
@@ -688,7 +690,7 @@
"\n min %lu"
"\n low %lu"
"\n high %lu"
- "\n scanned %lu (a: %lu i: %lu)"
+ "\n scanned %lu (aa: %lu ia: %lu af: %lu if: %lu)"
"\n spanned %lu"
"\n present %lu",
zone_page_state(zone, NR_FREE_PAGES),
@@ -696,8 +698,10 @@
zone->pages_low,
zone->pages_high,
zone->pages_scanned,
- zone->lru[LRU_ACTIVE].nr_scan,
- zone->lru[LRU_INACTIVE].nr_scan,
+ zone->lru[LRU_ACTIVE_ANON].nr_scan,
+ zone->lru[LRU_INACTIVE_ANON].nr_scan,
+ zone->lru[LRU_ACTIVE_FILE].nr_scan,
+ zone->lru[LRU_INACTIVE_FILE].nr_scan,
zone->spanned_pages,
zone->present_pages);
