linux_dsm_epyc7002/include/linux/swap.h
Mel Gorman 8afdcece49 mm: vmscan: kswapd should not free an excessive number of pages when balancing small zones
When reclaiming for order-0 pages, kswapd requires that all zones be
balanced.  Each cycle through balance_pgdat() does background ageing on
all zones if necessary and applies equal pressure on the inactive zone
unless a lot of pages are free already.

A "lot of free pages" is defined as a "balance gap" above the high
watermark which is currently 7*high_watermark.  Historically this was
reasonable as min_free_kbytes was small.  However, on systems using huge
pages, it is recommended that min_free_kbytes is higher and it is tuned
with hugeadm --set-recommended-min_free_kbytes.  With the introduction of
transparent huge page support, this recommended value is also applied.  On
X86-64 with 4G of memory, min_free_kbytes becomes 67584 so one would
expect around 68M of memory to be free.  The Normal zone is approximately
35000 pages so under even normal memory pressure such as copying a large
file, it gets exhausted quickly.  As it is getting exhausted, kswapd
applies pressure equally to all zones, including the DMA32 zone.  DMA32 is
approximately 700,000 pages with a high watermark of around 23,000 pages.
In this situation, kswapd will reclaim around (23000*8 where 8 is the high
watermark + balance gap of 7 * high watermark) pages or 718M of pages
before the zone is ignored.  What the user sees is that free memory far
higher than it should be.

To avoid an excessive number of pages being reclaimed from the larger
zones, explicitely defines the "balance gap" to be either 1% of the zone
or the low watermark for the zone, whichever is smaller.  While kswapd
will check all zones to apply pressure, it'll ignore zones that meets the
(high_wmark + balance_gap) watermark.

To test this, 80G were copied from a partition and the amount of memory
being used was recorded.  A comparison of a patch and unpatched kernel can
be seen at
http://www.csn.ul.ie/~mel/postings/minfree-20110222/memory-usage-hydra.ps
and shows that kswapd is not reclaiming as much memory with the patch
applied.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: "Chen, Tim C" <tim.c.chen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-22 17:44:04 -07:00

524 lines
15 KiB
C

#ifndef _LINUX_SWAP_H
#define _LINUX_SWAP_H
#include <linux/spinlock.h>
#include <linux/linkage.h>
#include <linux/mmzone.h>
#include <linux/list.h>
#include <linux/memcontrol.h>
#include <linux/sched.h>
#include <linux/node.h>
#include <asm/atomic.h>
#include <asm/page.h>
struct notifier_block;
struct bio;
#define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */
#define SWAP_FLAG_PRIO_MASK 0x7fff
#define SWAP_FLAG_PRIO_SHIFT 0
#define SWAP_FLAG_DISCARD 0x10000 /* discard swap cluster after use */
static inline int current_is_kswapd(void)
{
return current->flags & PF_KSWAPD;
}
/*
* MAX_SWAPFILES defines the maximum number of swaptypes: things which can
* be swapped to. The swap type and the offset into that swap type are
* encoded into pte's and into pgoff_t's in the swapcache. Using five bits
* for the type means that the maximum number of swapcache pages is 27 bits
* on 32-bit-pgoff_t architectures. And that assumes that the architecture packs
* the type/offset into the pte as 5/27 as well.
*/
#define MAX_SWAPFILES_SHIFT 5
/*
* Use some of the swap files numbers for other purposes. This
* is a convenient way to hook into the VM to trigger special
* actions on faults.
*/
/*
* NUMA node memory migration support
*/
#ifdef CONFIG_MIGRATION
#define SWP_MIGRATION_NUM 2
#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
#else
#define SWP_MIGRATION_NUM 0
#endif
/*
* Handling of hardware poisoned pages with memory corruption.
*/
#ifdef CONFIG_MEMORY_FAILURE
#define SWP_HWPOISON_NUM 1
#define SWP_HWPOISON MAX_SWAPFILES
#else
#define SWP_HWPOISON_NUM 0
#endif
#define MAX_SWAPFILES \
((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
/*
* Magic header for a swap area. The first part of the union is
* what the swap magic looks like for the old (limited to 128MB)
* swap area format, the second part of the union adds - in the
* old reserved area - some extra information. Note that the first
* kilobyte is reserved for boot loader or disk label stuff...
*
* Having the magic at the end of the PAGE_SIZE makes detecting swap
* areas somewhat tricky on machines that support multiple page sizes.
* For 2.5 we'll probably want to move the magic to just beyond the
* bootbits...
*/
union swap_header {
struct {
char reserved[PAGE_SIZE - 10];
char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
} magic;
struct {
char bootbits[1024]; /* Space for disklabel etc. */
__u32 version;
__u32 last_page;
__u32 nr_badpages;
unsigned char sws_uuid[16];
unsigned char sws_volume[16];
__u32 padding[117];
__u32 badpages[1];
} info;
};
/* A swap entry has to fit into a "unsigned long", as
* the entry is hidden in the "index" field of the
* swapper address space.
*/
typedef struct {
unsigned long val;
} swp_entry_t;
/*
* current->reclaim_state points to one of these when a task is running
* memory reclaim
*/
struct reclaim_state {
unsigned long reclaimed_slab;
};
#ifdef __KERNEL__
struct address_space;
struct sysinfo;
struct writeback_control;
struct zone;
/*
* A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of
* disk blocks. A list of swap extents maps the entire swapfile. (Where the
* term `swapfile' refers to either a blockdevice or an IS_REG file. Apart
* from setup, they're handled identically.
*
* We always assume that blocks are of size PAGE_SIZE.
*/
struct swap_extent {
struct list_head list;
pgoff_t start_page;
pgoff_t nr_pages;
sector_t start_block;
};
/*
* Max bad pages in the new format..
*/
#define __swapoffset(x) ((unsigned long)&((union swap_header *)0)->x)
#define MAX_SWAP_BADPAGES \
((__swapoffset(magic.magic) - __swapoffset(info.badpages)) / sizeof(int))
enum {
SWP_USED = (1 << 0), /* is slot in swap_info[] used? */
SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */
SWP_DISCARDABLE = (1 << 2), /* swapon+blkdev support discard */
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
SWP_BLKDEV = (1 << 6), /* its a block device */
/* add others here before... */
SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */
};
#define SWAP_CLUSTER_MAX 32
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
/*
* Ratio between the present memory in the zone and the "gap" that
* we're allowing kswapd to shrink in addition to the per-zone high
* wmark, even for zones that already have the high wmark satisfied,
* in order to provide better per-zone lru behavior. We are ok to
* spend not more than 1% of the memory for this zone balancing "gap".
*/
#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100
#define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */
#define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
#define SWAP_CONT_MAX 0x7f /* Max count, in each swap_map continuation */
#define COUNT_CONTINUED 0x80 /* See swap_map continuation for full count */
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs, in first swap_map */
/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
unsigned long flags; /* SWP_USED etc: see above */
signed short prio; /* swap priority of this type */
signed char type; /* strange name for an index */
signed char next; /* next type on the swap list */
unsigned int max; /* extent of the swap_map */
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
unsigned int lowest_bit; /* index of first free in swap_map */
unsigned int highest_bit; /* index of last free in swap_map */
unsigned int pages; /* total of usable pages of swap */
unsigned int inuse_pages; /* number of those currently in use */
unsigned int cluster_next; /* likely index for next allocation */
unsigned int cluster_nr; /* countdown to next cluster search */
unsigned int lowest_alloc; /* while preparing discard cluster */
unsigned int highest_alloc; /* while preparing discard cluster */
struct swap_extent *curr_swap_extent;
struct swap_extent first_swap_extent;
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
};
struct swap_list_t {
int head; /* head of priority-ordered swapfile list */
int next; /* swapfile to be used next */
};
/* Swap 50% full? Release swapcache more aggressively.. */
#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages)
/* linux/mm/page_alloc.c */
extern unsigned long totalram_pages;
extern unsigned long totalreserve_pages;
extern unsigned int nr_free_buffer_pages(void);
extern unsigned int nr_free_pagecache_pages(void);
/* Definition of global_page_state not available yet */
#define nr_free_pages() global_page_state(NR_FREE_PAGES)
/* linux/mm/swap.c */
extern void __lru_cache_add(struct page *, enum lru_list lru);
extern void lru_cache_add_lru(struct page *, enum lru_list lru);
extern void lru_add_page_tail(struct zone* zone,
struct page *page, struct page *page_tail);
extern void activate_page(struct page *);
extern void mark_page_accessed(struct page *);
extern void lru_add_drain(void);
extern int lru_add_drain_all(void);
extern void rotate_reclaimable_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);
/**
* lru_cache_add: add a page to the page lists
* @page: the page to add
*/
static inline void lru_cache_add_anon(struct page *page)
{
__lru_cache_add(page, LRU_INACTIVE_ANON);
}
static inline void lru_cache_add_file(struct page *page)
{
__lru_cache_add(page, LRU_INACTIVE_FILE);
}
/* LRU Isolation modes. */
#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */
#define ISOLATE_ACTIVE 1 /* Isolate active pages. */
#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */
/* linux/mm/vmscan.c */
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
unsigned int swappiness);
extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
unsigned int swappiness,
struct zone *zone);
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);
extern long vm_total_pages;
#ifdef CONFIG_NUMA
extern int zone_reclaim_mode;
extern int sysctl_min_unmapped_ratio;
extern int sysctl_min_slab_ratio;
extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
#else
#define zone_reclaim_mode 0
static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
{
return 0;
}
#endif
extern int page_evictable(struct page *page, struct vm_area_struct *vma);
extern void scan_mapping_unevictable_pages(struct address_space *);
extern unsigned long scan_unevictable_pages;
extern int scan_unevictable_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#ifdef CONFIG_NUMA
extern int scan_unevictable_register_node(struct node *node);
extern void scan_unevictable_unregister_node(struct node *node);
#else
static inline int scan_unevictable_register_node(struct node *node)
{
return 0;
}
static inline void scan_unevictable_unregister_node(struct node *node)
{
}
#endif
extern int kswapd_run(int nid);
extern void kswapd_stop(int nid);
#ifdef CONFIG_MMU
/* linux/mm/shmem.c */
extern int shmem_unuse(swp_entry_t entry, struct page *page);
#endif /* CONFIG_MMU */
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
struct page **pagep, swp_entry_t *ent);
#endif
extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
#ifdef CONFIG_SWAP
/* linux/mm/page_io.c */
extern int swap_readpage(struct page *);
extern int swap_writepage(struct page *page, struct writeback_control *wbc);
extern void end_swap_bio_read(struct bio *bio, int err);
/* linux/mm/swap_state.c */
extern struct address_space swapper_space;
#define total_swapcache_pages swapper_space.nrpages
extern void show_swap_cache_info(void);
extern int add_to_swap(struct page *);
extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
extern void __delete_from_swap_cache(struct page *);
extern void delete_from_swap_cache(struct page *);
extern void free_page_and_swap_cache(struct page *);
extern void free_pages_and_swap_cache(struct page **, int);
extern struct page *lookup_swap_cache(swp_entry_t);
extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr);
extern struct page *swapin_readahead(swp_entry_t, gfp_t,
struct vm_area_struct *vma, unsigned long addr);
/* linux/mm/swapfile.c */
extern long nr_swap_pages;
extern long total_swap_pages;
extern void si_swapinfo(struct sysinfo *);
extern swp_entry_t get_swap_page(void);
extern swp_entry_t get_swap_page_of_type(int);
extern int valid_swaphandles(swp_entry_t, unsigned long *);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
extern void swap_shmem_alloc(swp_entry_t);
extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t);
extern void swapcache_free(swp_entry_t, struct page *page);
extern int free_swap_and_cache(swp_entry_t);
extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int);
extern sector_t map_swap_page(struct page *, struct block_device **);
extern sector_t swapdev_block(int, pgoff_t);
extern int reuse_swap_page(struct page *);
extern int try_to_free_swap(struct page *);
struct backing_dev_info;
/* linux/mm/thrash.c */
extern struct mm_struct *swap_token_mm;
extern void grab_swap_token(struct mm_struct *);
extern void __put_swap_token(struct mm_struct *);
static inline int has_swap_token(struct mm_struct *mm)
{
return (mm == swap_token_mm);
}
static inline void put_swap_token(struct mm_struct *mm)
{
if (has_swap_token(mm))
__put_swap_token(mm);
}
static inline void disable_swap_token(void)
{
put_swap_token(swap_token_mm);
}
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
extern void
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
extern int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep);
#else
static inline void
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
{
}
#endif
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
#else
static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
{
}
#endif
#else /* CONFIG_SWAP */
#define nr_swap_pages 0L
#define total_swap_pages 0L
#define total_swapcache_pages 0UL
#define si_swapinfo(val) \
do { (val)->freeswap = (val)->totalswap = 0; } while (0)
/* only sparc can not include linux/pagemap.h in this file
* so leave page_cache_release and release_pages undeclared... */
#define free_page_and_swap_cache(page) \
page_cache_release(page)
#define free_pages_and_swap_cache(pages, nr) \
release_pages((pages), (nr), 0);
static inline void show_swap_cache_info(void)
{
}
#define free_swap_and_cache(swp) is_migration_entry(swp)
#define swapcache_prepare(swp) is_migration_entry(swp)
static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
{
return 0;
}
static inline void swap_shmem_alloc(swp_entry_t swp)
{
}
static inline int swap_duplicate(swp_entry_t swp)
{
return 0;
}
static inline void swap_free(swp_entry_t swp)
{
}
static inline void swapcache_free(swp_entry_t swp, struct page *page)
{
}
static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
return NULL;
}
static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
{
return 0;
}
static inline struct page *lookup_swap_cache(swp_entry_t swp)
{
return NULL;
}
static inline int add_to_swap(struct page *page)
{
return 0;
}
static inline int add_to_swap_cache(struct page *page, swp_entry_t entry,
gfp_t gfp_mask)
{
return -1;
}
static inline void __delete_from_swap_cache(struct page *page)
{
}
static inline void delete_from_swap_cache(struct page *page)
{
}
#define reuse_swap_page(page) (page_mapcount(page) == 1)
static inline int try_to_free_swap(struct page *page)
{
return 0;
}
static inline swp_entry_t get_swap_page(void)
{
swp_entry_t entry;
entry.val = 0;
return entry;
}
/* linux/mm/thrash.c */
static inline void put_swap_token(struct mm_struct *mm)
{
}
static inline void grab_swap_token(struct mm_struct *mm)
{
}
static inline int has_swap_token(struct mm_struct *mm)
{
return 0;
}
static inline void disable_swap_token(void)
{
}
static inline void
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
{
}
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
static inline int
mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
{
return 0;
}
#endif
#endif /* CONFIG_SWAP */
#endif /* __KERNEL__*/
#endif /* _LINUX_SWAP_H */