linux/mm/swap_state.c
Shaohua Li 23955622ff swap: add block io poll in swapin path
For fast flash disk, async IO could introduce overhead because of
context switch.  block-mq now supports IO poll, which improves
performance and latency a lot.  swapin is a good place to use this
technique, because the task is waiting for the swapin page to continue
execution.

In my virtual machine, directly read 4k data from a NVMe with iopoll is
about 60% better than that without poll.  With iopoll support in swapin
patch, my microbenchmark (a task does random memory write) is about
10%~25% faster.  CPU utilization increases a lot though, 2x and even 3x
CPU utilization.  This will depend on disk speed.

While iopoll in swapin isn't intended for all usage cases, it's a win
for latency sensistive workloads with high speed swap disk.  block layer
has knob to control poll in runtime.  If poll isn't enabled in block
layer, there should be no noticeable change in swapin.

I got a chance to run the same test in a NVMe with DRAM as the media.
In simple fio IO test, blkpoll boosts 50% performance in single thread
test and ~20% in 8 threads test.  So this is the base line.  In above
swap test, blkpoll boosts ~27% performance in single thread test.
blkpoll uses 2x CPU time though.

If we enable hybid polling, the performance gain has very slight drop
but CPU time is only 50% worse than that without blkpoll.  Also we can
adjust parameter of hybid poll, with it, the CPU time penality is
reduced further.  In 8 threads test, blkpoll doesn't help though.  The
performance is similar to that without blkpoll, but cpu utilization is
similar too.  There is lock contention in swap path.  The cpu time
spending on blkpoll isn't high.  So overall, blkpoll swapin isn't worse
than that without it.

The swapin readahead might read several pages in in the same time and
form a big IO request.  Since the IO will take longer time, it doesn't
make sense to do poll, so the patch only does iopoll for single page
swapin.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/070c3c3e40b711e7b1390002c991e86a-b5408f0@7511894063d3764ff01ea8111f5a004d7dd700ed078797c204a24e620ddb965c
Signed-off-by: Shaohua Li <shli@fb.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-10 16:32:30 -07:00

564 lines
15 KiB
C

/*
* linux/mm/swap_state.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
*
* Rewritten to use page cache, (C) 1998 Stephen Tweedie
*/
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/migrate.h>
#include <linux/vmalloc.h>
#include <linux/swap_slots.h>
#include <linux/huge_mm.h>
#include <asm/pgtable.h>
/*
* swapper_space is a fiction, retained to simplify the path through
* vmscan's shrink_page_list.
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
.set_page_dirty = swap_set_page_dirty,
#ifdef CONFIG_MIGRATION
.migratepage = migrate_page,
#endif
};
struct address_space *swapper_spaces[MAX_SWAPFILES];
static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
#define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0)
#define ADD_CACHE_INFO(x, nr) do { swap_cache_info.x += (nr); } while (0)
static struct {
unsigned long add_total;
unsigned long del_total;
unsigned long find_success;
unsigned long find_total;
} swap_cache_info;
unsigned long total_swapcache_pages(void)
{
unsigned int i, j, nr;
unsigned long ret = 0;
struct address_space *spaces;
rcu_read_lock();
for (i = 0; i < MAX_SWAPFILES; i++) {
/*
* The corresponding entries in nr_swapper_spaces and
* swapper_spaces will be reused only after at least
* one grace period. So it is impossible for them
* belongs to different usage.
*/
nr = nr_swapper_spaces[i];
spaces = rcu_dereference(swapper_spaces[i]);
if (!nr || !spaces)
continue;
for (j = 0; j < nr; j++)
ret += spaces[j].nrpages;
}
rcu_read_unlock();
return ret;
}
static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
void show_swap_cache_info(void)
{
printk("%lu pages in swap cache\n", total_swapcache_pages());
printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
swap_cache_info.add_total, swap_cache_info.del_total,
swap_cache_info.find_success, swap_cache_info.find_total);
printk("Free swap = %ldkB\n",
get_nr_swap_pages() << (PAGE_SHIFT - 10));
printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
}
/*
* __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
* but sets SwapCache flag and private instead of mapping and index.
*/
int __add_to_swap_cache(struct page *page, swp_entry_t entry)
{
int error, i, nr = hpage_nr_pages(page);
struct address_space *address_space;
pgoff_t idx = swp_offset(entry);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapCache(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
page_ref_add(page, nr);
SetPageSwapCache(page);
address_space = swap_address_space(entry);
spin_lock_irq(&address_space->tree_lock);
for (i = 0; i < nr; i++) {
set_page_private(page + i, entry.val + i);
error = radix_tree_insert(&address_space->page_tree,
idx + i, page + i);
if (unlikely(error))
break;
}
if (likely(!error)) {
address_space->nrpages += nr;
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
ADD_CACHE_INFO(add_total, nr);
} else {
/*
* Only the context which have set SWAP_HAS_CACHE flag
* would call add_to_swap_cache().
* So add_to_swap_cache() doesn't returns -EEXIST.
*/
VM_BUG_ON(error == -EEXIST);
set_page_private(page + i, 0UL);
while (i--) {
radix_tree_delete(&address_space->page_tree, idx + i);
set_page_private(page + i, 0UL);
}
ClearPageSwapCache(page);
page_ref_sub(page, nr);
}
spin_unlock_irq(&address_space->tree_lock);
return error;
}
int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
{
int error;
error = radix_tree_maybe_preload_order(gfp_mask, compound_order(page));
if (!error) {
error = __add_to_swap_cache(page, entry);
radix_tree_preload_end();
}
return error;
}
/*
* This must be called only on pages that have
* been verified to be in the swap cache.
*/
void __delete_from_swap_cache(struct page *page)
{
struct address_space *address_space;
int i, nr = hpage_nr_pages(page);
swp_entry_t entry;
pgoff_t idx;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
VM_BUG_ON_PAGE(PageWriteback(page), page);
entry.val = page_private(page);
address_space = swap_address_space(entry);
idx = swp_offset(entry);
for (i = 0; i < nr; i++) {
radix_tree_delete(&address_space->page_tree, idx + i);
set_page_private(page + i, 0);
}
ClearPageSwapCache(page);
address_space->nrpages -= nr;
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
ADD_CACHE_INFO(del_total, nr);
}
/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
*
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
*/
int add_to_swap(struct page *page)
{
swp_entry_t entry;
int err;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageUptodate(page), page);
entry = get_swap_page(page);
if (!entry.val)
return 0;
if (mem_cgroup_try_charge_swap(page, entry))
goto fail;
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC
* stops emergency reserves from being allocated.
*
* TODO: this could cause a theoretical memory reclaim
* deadlock in the swap out path.
*/
/*
* Add it to the swap cache.
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
/* -ENOMEM radix-tree allocation failure */
if (err)
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
goto fail;
return 1;
fail:
put_swap_page(page, entry);
return 0;
}
/*
* This must be called only on pages that have
* been verified to be in the swap cache and locked.
* It will never put the page into the free list,
* the caller has a reference on the page.
*/
void delete_from_swap_cache(struct page *page)
{
swp_entry_t entry;
struct address_space *address_space;
entry.val = page_private(page);
address_space = swap_address_space(entry);
spin_lock_irq(&address_space->tree_lock);
__delete_from_swap_cache(page);
spin_unlock_irq(&address_space->tree_lock);
put_swap_page(page, entry);
page_ref_sub(page, hpage_nr_pages(page));
}
/*
* If we are the only user, then try to free up the swap cache.
*
* Its ok to check for PageSwapCache without the page lock
* here because we are going to recheck again inside
* try_to_free_swap() _with_ the lock.
* - Marcelo
*/
static inline void free_swap_cache(struct page *page)
{
if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) {
try_to_free_swap(page);
unlock_page(page);
}
}
/*
* Perform a free_page(), also freeing any swap cache associated with
* this page if it is the last user of the page.
*/
void free_page_and_swap_cache(struct page *page)
{
free_swap_cache(page);
if (!is_huge_zero_page(page))
put_page(page);
}
/*
* Passed an array of pages, drop them all from swapcache and then release
* them. They are removed from the LRU and freed if this is their last use.
*/
void free_pages_and_swap_cache(struct page **pages, int nr)
{
struct page **pagep = pages;
int i;
lru_add_drain();
for (i = 0; i < nr; i++)
free_swap_cache(pagep[i]);
release_pages(pagep, nr, false);
}
/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *page;
page = find_get_page(swap_address_space(entry), swp_offset(entry));
if (page && likely(!PageTransCompound(page))) {
INC_CACHE_INFO(find_success);
if (TestClearPageReadahead(page))
atomic_inc(&swapin_readahead_hits);
}
INC_CACHE_INFO(find_total);
return page;
}
struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated)
{
struct page *found_page, *new_page = NULL;
struct address_space *swapper_space = swap_address_space(entry);
int err;
*new_page_allocated = false;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(swapper_space, swp_offset(entry));
if (found_page)
break;
/*
* Just skip read ahead for unused swap slot.
* During swap_off when swap_slot_cache is disabled,
* we have to handle the race between putting
* swap entry in swap cache and marking swap slot
* as SWAP_HAS_CACHE. That's done in later part of code or
* else swap_off will be aborted if we return NULL.
*/
if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page_vma(gfp_mask, vma, addr);
if (!new_page)
break; /* Out of memory */
}
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) {
radix_tree_preload_end();
/*
* We might race against get_swap_page() and stumble
* across a SWAP_HAS_CACHE swap_map entry whose page
* has not been brought into the swapcache yet.
*/
cond_resched();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__SetPageLocked(new_page);
__SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
/*
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
*new_page_allocated = true;
return new_page;
}
radix_tree_preload_end();
__ClearPageLocked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
put_swap_page(new_page, entry);
} while (err != -ENOMEM);
if (new_page)
put_page(new_page);
return found_page;
}
/*
* Locate a page of swap in physical memory, reserving swap cache space
* and reading the disk if it is not already cached.
* A failure return means that either the page allocation failed or that
* the swap entry is no longer in use.
*/
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr, bool do_poll)
{
bool page_was_allocated;
struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
vma, addr, &page_was_allocated);
if (page_was_allocated)
swap_readpage(retpage, do_poll);
return retpage;
}
static unsigned long swapin_nr_pages(unsigned long offset)
{
static unsigned long prev_offset;
unsigned int pages, max_pages, last_ra;
static atomic_t last_readahead_pages;
max_pages = 1 << READ_ONCE(page_cluster);
if (max_pages <= 1)
return 1;
/*
* This heuristic has been found to work well on both sequential and
* random loads, swapping to hard disk or to SSD: please don't ask
* what the "+ 2" means, it just happens to work well, that's all.
*/
pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
if (pages == 2) {
/*
* We can have no readahead hits to judge by: but must not get
* stuck here forever, so check for an adjacent offset instead
* (and don't even bother to check whether swap type is same).
*/
if (offset != prev_offset + 1 && offset != prev_offset - 1)
pages = 1;
prev_offset = offset;
} else {
unsigned int roundup = 4;
while (roundup < pages)
roundup <<= 1;
pages = roundup;
}
if (pages > max_pages)
pages = max_pages;
/* Don't shrink readahead too fast */
last_ra = atomic_read(&last_readahead_pages) / 2;
if (pages < last_ra)
pages = last_ra;
atomic_set(&last_readahead_pages, pages);
return pages;
}
/**
* swapin_readahead - swap in pages in hope we need them soon
* @entry: swap entry of this memory
* @gfp_mask: memory allocation flags
* @vma: user vma this address belongs to
* @addr: target address for mempolicy
*
* Returns the struct page for entry and addr, after queueing swapin.
*
* Primitive swap readahead code. We simply read an aligned block of
* (1 << page_cluster) entries in the swap area. This method is chosen
* because it doesn't cost us any seek time. We also make sure to queue
* the 'original' request together with the readahead ones...
*
* This has been extended to use the NUMA policies from the mm triggering
* the readahead.
*
* Caller must hold down_read on the vma->vm_mm if vma is not NULL.
*/
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
unsigned long entry_offset = swp_offset(entry);
unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
unsigned long mask;
struct blk_plug plug;
bool do_poll = true;
mask = swapin_nr_pages(offset) - 1;
if (!mask)
goto skip;
do_poll = false;
/* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask;
end_offset = offset | mask;
if (!start_offset) /* First page is swap header. */
start_offset++;
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
gfp_mask, vma, addr, false);
if (!page)
continue;
if (offset != entry_offset && likely(!PageTransCompound(page)))
SetPageReadahead(page);
put_page(page);
}
blk_finish_plug(&plug);
lru_add_drain(); /* Push any new pages onto the LRU now */
skip:
return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
}
int init_swap_address_space(unsigned int type, unsigned long nr_pages)
{
struct address_space *spaces, *space;
unsigned int i, nr;
nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
spaces = kvzalloc(sizeof(struct address_space) * nr, GFP_KERNEL);
if (!spaces)
return -ENOMEM;
for (i = 0; i < nr; i++) {
space = spaces + i;
INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN);
atomic_set(&space->i_mmap_writable, 0);
space->a_ops = &swap_aops;
/* swap cache doesn't use writeback related tags */
mapping_set_no_writeback_tags(space);
spin_lock_init(&space->tree_lock);
}
nr_swapper_spaces[type] = nr;
rcu_assign_pointer(swapper_spaces[type], spaces);
return 0;
}
void exit_swap_address_space(unsigned int type)
{
struct address_space *spaces;
spaces = swapper_spaces[type];
nr_swapper_spaces[type] = 0;
rcu_assign_pointer(swapper_spaces[type], NULL);
synchronize_rcu();
kvfree(spaces);
}