linux-stable/fs/f2fs/shrinker.c
Jaegeuk Kim 71644dff48 f2fs: add block_age-based extent cache
This patch introduces a runtime hot/cold data separation method
for f2fs, in order to improve the accuracy for data temperature
classification, reduce the garbage collection overhead after
long-term data updates.

Enhanced hot/cold data separation can record data block update
frequency as "age" of the extent per inode, and take use of the age
info to indicate better temperature type for data block allocation:
 - It records total data blocks allocated since mount;
 - When file extent has been updated, it calculate the count of data
blocks allocated since last update as the age of the extent;
 - Before the data block allocated, it searches for the age info and
chooses the suitable segment for allocation.

Test and result:
 - Prepare: create about 30000 files
  * 3% for cold files (with cold file extension like .apk, from 3M to 10M)
  * 50% for warm files (with random file extension like .FcDxq, from 1K
to 4M)
  * 47% for hot files (with hot file extension like .db, from 1K to 256K)
 - create(5%)/random update(90%)/delete(5%) the files
  * total write amount is about 70G
  * fsync will be called for .db files, and buffered write will be used
for other files

The storage of test device is large enough(128G) so that it will not
switch to SSR mode during the test.

Benefit: dirty segment count increment reduce about 14%
 - before: Dirty +21110
 - after:  Dirty +18286

Signed-off-by: qixiaoyu1 <qixiaoyu1@xiaomi.com>
Signed-off-by: xiongping1 <xiongping1@xiaomi.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2022-12-12 14:53:56 -08:00

149 lines
3.5 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* f2fs shrinker support
* the basic infra was copied from fs/ubifs/shrinker.c
*
* Copyright (c) 2015 Motorola Mobility
* Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org>
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include "f2fs.h"
#include "node.h"
static LIST_HEAD(f2fs_list);
static DEFINE_SPINLOCK(f2fs_list_lock);
static unsigned int shrinker_run_no;
static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
{
return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT];
}
static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
{
long count = NM_I(sbi)->nid_cnt[FREE_NID] - MAX_FREE_NIDS;
return count > 0 ? count : 0;
}
static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi,
enum extent_type type)
{
struct extent_tree_info *eti = &sbi->extent_tree[type];
return atomic_read(&eti->total_zombie_tree) +
atomic_read(&eti->total_ext_node);
}
unsigned long f2fs_shrink_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct f2fs_sb_info *sbi;
struct list_head *p;
unsigned long count = 0;
spin_lock(&f2fs_list_lock);
p = f2fs_list.next;
while (p != &f2fs_list) {
sbi = list_entry(p, struct f2fs_sb_info, s_list);
/* stop f2fs_put_super */
if (!mutex_trylock(&sbi->umount_mutex)) {
p = p->next;
continue;
}
spin_unlock(&f2fs_list_lock);
/* count read extent cache entries */
count += __count_extent_cache(sbi, EX_READ);
/* count block age extent cache entries */
count += __count_extent_cache(sbi, EX_BLOCK_AGE);
/* count clean nat cache entries */
count += __count_nat_entries(sbi);
/* count free nids cache entries */
count += __count_free_nids(sbi);
spin_lock(&f2fs_list_lock);
p = p->next;
mutex_unlock(&sbi->umount_mutex);
}
spin_unlock(&f2fs_list_lock);
return count;
}
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
unsigned long nr = sc->nr_to_scan;
struct f2fs_sb_info *sbi;
struct list_head *p;
unsigned int run_no;
unsigned long freed = 0;
spin_lock(&f2fs_list_lock);
do {
run_no = ++shrinker_run_no;
} while (run_no == 0);
p = f2fs_list.next;
while (p != &f2fs_list) {
sbi = list_entry(p, struct f2fs_sb_info, s_list);
if (sbi->shrinker_run_no == run_no)
break;
/* stop f2fs_put_super */
if (!mutex_trylock(&sbi->umount_mutex)) {
p = p->next;
continue;
}
spin_unlock(&f2fs_list_lock);
sbi->shrinker_run_no = run_no;
/* shrink extent cache entries */
freed += f2fs_shrink_age_extent_tree(sbi, nr >> 2);
/* shrink read extent cache entries */
freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2);
/* shrink clean nat cache entries */
if (freed < nr)
freed += f2fs_try_to_free_nats(sbi, nr - freed);
/* shrink free nids cache entries */
if (freed < nr)
freed += f2fs_try_to_free_nids(sbi, nr - freed);
spin_lock(&f2fs_list_lock);
p = p->next;
list_move_tail(&sbi->s_list, &f2fs_list);
mutex_unlock(&sbi->umount_mutex);
if (freed >= nr)
break;
}
spin_unlock(&f2fs_list_lock);
return freed;
}
void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
{
spin_lock(&f2fs_list_lock);
list_add_tail(&sbi->s_list, &f2fs_list);
spin_unlock(&f2fs_list_lock);
}
void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
{
f2fs_shrink_read_extent_tree(sbi, __count_extent_cache(sbi, EX_READ));
f2fs_shrink_age_extent_tree(sbi,
__count_extent_cache(sbi, EX_BLOCK_AGE));
spin_lock(&f2fs_list_lock);
list_del_init(&sbi->s_list);
spin_unlock(&f2fs_list_lock);
}