linux/fs/f2fs/shrinker.c

150 lines
3.5 KiB
C
Raw Normal View History

// 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);
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>
2022-12-02 01:37:15 +00:00
/* 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;
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>
2022-12-02 01:37:15 +00:00
/* shrink extent cache entries */
freed += f2fs_shrink_age_extent_tree(sbi, nr >> 2);
/* shrink read extent cache entries */
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>
2022-12-02 01:37:15 +00:00
freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2);
/* shrink clean nat cache entries */
if (freed < nr)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
freed += f2fs_try_to_free_nats(sbi, nr - freed);
/* shrink free nids cache entries */
if (freed < nr)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
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: 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>
2022-12-02 01:37:15 +00:00
f2fs_shrink_age_extent_tree(sbi,
__count_extent_cache(sbi, EX_BLOCK_AGE));
spin_lock(&f2fs_list_lock);
f2fs: fix sbi->extent_list corruption issue When there is a failure in f2fs_fill_super() after/during the recovery of fsync'd nodes, it frees the current sbi and retries again. This time the mount is successful, but the files that got recovered before retry, still holds the extent tree, whose extent nodes list is corrupted since sbi and sbi->extent_list is freed up. The list_del corruption issue is observed when the file system is getting unmounted and when those recoverd files extent node is being freed up in the below context. list_del corruption. prev->next should be fffffff1e1ef5480, but was (null) <...> kernel BUG at kernel/msm-4.14/lib/list_debug.c:53! lr : __list_del_entry_valid+0x94/0xb4 pc : __list_del_entry_valid+0x94/0xb4 <...> Call trace: __list_del_entry_valid+0x94/0xb4 __release_extent_node+0xb0/0x114 __free_extent_tree+0x58/0x7c f2fs_shrink_extent_tree+0xdc/0x3b0 f2fs_leave_shrinker+0x28/0x7c f2fs_put_super+0xfc/0x1e0 generic_shutdown_super+0x70/0xf4 kill_block_super+0x2c/0x5c kill_f2fs_super+0x44/0x50 deactivate_locked_super+0x60/0x8c deactivate_super+0x68/0x74 cleanup_mnt+0x40/0x78 __cleanup_mnt+0x1c/0x28 task_work_run+0x48/0xd0 do_notify_resume+0x678/0xe98 work_pending+0x8/0x14 Fix this by not creating extents for those recovered files if shrinker is not registered yet. Once mount is successful and shrinker is registered, those files can have extents again. Signed-off-by: Sahitya Tummala <stummala@codeaurora.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-12-18 11:09:24 +00:00
list_del_init(&sbi->s_list);
spin_unlock(&f2fs_list_lock);
}