Does DISCARD forcibly in a period of given min_discard_issue_time when the number
of discards is not 0 and set discard granularity to 1.
Default: 80
+
+What: /sys/fs/f2fs/<disk>/hot_data_age_threshold
+Date: November 2022
+Contact: "Ping Xiong" <xiongping1@xiaomi.com>
+Description: When DATA SEPARATION is on, it controls the age threshold to indicate
+ the data blocks as hot. By default it was initialized as 262144 blocks
+ (equals to 1GB).
+
+What: /sys/fs/f2fs/<disk>/warm_data_age_threshold
+Date: November 2022
+Contact: "Ping Xiong" <xiongping1@xiaomi.com>
+Description: When DATA SEPARATION is on, it controls the age threshold to indicate
+ the data blocks as warm. By default it was initialized as 2621440 blocks
+ (equals to 10GB).
Because of the nature of low memory devices, in this mode, f2fs
will try to save memory sometimes by sacrificing performance.
"normal" mode is the default mode and same as before.
+age_extent_cache Enable an age extent cache based on rb-tree. It records
+ data block update frequency of the extent per inode, in
+ order to provide better temperature hints for data block
+ allocation.
======================== ============================================================
Debugfs Entries
si->hit_largest = atomic64_read(&sbi->read_hit_largest);
si->hit_total[EX_READ] += si->hit_largest;
+ /* block age extent_cache only */
+ si->allocated_data_blocks = atomic64_read(&sbi->allocated_data_blocks);
+
/* validation check of the segment numbers */
si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n",
si->ext_tree[EX_READ], si->zombie_tree[EX_READ],
si->ext_node[EX_READ]);
+ seq_puts(s, "\nExtent Cache (Block Age):\n");
+ seq_printf(s, " - Allocated Data Blocks: %llu\n",
+ si->allocated_data_blocks);
+ seq_printf(s, " - Hit Count: L1:%llu L2:%llu\n",
+ si->hit_cached[EX_BLOCK_AGE],
+ si->hit_rbtree[EX_BLOCK_AGE]);
+ seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n",
+ !si->total_ext[EX_BLOCK_AGE] ? 0 :
+ div64_u64(si->hit_total[EX_BLOCK_AGE] * 100,
+ si->total_ext[EX_BLOCK_AGE]),
+ si->hit_total[EX_BLOCK_AGE],
+ si->total_ext[EX_BLOCK_AGE]);
+ seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n",
+ si->ext_tree[EX_BLOCK_AGE],
+ si->zombie_tree[EX_BLOCK_AGE],
+ si->ext_node[EX_BLOCK_AGE]);
seq_puts(s, "\nBalancing F2FS Async:\n");
seq_printf(s, " - DIO (R: %4d, W: %4d)\n",
si->nr_dio_read, si->nr_dio_write);
si->cache_mem >> 10);
seq_printf(s, " - read extent cache: %llu KB\n",
si->ext_mem[EX_READ] >> 10);
+ seq_printf(s, " - block age extent cache: %llu KB\n",
+ si->ext_mem[EX_BLOCK_AGE] >> 10);
seq_printf(s, " - paged : %llu KB\n",
si->page_mem >> 10);
}
* Copyright (c) 2015 Samsung Electronics
* Authors: Jaegeuk Kim <jaegeuk@kernel.org>
* Chao Yu <chao2.yu@samsung.com>
+ *
+ * block_age-based extent cache added by:
+ * Copyright (c) 2022 xiaomi Co., Ltd.
+ * http://www.xiaomi.com/
*/
#include <linux/fs.h>
static void __set_extent_info(struct extent_info *ei,
unsigned int fofs, unsigned int len,
block_t blk, bool keep_clen,
+ unsigned long age, unsigned long last_blocks,
enum extent_type type)
{
ei->fofs = fofs;
#ifdef CONFIG_F2FS_FS_COMPRESSION
ei->c_len = 0;
#endif
+ } else if (type == EX_BLOCK_AGE) {
+ ei->age = age;
+ ei->last_blocks = last_blocks;
}
}
return S_ISREG(inode->i_mode);
}
+static bool __may_age_extent_tree(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (!test_opt(sbi, AGE_EXTENT_CACHE))
+ return false;
+ /* don't cache block age info for cold file */
+ if (is_inode_flag_set(inode, FI_COMPRESSED_FILE))
+ return false;
+ if (file_is_cold(inode))
+ return false;
+
+ return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
+}
+
static bool __init_may_extent_tree(struct inode *inode, enum extent_type type)
{
if (type == EX_READ)
return __may_read_extent_tree(inode);
+ else if (type == EX_BLOCK_AGE)
+ return __may_age_extent_tree(inode);
return false;
}
#endif
return (back->fofs + back->len == front->fofs &&
back->blk + back->len == front->blk);
+ } else if (type == EX_BLOCK_AGE) {
+ return (back->fofs + back->len == front->fofs &&
+ abs(back->age - front->age) <= SAME_AGE_REGION &&
+ abs(back->last_blocks - front->last_blocks) <=
+ SAME_AGE_REGION);
}
return false;
}
set_inode_flag(inode, FI_NO_EXTENT);
}
+void f2fs_init_age_extent_tree(struct inode *inode)
+{
+ if (!__init_may_extent_tree(inode, EX_BLOCK_AGE))
+ return;
+ __grab_extent_tree(inode, EX_BLOCK_AGE);
+}
+
void f2fs_init_extent_tree(struct inode *inode)
{
/* initialize read cache */
if (__init_may_extent_tree(inode, EX_READ))
__grab_extent_tree(inode, EX_READ);
+
+ /* initialize block age cache */
+ if (__init_may_extent_tree(inode, EX_BLOCK_AGE))
+ __grab_extent_tree(inode, EX_BLOCK_AGE);
}
static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
if (type == EX_READ)
trace_f2fs_lookup_read_extent_tree_end(inode, pgofs, ei);
+ else if (type == EX_BLOCK_AGE)
+ trace_f2fs_lookup_age_extent_tree_end(inode, pgofs, ei);
return ret;
}
if (type == EX_READ)
trace_f2fs_update_read_extent_tree_range(inode, fofs, len,
tei->blk, 0);
+ else if (type == EX_BLOCK_AGE)
+ trace_f2fs_update_age_extent_tree_range(inode, fofs, len,
+ tei->age, tei->last_blocks);
+
write_lock(&et->lock);
if (type == EX_READ) {
__set_extent_info(&ei,
end, org_end - end,
end - dei.fofs + dei.blk, false,
+ dei.age, dei.last_blocks,
type);
en1 = __insert_extent_tree(sbi, et, &ei,
NULL, NULL, true);
__set_extent_info(&en->ei,
end, en->ei.len - (end - dei.fofs),
en->ei.blk + (end - dei.fofs), true,
+ dei.age, dei.last_blocks,
type);
next_en = en;
}
en = next_en;
}
+ if (type == EX_BLOCK_AGE)
+ goto update_age_extent_cache;
+
/* 3. update extent in read extent cache */
BUG_ON(type != EX_READ);
if (tei->blk) {
- __set_extent_info(&ei, fofs, len, tei->blk, false, EX_READ);
+ __set_extent_info(&ei, fofs, len, tei->blk, false,
+ 0, 0, EX_READ);
if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
__insert_extent_tree(sbi, et, &ei,
insert_p, insert_parent, leftmost);
et->largest_updated = false;
updated = true;
}
+ goto out_read_extent_cache;
+update_age_extent_cache:
+ if (!tei->last_blocks)
+ goto out_read_extent_cache;
+ __set_extent_info(&ei, fofs, len, 0, false,
+ tei->age, tei->last_blocks, EX_BLOCK_AGE);
+ if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+ __insert_extent_tree(sbi, et, &ei,
+ insert_p, insert_parent, leftmost);
+out_read_extent_cache:
write_unlock(&et->lock);
if (updated)
if (en)
goto unlock_out;
- __set_extent_info(&ei, fofs, llen, blkaddr, true, EX_READ);
+ __set_extent_info(&ei, fofs, llen, blkaddr, true, 0, 0, EX_READ);
ei.c_len = c_len;
if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
}
#endif
+static unsigned long long __calculate_block_age(unsigned long long new,
+ unsigned long long old)
+{
+ unsigned long long diff;
+
+ diff = (new >= old) ? new - (new - old) : new + (old - new);
+
+ return div_u64(diff * LAST_AGE_WEIGHT, 100);
+}
+
+/* This returns a new age and allocated blocks in ei */
+static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ loff_t f_size = i_size_read(inode);
+ unsigned long long cur_blocks =
+ atomic64_read(&sbi->allocated_data_blocks);
+
+ /*
+ * When I/O is not aligned to a PAGE_SIZE, update will happen to the last
+ * file block even in seq write. So don't record age for newly last file
+ * block here.
+ */
+ if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) &&
+ ei->blk == NEW_ADDR)
+ return -EINVAL;
+
+ if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) {
+ unsigned long long cur_age;
+
+ if (cur_blocks >= ei->last_blocks)
+ cur_age = cur_blocks - ei->last_blocks;
+ else
+ /* allocated_data_blocks overflow */
+ cur_age = ULLONG_MAX - ei->last_blocks + cur_blocks;
+
+ if (ei->age)
+ ei->age = __calculate_block_age(cur_age, ei->age);
+ else
+ ei->age = cur_age;
+ ei->last_blocks = cur_blocks;
+ WARN_ON(ei->age > cur_blocks);
+ return 0;
+ }
+
+ f2fs_bug_on(sbi, ei->blk == NULL_ADDR);
+
+ /* the data block was allocated for the first time */
+ if (ei->blk == NEW_ADDR)
+ goto out;
+
+ if (__is_valid_data_blkaddr(ei->blk) &&
+ !f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE)) {
+ f2fs_bug_on(sbi, 1);
+ return -EINVAL;
+ }
+out:
+ /*
+ * init block age with zero, this can happen when the block age extent
+ * was reclaimed due to memory constraint or system reboot
+ */
+ ei->age = 0;
+ ei->last_blocks = cur_blocks;
+ return 0;
+}
+
static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type)
{
struct extent_info ei;
ei.blk = NULL_ADDR;
else
ei.blk = dn->data_blkaddr;
+ } else if (type == EX_BLOCK_AGE) {
+ ei.blk = dn->data_blkaddr;
+ if (__get_new_block_age(dn->inode, &ei))
+ return;
}
__update_extent_tree_range(dn->inode, &ei, type);
}
return __shrink_extent_tree(sbi, nr_shrink, EX_READ);
}
+/* block age extent cache operations */
+bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei)
+{
+ if (!__may_extent_tree(inode, EX_BLOCK_AGE))
+ return false;
+
+ return __lookup_extent_tree(inode, pgofs, ei, EX_BLOCK_AGE);
+}
+
+void f2fs_update_age_extent_cache(struct dnode_of_data *dn)
+{
+ return __update_extent_cache(dn, EX_BLOCK_AGE);
+}
+
+void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t fofs, unsigned int len)
+{
+ struct extent_info ei = {
+ .fofs = fofs,
+ .len = len,
+ };
+
+ if (!__may_extent_tree(dn->inode, EX_BLOCK_AGE))
+ return;
+
+ __update_extent_tree_range(dn->inode, &ei, EX_BLOCK_AGE);
+}
+
+unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+ if (!test_opt(sbi, AGE_EXTENT_CACHE))
+ return 0;
+
+ return __shrink_extent_tree(sbi, nr_shrink, EX_BLOCK_AGE);
+}
+
static unsigned int __destroy_extent_node(struct inode *inode,
enum extent_type type)
{
void f2fs_destroy_extent_node(struct inode *inode)
{
__destroy_extent_node(inode, EX_READ);
+ __destroy_extent_node(inode, EX_BLOCK_AGE);
}
static void __drop_extent_tree(struct inode *inode, enum extent_type type)
void f2fs_drop_extent_tree(struct inode *inode)
{
__drop_extent_tree(inode, EX_READ);
+ __drop_extent_tree(inode, EX_BLOCK_AGE);
}
static void __destroy_extent_tree(struct inode *inode, enum extent_type type)
void f2fs_destroy_extent_tree(struct inode *inode)
{
__destroy_extent_tree(inode, EX_READ);
+ __destroy_extent_tree(inode, EX_BLOCK_AGE);
}
static void __init_extent_tree_info(struct extent_tree_info *eti)
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
{
__init_extent_tree_info(&sbi->extent_tree[EX_READ]);
+ __init_extent_tree_info(&sbi->extent_tree[EX_BLOCK_AGE]);
+
+ /* initialize for block age extents */
+ atomic64_set(&sbi->allocated_data_blocks, 0);
+ sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD;
+ sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD;
}
int __init f2fs_create_extent_cache(void)
#define F2FS_MOUNT_MERGE_CHECKPOINT 0x10000000
#define F2FS_MOUNT_GC_MERGE 0x20000000
#define F2FS_MOUNT_COMPRESS_CACHE 0x40000000
+#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x80000000
#define F2FS_OPTION(sbi) ((sbi)->mount_opt)
#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
/* number of extent info in extent cache we try to shrink */
#define READ_EXTENT_CACHE_SHRINK_NUMBER 128
+/* number of age extent info in extent cache we try to shrink */
+#define AGE_EXTENT_CACHE_SHRINK_NUMBER 128
+#define LAST_AGE_WEIGHT 30
+#define SAME_AGE_REGION 1024
+
+/*
+ * Define data block with age less than 1GB as hot data
+ * define data block with age less than 10GB but more than 1GB as warm data
+ */
+#define DEF_HOT_DATA_AGE_THRESHOLD 262144
+#define DEF_WARM_DATA_AGE_THRESHOLD 2621440
+
/* extent cache type */
enum extent_type {
EX_READ,
+ EX_BLOCK_AGE,
NR_EXTENT_CACHES,
};
unsigned int c_len;
#endif
};
+ /* block age extent_cache */
+ struct {
+ /* block age of the extent */
+ unsigned long long age;
+ /* last total blocks allocated */
+ unsigned long long last_blocks;
+ };
};
};
/* for extent tree cache */
struct extent_tree_info extent_tree[NR_EXTENT_CACHES];
+ atomic64_t allocated_data_blocks; /* for block age extent_cache */
+
+ /* The threshold used for hot and warm data seperation*/
+ unsigned int hot_data_age_threshold;
+ unsigned int warm_data_age_threshold;
/* basic filesystem units */
unsigned int log_sectors_per_block; /* log2 sectors per block */
unsigned long long ext_mem[NR_EXTENT_CACHES];
/* for read extent cache */
unsigned long long hit_largest;
+ /* for block age extent cache */
+ unsigned long long allocated_data_blocks;
int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
int ndirty_data, ndirty_qdata;
unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi,
int nr_shrink);
+/* block age extent cache ops */
+void f2fs_init_age_extent_tree(struct inode *inode);
+bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei);
+void f2fs_update_age_extent_cache(struct dnode_of_data *dn);
+void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t fofs, unsigned int len);
+unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi,
+ int nr_shrink);
+
/*
* sysfs.c
*/
fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page),
dn->inode) + ofs;
f2fs_update_read_extent_cache_range(dn, fofs, 0, len);
+ f2fs_update_age_extent_cache_range(dn, fofs, nr_free);
dec_valid_block_count(sbi, dn->inode, nr_free);
}
dn->ofs_in_node = ofs;
/* Need all the flag bits */
f2fs_init_read_extent_tree(inode, node_page);
+ f2fs_init_age_extent_tree(inode);
f2fs_put_page(node_page, 1);
avail_ram = val.totalram - val.totalhigh;
/*
- * give 25%, 25%, 50%, 50%, 50% memory for each components respectively
+ * give 25%, 25%, 50%, 50%, 25%, 25% memory for each components respectively
*/
if (type == FREE_NIDS) {
mem_size = (nm_i->nid_cnt[FREE_NID] *
sizeof(struct ino_entry);
mem_size >>= PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
- } else if (type == READ_EXTENT_CACHE) {
- struct extent_tree_info *eti = &sbi->extent_tree[EX_READ];
+ } else if (type == READ_EXTENT_CACHE || type == AGE_EXTENT_CACHE) {
+ enum extent_type etype = type == READ_EXTENT_CACHE ?
+ EX_READ : EX_BLOCK_AGE;
+ struct extent_tree_info *eti = &sbi->extent_tree[etype];
mem_size = (atomic_read(&eti->total_ext_tree) *
sizeof(struct extent_tree) +
atomic_read(&eti->total_ext_node) *
sizeof(struct extent_node)) >> PAGE_SHIFT;
- res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == DISCARD_CACHE) {
mem_size = (atomic_read(&dcc->discard_cmd_cnt) *
sizeof(struct discard_cmd)) >> PAGE_SHIFT;
DIRTY_DENTS, /* indicates dirty dentry pages */
INO_ENTRIES, /* indicates inode entries */
READ_EXTENT_CACHE, /* indicates read extent cache */
+ AGE_EXTENT_CACHE, /* indicates age extent cache */
DISCARD_CACHE, /* indicates memory of cached discard cmds */
COMPRESS_PAGE, /* indicates memory of cached compressed pages */
BASE_CHECK, /* check kernel status */
f2fs_shrink_read_extent_tree(sbi,
READ_EXTENT_CACHE_SHRINK_NUMBER);
+ /* try to shrink age extent cache when there is no enough memory */
+ if (!f2fs_available_free_memory(sbi, AGE_EXTENT_CACHE))
+ f2fs_shrink_age_extent_tree(sbi,
+ AGE_EXTENT_CACHE_SHRINK_NUMBER);
+
/* check the # of cached NAT entries */
if (!f2fs_available_free_memory(sbi, NAT_ENTRIES))
f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
}
}
+static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct extent_info ei;
+
+ if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) {
+ if (!ei.age)
+ return NO_CHECK_TYPE;
+ if (ei.age <= sbi->hot_data_age_threshold)
+ return CURSEG_HOT_DATA;
+ if (ei.age <= sbi->warm_data_age_threshold)
+ return CURSEG_WARM_DATA;
+ return CURSEG_COLD_DATA;
+ }
+ return NO_CHECK_TYPE;
+}
+
static int __get_segment_type_6(struct f2fs_io_info *fio)
{
if (fio->type == DATA) {
struct inode *inode = fio->page->mapping->host;
+ int type;
if (is_inode_flag_set(inode, FI_ALIGNED_WRITE))
return CURSEG_COLD_DATA_PINNED;
}
if (file_is_cold(inode) || f2fs_need_compress_data(inode))
return CURSEG_COLD_DATA;
+
+ type = __get_age_segment_type(inode, fio->page->index);
+ if (type != NO_CHECK_TYPE)
+ return type;
+
if (file_is_hot(inode) ||
is_inode_flag_set(inode, FI_HOT_DATA) ||
f2fs_is_cow_file(inode))
locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr));
+ if (IS_DATASEG(type))
+ atomic64_inc(&sbi->allocated_data_blocks);
+
up_write(&sit_i->sentry_lock);
if (page && IS_NODESEG(type)) {
struct f2fs_summary sum;
f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
+ if (fio->io_type == FS_DATA_IO || fio->io_type == FS_CP_DATA_IO)
+ f2fs_update_age_extent_cache(dn);
set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version);
do_write_page(&sum, fio);
f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
/* 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);
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 >> 1);
+ freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2);
/* shrink clean nat cache entries */
if (freed < nr)
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);
Opt_nogc_merge,
Opt_discard_unit,
Opt_memory_mode,
+ Opt_age_extent_cache,
Opt_err,
};
{Opt_nogc_merge, "nogc_merge"},
{Opt_discard_unit, "discard_unit=%s"},
{Opt_memory_mode, "memory=%s"},
+ {Opt_age_extent_cache, "age_extent_cache"},
{Opt_err, NULL},
};
}
kfree(name);
break;
+ case Opt_age_extent_cache:
+ set_opt(sbi, AGE_EXTENT_CACHE);
+ break;
default:
f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
p);
seq_puts(seq, ",extent_cache");
else
seq_puts(seq, ",noextent_cache");
+ if (test_opt(sbi, AGE_EXTENT_CACHE))
+ seq_puts(seq, ",age_extent_cache");
if (test_opt(sbi, DATA_FLUSH))
seq_puts(seq, ",data_flush");
bool need_restart_flush = false, need_stop_flush = false;
bool need_restart_discard = false, need_stop_discard = false;
bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE);
+ bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE);
bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT);
bool no_io_align = !F2FS_IO_ALIGNED(sbi);
bool no_atgc = !test_opt(sbi, ATGC);
f2fs_warn(sbi, "switch extent_cache option is not allowed");
goto restore_opts;
}
+ /* disallow enable/disable age extent_cache dynamically */
+ if (no_age_extent_cache == !!test_opt(sbi, AGE_EXTENT_CACHE)) {
+ err = -EINVAL;
+ f2fs_warn(sbi, "switch age_extent_cache option is not allowed");
+ goto restore_opts;
+ }
if (no_io_align == !!F2FS_IO_ALIGNED(sbi)) {
err = -EINVAL;
return count;
}
+ if (!strcmp(a->attr.name, "hot_data_age_threshold")) {
+ if (t == 0 || t >= sbi->warm_data_age_threshold)
+ return -EINVAL;
+ if (t == *ui)
+ return count;
+ *ui = (unsigned int)t;
+ return count;
+ }
+
+ if (!strcmp(a->attr.name, "warm_data_age_threshold")) {
+ if (t == 0 || t <= sbi->hot_data_age_threshold)
+ return -EINVAL;
+ if (t == *ui)
+ return count;
+ *ui = (unsigned int)t;
+ return count;
+ }
+
*ui = (unsigned int)t;
return count;
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, committed_atomic_block, committed_atomic_block);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, revoked_atomic_block, revoked_atomic_block);
+/* For block age extent cache */
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, hot_data_age_threshold, hot_data_age_threshold);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, warm_data_age_threshold, warm_data_age_threshold);
+
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
ATTR_LIST(gc_urgent_sleep_time),
ATTR_LIST(peak_atomic_write),
ATTR_LIST(committed_atomic_block),
ATTR_LIST(revoked_atomic_block),
+ ATTR_LIST(hot_data_age_threshold),
+ ATTR_LIST(warm_data_age_threshold),
NULL,
};
ATTRIBUTE_GROUPS(f2fs);
TRACE_DEFINE_ENUM(CP_PAUSE);
TRACE_DEFINE_ENUM(CP_RESIZE);
TRACE_DEFINE_ENUM(EX_READ);
+TRACE_DEFINE_ENUM(EX_BLOCK_AGE);
#define show_block_type(type) \
__print_symbolic(type, \
{ COMPRESS_ZSTD, "ZSTD" }, \
{ COMPRESS_LZORLE, "LZO-RLE" })
+#define show_extent_type(type) \
+ __print_symbolic(type, \
+ { EX_READ, "Read" }, \
+ { EX_BLOCK_AGE, "Block Age" })
+
struct f2fs_sb_info;
struct f2fs_io_info;
struct extent_info;
TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, type = %s",
show_dev_ino(__entry),
__entry->pgofs,
- __entry->type == EX_READ ? "Read" : "N/A")
+ show_extent_type(__entry->type))
);
TRACE_EVENT_CONDITION(f2fs_lookup_read_extent_tree_end,
__entry->blk)
);
+TRACE_EVENT_CONDITION(f2fs_lookup_age_extent_tree_end,
+
+ TP_PROTO(struct inode *inode, unsigned int pgofs,
+ struct extent_info *ei),
+
+ TP_ARGS(inode, pgofs, ei),
+
+ TP_CONDITION(ei),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(unsigned int, pgofs)
+ __field(unsigned int, fofs)
+ __field(unsigned int, len)
+ __field(unsigned long long, age)
+ __field(unsigned long long, blocks)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pgofs = pgofs;
+ __entry->fofs = ei->fofs;
+ __entry->len = ei->len;
+ __entry->age = ei->age;
+ __entry->blocks = ei->last_blocks;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+ "age_ext_info(fofs: %u, len: %u, age: %llu, blocks: %llu)",
+ show_dev_ino(__entry),
+ __entry->pgofs,
+ __entry->fofs,
+ __entry->len,
+ __entry->age,
+ __entry->blocks)
+);
+
TRACE_EVENT(f2fs_update_read_extent_tree_range,
TP_PROTO(struct inode *inode, unsigned int pgofs, unsigned int len,
__entry->c_len)
);
+TRACE_EVENT(f2fs_update_age_extent_tree_range,
+
+ TP_PROTO(struct inode *inode, unsigned int pgofs, unsigned int len,
+ unsigned long long age,
+ unsigned long long last_blks),
+
+ TP_ARGS(inode, pgofs, len, age, last_blks),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(unsigned int, pgofs)
+ __field(unsigned int, len)
+ __field(unsigned long long, age)
+ __field(unsigned long long, blocks)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pgofs = pgofs;
+ __entry->len = len;
+ __entry->age = age;
+ __entry->blocks = last_blks;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+ "len = %u, age = %llu, blocks = %llu",
+ show_dev_ino(__entry),
+ __entry->pgofs,
+ __entry->len,
+ __entry->age,
+ __entry->blocks)
+);
+
TRACE_EVENT(f2fs_shrink_extent_tree,
TP_PROTO(struct f2fs_sb_info *sbi, unsigned int node_cnt,
show_dev(__entry->dev),
__entry->node_cnt,
__entry->tree_cnt,
- __entry->type == EX_READ ? "Read" : "N/A")
+ show_extent_type(__entry->type))
);
TRACE_EVENT(f2fs_destroy_extent_tree,
TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u, type = %s",
show_dev_ino(__entry),
__entry->node_cnt,
- __entry->type == EX_READ ? "Read" : "N/A")
+ show_extent_type(__entry->type))
);
DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
projects / platform / kernel / linux-rpi.git / commitdiff