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>

1 files changed, 33 insertions, 0 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 8722d1a13c17..dee712f7225f 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -453,6 +453,11 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 		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);
@@ -3151,10 +3156,28 @@ static int __get_segment_type_4(struct f2fs_io_info *fio)
 	}
 }
 
+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;
@@ -3169,6 +3192,11 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 		}
 		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))
@@ -3287,6 +3315,9 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	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)) {
@@ -3414,6 +3445,8 @@ void f2fs_outplace_write_data(struct dnode_of_data *dn,
 	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);