Commit 47c8ebcc authored by Jaegeuk Kim's avatar Jaegeuk Kim
Browse files

f2fs: add a way to limit roll forward recovery time 



This adds a sysfs entry to call checkpoint during fsync() in order to avoid
long elapsed time to run roll-forward recovery when booting the device.
Default value doesn't enforce the limitation which is same as before.

Reviewed-by: default avatarChao Yu <chao@kernel.org>
Signed-off-by: default avatarJaegeuk Kim <jaegeuk@kernel.org>
parent 1018a546

Documentation/ABI/testing/sysfs-fs-f2fs

+6 −0
Original line number Diff line number Diff line
@@ -568,3 +568,9 @@ Contact: "Daeho Jeong" <daehojeong@google.com> 
Description:	You can set the trial count limit for GC urgent high mode with this value.

		If GC thread gets to the limit, the mode will turn back to GC normal mode.

		By default, the value is zero, which means there is no limit like before.



What:		/sys/fs/f2fs/<disk>/max_roll_forward_node_blocks

Date:		January 2022

Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>

Description:	Controls max # of node block writes to be used for roll forward

		recovery. This can limit the roll forward recovery time.

fs/f2fs/checkpoint.c

+1 −0
Original line number Diff line number Diff line
@@ -1547,6 +1547,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) 
	/* update user_block_counts */

	sbi->last_valid_block_count = sbi->total_valid_block_count;

	percpu_counter_set(&sbi->alloc_valid_block_count, 0);

	percpu_counter_set(&sbi->rf_node_block_count, 0);



	/* Here, we have one bio having CP pack except cp pack 2 page */

	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);

fs/f2fs/debug.c

+3 −0
Original line number Diff line number Diff line
@@ -532,6 +532,9 @@ static int stat_show(struct seq_file *s, void *v) 
			   si->ndirty_meta, si->meta_pages);

		seq_printf(s, "  - imeta: %4d\n",

			   si->ndirty_imeta);

		seq_printf(s, "  - fsync mark: %4lld\n",

			   percpu_counter_sum_positive(

					&si->sbi->rf_node_block_count));

		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",

			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);

		seq_printf(s, "  - free_nids: %9d/%9d\n  - alloc_nids: %9d\n",

fs/f2fs/f2fs.h

+3 −0
Original line number Diff line number Diff line
@@ -917,6 +917,7 @@ struct f2fs_nm_info { 
	nid_t max_nid;			/* maximum possible node ids */

	nid_t available_nids;		/* # of available node ids */

	nid_t next_scan_nid;		/* the next nid to be scanned */

	nid_t max_rf_node_blocks;	/* max # of nodes for recovery */

	unsigned int ram_thresh;	/* control the memory footprint */

	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */

	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
@@ -1688,6 +1689,8 @@ struct f2fs_sb_info { 
	atomic_t nr_pages[NR_COUNT_TYPE];

	/* # of allocated blocks */

	struct percpu_counter alloc_valid_block_count;

	/* # of node block writes as roll forward recovery */

	struct percpu_counter rf_node_block_count;



	/* writeback control */

	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */

fs/f2fs/node.c

+2 −0
Original line number Diff line number Diff line
@@ -1782,6 +1782,7 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, 


			if (!atomic || page == last_page) {

				set_fsync_mark(page, 1);

				percpu_counter_inc(&sbi->rf_node_block_count);

				if (IS_INODE(page)) {

					if (is_inode_flag_set(inode,

								FI_DIRTY_INODE))
@@ -3218,6 +3219,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) 
	nm_i->ram_thresh = DEF_RAM_THRESHOLD;

	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;

	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;

	nm_i->max_rf_node_blocks = DEF_RF_NODE_BLOCKS;



	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);

	INIT_LIST_HEAD(&nm_i->free_nid_list);