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: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -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

@@ -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

@@ -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

@@ -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

@@ -1782,6 +1782,7 @@ continue_unlock:
 
 			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);

fs/f2fs/node.h

@@ -31,6 +31,9 @@
 /* control total # of nats */
 #define DEF_NAT_CACHE_THRESHOLD			100000
 
+/* control total # of node writes used for roll-fowrad recovery */
+#define DEF_RF_NODE_BLOCKS			0
+
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
 #define SETVEC_SIZE	32

fs/f2fs/recovery.c

@@ -56,6 +56,10 @@ bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
 
 	if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
 		return false;
+	if (NM_I(sbi)->max_rf_node_blocks &&
+		percpu_counter_sum_positive(&sbi->rf_node_block_count) >=
+						NM_I(sbi)->max_rf_node_blocks)
+		return false;
 	return true;
 }
 

fs/f2fs/super.c

@@ -1501,8 +1501,9 @@ static void f2fs_free_inode(struct inode *inode)
 
 static void destroy_percpu_info(struct f2fs_sb_info *sbi)
 {
-	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 	percpu_counter_destroy(&sbi->total_valid_inode_count);
+	percpu_counter_destroy(&sbi->rf_node_block_count);
+	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 }
 
 static void destroy_device_list(struct f2fs_sb_info *sbi)
@@ -3619,11 +3620,20 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
 	if (err)
 		return err;
 
+	err = percpu_counter_init(&sbi->rf_node_block_count, 0, GFP_KERNEL);
+	if (err)
+		goto err_valid_block;
+
 	err = percpu_counter_init(&sbi->total_valid_inode_count, 0,
 								GFP_KERNEL);
 	if (err)
-		percpu_counter_destroy(&sbi->alloc_valid_block_count);
+		goto err_node_block;
+	return 0;
 
+err_node_block:
+	percpu_counter_destroy(&sbi->rf_node_block_count);
+err_valid_block:
+	percpu_counter_destroy(&sbi->alloc_valid_block_count);
 	return err;
 }
 

fs/f2fs/sysfs.c

@@ -732,6 +732,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, max_roll_forward_node_blocks, max_rf_node_blocks);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, migration_granularity, migration_granularity);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
@@ -855,6 +856,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(ram_thresh),
 	ATTR_LIST(ra_nid_pages),
 	ATTR_LIST(dirty_nats_ratio),
+	ATTR_LIST(max_roll_forward_node_blocks),
 	ATTR_LIST(cp_interval),
 	ATTR_LIST(idle_interval),
 	ATTR_LIST(discard_idle_interval),