f2fs: introduce checkpoint_merge mount option

We've added a new mount options, "checkpoint_merge" and "nocheckpoint_merge",
which creates a kernel daemon and makes it to merge concurrent checkpoint
requests as much as possible to eliminate redundant checkpoint issues. Plus,
we can eliminate the sluggish issue caused by slow checkpoint operation
when the checkpoint is done in a process context in a cgroup having
low i/o budget and cpu shares. To make this do better, we set the
default i/o priority of the kernel daemon to "3", to give one higher
priority than other kernel threads. The below verification result
explains this.
The basic idea has come from https://opensource.samsung.com.

[Verification]
Android Pixel Device(ARM64, 7GB RAM, 256GB UFS)
Create two I/O cgroups (fg w/ weight 100, bg w/ wight 20)
Set "strict_guarantees" to "1" in BFQ tunables

In "fg" cgroup,
- thread A => trigger 1000 checkpoint operations
  "for i in `seq 1 1000`; do touch test_dir1/file; fsync test_dir1;
   done"
- thread B => gererating async. I/O
  "fio --rw=write --numjobs=1 --bs=128k --runtime=3600 --time_based=1
       --filename=test_img --name=test"

In "bg" cgroup,
- thread C => trigger repeated checkpoint operations
  "echo $$ > /dev/blkio/bg/tasks; while true; do touch test_dir2/file;
   fsync test_dir2; done"

We've measured thread A's execution time.

[ w/o patch ]
Elapsed Time: Avg. 68 seconds
[ w/  patch ]
Elapsed Time: Avg. 48 seconds

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
[Jaegeuk Kim: fix the return value in f2fs_start_ckpt_thread, reported by Dan]
Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Sungjong Seo <sj1557.seo@samsung.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 27 insertions, 0 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index a2e520a13630..f7536aca8a31 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -97,6 +97,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
 #define F2FS_MOUNT_NORECOVERY		0x04000000
 #define F2FS_MOUNT_ATGC			0x08000000
+#define F2FS_MOUNT_MERGE_CHECKPOINT	0x10000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -267,6 +268,25 @@ struct fsync_node_entry {
 	unsigned int seq_id;	/* sequence id */
 };
 
+struct ckpt_req {
+	struct completion wait;		/* completion for checkpoint done */
+	struct llist_node llnode;	/* llist_node to be linked in wait queue */
+	int ret;			/* return code of checkpoint */
+	ktime_t queue_time;		/* request queued time */
+};
+
+struct ckpt_req_control {
+	struct task_struct *f2fs_issue_ckpt;	/* checkpoint task */
+	wait_queue_head_t ckpt_wait_queue;	/* waiting queue for wake-up */
+	atomic_t issued_ckpt;		/* # of actually issued ckpts */
+	atomic_t total_ckpt;		/* # of total ckpts */
+	atomic_t queued_ckpt;		/* # of queued ckpts */
+	struct llist_head issue_list;	/* list for command issue */
+	spinlock_t stat_lock;		/* lock for below checkpoint time stats */
+	unsigned int cur_time;		/* cur wait time in msec for currently issued checkpoint */
+	unsigned int peak_time;		/* peak wait time in msec until now */
+};
+
 /* for the bitmap indicate blocks to be discarded */
 struct discard_entry {
 	struct list_head list;	/* list head */
@@ -1433,6 +1453,7 @@ struct f2fs_sb_info {
 	wait_queue_head_t cp_wait;
 	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
 	long interval_time[MAX_TIME];		/* to store thresholds */
+	struct ckpt_req_control cprc_info;	/* for checkpoint request control */
 
 	struct inode_management im[MAX_INO_ENTRY];	/* manage inode cache */
 
@@ -3450,6 +3471,10 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
 int __init f2fs_create_checkpoint_caches(void);
 void f2fs_destroy_checkpoint_caches(void);
+int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi);
+int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi);
+void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi);
+void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi);
 
 /*
  * data.c
@@ -3562,6 +3587,8 @@ struct f2fs_stat_info {
 	int nr_discarding, nr_discarded;
 	int nr_discard_cmd;
 	unsigned int undiscard_blks;
+	int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt;
+	unsigned int cur_ckpt_time, peak_ckpt_time;
 	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
 	int compr_inode;
 	unsigned long long compr_blocks;