[f2fs-dev] [PATCH v2] f2fs: avoid congestion_wait when do_checkpointfor better performance

[Yuan Zhong]

Previously, do_checkpoint() will call congestion_wait() for waiting the pages (previous submitted node/meta/data pages) to be written back.
Because congestion_wait() will set a regular period (e.g. HZ / 50 ) for waiting.
For this reason, there is a situation that after the pages have been written back, but the checkpoint thread still wait for congestion_wait to exit.
This is a problem here, especially, when sync a large number of small files or dirs.
In order to avoid this, a wait_list is introduced, the checkpoint thread will be dropped into the wait_list if the pages have not been written back, and will be waked up by contrast.

Signed-off-by: Yuan Zhong <yuan.mark.zhong@xxxxxxxxxxx>
---  
 fs/f2fs/checkpoint.c |    3 +--
 fs/f2fs/f2fs.h       |   19 +++++++++++++++++++
 fs/f2fs/segment.c    |    1 +
 fs/f2fs/super.c      |    1 +
 4 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ca39442..5d69ae0 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -758,8 +758,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	f2fs_put_page(cp_page, 1);
 
 	/* wait for previous submitted node/meta pages writeback */
-	while (get_pages(sbi, F2FS_WRITEBACK))
-		congestion_wait(BLK_RW_ASYNC, HZ / 50);
+	f2fs_writeback_wait(sbi);
 
 	filemap_fdatawait_range(sbi->node_inode->i_mapping, 0, LONG_MAX);
 	filemap_fdatawait_range(sbi->meta_inode->i_mapping, 0, LONG_MAX);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7fd99d8..4b0d70e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -18,6 +18,8 @@
 #include <linux/crc32.h>
 #include <linux/magic.h>
 #include <linux/kobject.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
 
 /*
  * For mount options
@@ -368,6 +370,7 @@ struct f2fs_sb_info {
 	struct mutex fs_lock[NR_GLOBAL_LOCKS];	/* blocking FS operations */
 	struct mutex node_write;		/* locking node writes */
 	struct mutex writepages;		/* mutex for writepages() */
+	wait_queue_head_t writeback_wqh;	/* wait_queue for writeback */
 	unsigned char next_lock_num;		/* round-robin global locks */
 	int por_doing;				/* recovery is doing or not */
 	int on_build_free_nids;			/* build_free_nids is doing */
@@ -961,6 +964,22 @@ static inline int f2fs_readonly(struct super_block *sb)
 	return sb->s_flags & MS_RDONLY;
 }
 
+static inline void f2fs_writeback_wait(struct f2fs_sb_info *sbi)
+{
+	DEFINE_WAIT(wait);
+
+	prepare_to_wait(&sbi->writeback_wqh, &wait, TASK_UNINTERRUPTIBLE);
+	if (get_pages(sbi, F2FS_WRITEBACK))
+		io_schedule();
+	finish_wait(&sbi->writeback_wqh, &wait);
+}
+
+static inline void f2fs_writeback_wake(struct f2fs_sb_info *sbi)
+{
+	if (!get_pages(sbi, F2FS_WRITEBACK))
+		wake_up_all(&sbi->writeback_wqh);
+}
+
 /*
  * file.c
  */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index bd79bbe..0708aa9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -597,6 +597,7 @@ static void f2fs_end_io_write(struct bio *bio, int err)
 
 	if (p->is_sync)
 		complete(p->wait);
+	f2fs_writeback_wake(p->sbi);
 	kfree(p);
 	bio_put(bio);
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 094ccc6..3ac6d85 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -835,6 +835,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	mutex_init(&sbi->gc_mutex);
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
+	init_waitqueue_head(&sbi->writeback_wqh);
 	for (i = 0; i < NR_GLOBAL_LOCKS; i++)
 		mutex_init(&sbi->fs_lock[i]);
 	mutex_init(&sbi->node_write);N‹§²æìr¸›yúèšØb²X¬¶Ç§vØ^–)Þº{.nÇ+‰·¥Š{±‘êçzX§¶›¡Ü¨}©ž²Æ zÚ&j:+v‰¨¾«‘êçzZ+€Ê+zf£¢·hšˆ§~†­†Ûiÿûàz¹®w¥¢¸?™¨è­Ú&¢)ߢf”ù^jÇ«y§m…á@A«a¶Úÿ0¶ìh®å’i