f2fs: fix performance issue observed with multi-thread sequential read

This reverts the commit - "b93f7712 - f2fs: remove writepages lock"
to fix the drop in sequential read throughput.

Test: ./tiotest -t 32 -d /data/tio_tmp -f 32 -b 524288 -k 1 -k 3 -L
device: UFS

Before -
read throughput: 185 MB/s
total read requests: 85177 (of these ~80000 are 4KB size requests).
total write requests: 2546 (of these ~2208 requests are written in 512KB).

After -
read throughput: 758 MB/s
total read requests: 2417 (of these ~2042 are 512KB reads).
total write requests: 2701 (of these ~2034 requests are written in 512KB).
Signed-off-by: NSahitya Tummala <stummala@codeaurora.org>
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -51,6 +51,14 @@ Description:
 		 Controls the dirty page count condition for the in-place-update
 		 policies.
 
+What:		/sys/fs/f2fs/<disk>/min_seq_blocks
+Date:		August 2018
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the dirty page count condition for batched sequential
+		 writes in ->writepages.
+
+
 What:		/sys/fs/f2fs/<disk>/min_hot_blocks
 Date:		March 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>

fs/f2fs/data.c

@@ -2122,6 +2122,18 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	return ret;
 }
 
+static inline bool __should_serialize_io(struct inode *inode,
+					struct writeback_control *wbc)
+{
+	if (!S_ISREG(inode->i_mode))
+		return false;
+	if (wbc->sync_mode != WB_SYNC_ALL)
+		return true;
+	if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
+		return true;
+	return false;
+}
+
 static int __f2fs_write_data_pages(struct address_space *mapping,
 						struct writeback_control *wbc,
 						enum iostat_type io_type)
@@ -2130,6 +2142,7 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct blk_plug plug;
 	int ret;
+	bool locked = false;
 
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
@@ -2160,10 +2173,18 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
 	else if (atomic_read(&sbi->wb_sync_req[DATA]))
 		goto skip_write;
 
+	if (__should_serialize_io(inode, wbc)) {
+		mutex_lock(&sbi->writepages);
+		locked = true;
+	}
+
 	blk_start_plug(&plug);
 	ret = f2fs_write_cache_pages(mapping, wbc, io_type);
 	blk_finish_plug(&plug);
 
+	if (locked)
+		mutex_unlock(&sbi->writepages);
+
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		atomic_dec(&sbi->wb_sync_req[DATA]);
 	/*

fs/f2fs/f2fs.h

@@ -913,6 +913,7 @@ struct f2fs_sm_info {
 	unsigned int ipu_policy;	/* in-place-update policy */
 	unsigned int min_ipu_util;	/* in-place-update threshold */
 	unsigned int min_fsync_blocks;	/* threshold for fsync */
+	unsigned int min_seq_blocks;	/* threshold for sequential blocks */
 	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
 	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
 
@@ -1133,6 +1134,7 @@ struct f2fs_sb_info {
 	struct rw_semaphore sb_lock;		/* lock for raw super block */
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
+	struct mutex writepages;		/* mutex for writepages() */
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */

fs/f2fs/segment.c

@@ -4127,6 +4127,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
 		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
+	sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
 	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
 	sm_info->min_ssr_sections = reserved_sections(sbi);
 

fs/f2fs/super.c

@@ -2842,6 +2842,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	/* init f2fs-specific super block info */
 	sbi->valid_super_block = valid_super_block;
 	mutex_init(&sbi->gc_mutex);
+	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
 	init_rwsem(&sbi->node_change);

fs/f2fs/sysfs.c

@@ -397,6 +397,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_seq_blocks, min_seq_blocks);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
 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);
@@ -449,6 +450,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
 	ATTR_LIST(min_fsync_blocks),
+	ATTR_LIST(min_seq_blocks),
 	ATTR_LIST(min_hot_blocks),
 	ATTR_LIST(min_ssr_sections),
 	ATTR_LIST(max_victim_search),