From: Chao Yu <chao@kernel.org>
Date: Mon, 21 Jul 2025 02:13:52 +0000 (+0800)
Subject: erofs: support to readahead dirent blocks in erofs_readdir()
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=df0ce6cefa453d2236381645e529a27ef2f0a573;p=thirdparty%2Flinux.git

erofs: support to readahead dirent blocks in erofs_readdir()

This patch supports to readahead more blocks in erofs_readdir(), it can
enhance readdir performance in large direcotry.

readdir test in a large directory which contains 12000 sub-files.

		files_per_second
Before:		926385.54
After:		2380435.562

Meanwhile, let's introduces a new sysfs entry to control readahead
bytes to provide more flexible policy for readahead of readdir().
- location: /sys/fs/erofs/<disk>/dir_ra_bytes
- default value: 16384
- disable readahead: set the value to 0

Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250721021352.2495371-1-chao@kernel.org
[ Gao Xiang: minor styling adjustment. ]
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---

diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs
index ad6d1a3ccd4e0..76d9808ed5814 100644
--- a/Documentation/ABI/testing/sysfs-fs-erofs
+++ b/Documentation/ABI/testing/sysfs-fs-erofs
@@ -35,3 +35,11 @@ Description:	Used to set or show hardware accelerators in effect
 		and multiple accelerators are separated by '\n'.
 		Supported accelerator(s): qat_deflate.
 		Disable all accelerators with an empty string (echo > accel).
+
+What:		/sys/fs/erofs/<disk>/dir_ra_bytes
+Date:		July 2025
+Contact:	"Chao Yu" <chao@kernel.org>
+Description:	Used to set or show readahead bytes during readdir(), by
+		default the value is 16384.
+
+		- 0: disable readahead.
diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index d1c6cd1a45e87..debf469ad6bd5 100644
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -48,8 +48,12 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 	struct inode *dir = file_inode(f);
 	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
 	struct super_block *sb = dir->i_sb;
+	struct file_ra_state *ra = &f->f_ra;
 	unsigned long bsz = sb->s_blocksize;
 	unsigned int ofs = erofs_blkoff(sb, ctx->pos);
+	pgoff_t ra_pages = DIV_ROUND_UP_POW2(
+			EROFS_I_SB(dir)->dir_ra_bytes, PAGE_SIZE);
+	pgoff_t nr_pages = DIV_ROUND_UP_POW2(dir->i_size, PAGE_SIZE);
 	int err = 0;
 	bool initial = true;
 
@@ -64,6 +68,16 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 			break;
 		}
 
+		/* readahead blocks to enhance performance for large directories */
+		if (ra_pages) {
+			pgoff_t idx = DIV_ROUND_UP_POW2(ctx->pos, PAGE_SIZE);
+			pgoff_t pages = min(nr_pages - idx, ra_pages);
+
+			if (pages > 1 && !ra_has_index(ra, idx))
+				page_cache_sync_readahead(dir->i_mapping, ra,
+							  f, idx, pages);
+		}
+
 		de = erofs_bread(&buf, dbstart, true);
 		if (IS_ERR(de)) {
 			erofs_err(sb, "failed to readdir of logical block %llu of nid %llu",
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 26f9aa57ff3ca..4ccc5f0ee8dfb 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -159,6 +159,7 @@ struct erofs_sb_info {
 	/* sysfs support */
 	struct kobject s_kobj;		/* /sys/fs/erofs/<devname> */
 	struct completion s_kobj_unregister;
+	erofs_off_t dir_ra_bytes;
 
 	/* fscache support */
 	struct fscache_volume *volume;
@@ -259,6 +260,9 @@ static inline u64 erofs_nid_to_ino64(struct erofs_sb_info *sbi, erofs_nid_t nid)
 #define EROFS_I_BL_XATTR_BIT	(BITS_PER_LONG - 1)
 #define EROFS_I_BL_Z_BIT	(BITS_PER_LONG - 2)
 
+/* default readahead size of directories */
+#define EROFS_DIR_RA_BYTES	16384
+
 struct erofs_inode {
 	erofs_nid_t nid;
 
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index c7b9b784dc3da..e1020aa607714 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -731,6 +731,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
+	sbi->dir_ra_bytes = EROFS_DIR_RA_BYTES;
 	erofs_info(sb, "mounted with root inode @ nid %llu.", sbi->root_nid);
 	return 0;
 }
diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c
index a9fe35ba0906f..1e0658a1d95b9 100644
--- a/fs/erofs/sysfs.c
+++ b/fs/erofs/sysfs.c
@@ -65,12 +65,14 @@ EROFS_ATTR_FUNC(drop_caches, 0200);
 #ifdef CONFIG_EROFS_FS_ZIP_ACCEL
 EROFS_ATTR_FUNC(accel, 0644);
 #endif
+EROFS_ATTR_RW_UI(dir_ra_bytes, erofs_sb_info);
 
 static struct attribute *erofs_sb_attrs[] = {
 #ifdef CONFIG_EROFS_FS_ZIP
 	ATTR_LIST(sync_decompress),
 	ATTR_LIST(drop_caches),
 #endif
+	ATTR_LIST(dir_ra_bytes),
 	NULL,
 };
 ATTRIBUTE_GROUPS(erofs_sb);