f2fs: avoid readahead race condition

If two readahead threads having same offset enter in readpages, every read
IOs are split and issued to the disk which giving lower bandwidth.

This patch tries to avoid redundant readahead calls.

Fixes one build error reported by Randy.
Fix build error when F2FS_FS_COMPRESSION is not set/enabled.
This label is needed in either case.

../fs/f2fs/data.c: In function ‘f2fs_mpage_readpages’:
../fs/f2fs/data.c:2327:5: error: label ‘next_page’ used but not defined
     goto next_page;

Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 20f31ff47e05ffb4a21e031f686790cc17b32f61..44645f4f914b62c566c077b59dc8a790ef75ef6b 100644 (file)
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2298,6 +2298,7 @@ static int f2fs_mpage_readpages(struct inode *inode,
        unsigned nr_pages = rac ? readahead_count(rac) : 1;
        unsigned max_nr_pages = nr_pages;
        int ret = 0;
+       bool drop_ra = false;
 
        map.m_pblk = 0;
        map.m_lblk = 0;
@@ -2308,10 +2309,26 @@ static int f2fs_mpage_readpages(struct inode *inode,
        map.m_seg_type = NO_CHECK_TYPE;
        map.m_may_create = false;
 
+       /*
+        * Two readahead threads for same address range can cause race condition
+        * which fragments sequential read IOs. So let's avoid each other.
+        */
+       if (rac && readahead_count(rac)) {
+               if (READ_ONCE(F2FS_I(inode)->ra_offset) == readahead_index(rac))
+                       drop_ra = true;
+               else
+                       WRITE_ONCE(F2FS_I(inode)->ra_offset,
+                                               readahead_index(rac));
+       }
+
        for (; nr_pages; nr_pages--) {
                if (rac) {
                        page = readahead_page(rac);
                        prefetchw(&page->flags);
+                       if (drop_ra) {
+                               f2fs_put_page(page, 1);
+                               continue;
+                       }
                }
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -2374,6 +2391,9 @@ next_page:
        }
        if (bio)
                __submit_bio(F2FS_I_SB(inode), bio, DATA);
+
+       if (rac && readahead_count(rac) && !drop_ra)
+               WRITE_ONCE(F2FS_I(inode)->ra_offset, -1);
        return ret;
 }
 

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4f1f1a3e33347ebefc164bdd6e901087162c8461..c98a9182862b23e01866443662bcdbfce283f8ee 100644 (file)
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -794,6 +794,7 @@ struct f2fs_inode_info {
        struct list_head inmem_pages;   /* inmemory pages managed by f2fs */
        struct task_struct *inmem_task; /* store inmemory task */
        struct mutex inmem_lock;        /* lock for inmemory pages */
+       pgoff_t ra_offset;              /* ongoing readahead offset */
        struct extent_tree *extent_tree;        /* cached extent_tree entry */
 
        /* avoid racing between foreground op and gc */

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 7326522057378a2df8b398c0a7de540a3a7d5a30..80cb7cd358f8498150934b183ed327417b0d82f1 100644 (file)
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1015,6 +1015,8 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
        /* Will be used by directory only */
        fi->i_dir_level = F2FS_SB(sb)->dir_level;
 
+       fi->ra_offset = -1;
+
        return &fi->vfs_inode;
 }