fuse: enable per inode DAX

DAX may be limited in some specific situation. When the number of usable
DAX windows is under watermark, the recalim routine will be triggered to
reclaim some DAX windows. It may have a negative impact on the
performance, since some processes may need to wait for DAX windows to be
recalimed and reused then. To mitigate the performance degradation, the
overall DAX window need to be expanded larger.

However, simply expanding the DAX window may not be a good deal in some
scenario. To maintain one DAX window chunk (i.e., 2MB in size), 32KB
(512 * 64 bytes) memory footprint will be consumed for page descriptors
inside guest, which is greater than the memory footprint if it uses
guest page cache when DAX disabled. Thus it'd better disable DAX for
those files smaller than 32KB, to reduce the demand for DAX window and
thus avoid the unworthy memory overhead.

Per inode DAX feature is introduced to address this issue, by offering a
finer grained control for dax to users, trying to achieve a balance
between performance and memory overhead.

The FUSE_ATTR_DAX flag in FUSE_LOOKUP reply is used to indicate whether
DAX should be enabled or not for corresponding file. Currently the state
whether DAX is enabled or not for the file is initialized only when
inode is instantiated.

Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index d2bc5e7f513225ab78ab50b118bee5c82834a0ba..ff17bc7a0b6e6abfb7f0ca64078c8c2458404866 100644 (file)
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1330,7 +1330,7 @@ static const struct address_space_operations fuse_dax_file_aops  = {
        .invalidatepage = noop_invalidatepage,
 };
 
-static bool fuse_should_enable_dax(struct inode *inode)
+static bool fuse_should_enable_dax(struct inode *inode, unsigned int flags)
 {
        struct fuse_conn *fc = get_fuse_conn(inode);
        enum fuse_dax_mode dax_mode = fc->dax_mode;
@@ -1345,12 +1345,16 @@ static bool fuse_should_enable_dax(struct inode *inode)
        if (!fc->dax)
                return false;
 
-       return true;
+       if (dax_mode == FUSE_DAX_ALWAYS)
+               return true;
+
+       /* dax_mode is FUSE_DAX_INODE* */
+       return flags & FUSE_ATTR_DAX;
 }
 
-void fuse_dax_inode_init(struct inode *inode)
+void fuse_dax_inode_init(struct inode *inode, unsigned int flags)
 {
-       if (!fuse_should_enable_dax(inode))
+       if (!fuse_should_enable_dax(inode, flags))
                return;
 
        inode->i_flags |= S_DAX;

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index df81768c81a73efdaf7d1b46dc238686dfa12469..8290944517749161840a047d4416b43750b4c5bb 100644 (file)
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -3169,7 +3169,7 @@ static const struct address_space_operations fuse_file_aops  = {
        .write_end      = fuse_write_end,
 };
 
-void fuse_init_file_inode(struct inode *inode)
+void fuse_init_file_inode(struct inode *inode, unsigned int flags)
 {
        struct fuse_inode *fi = get_fuse_inode(inode);
 
@@ -3183,5 +3183,5 @@ void fuse_init_file_inode(struct inode *inode)
        fi->writepages = RB_ROOT;
 
        if (IS_ENABLED(CONFIG_FUSE_DAX))
-               fuse_dax_inode_init(inode);
+               fuse_dax_inode_init(inode, flags);
 }

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 8bf133109170204d83229c585c9774cceb8ff234..ccbc4de7870baeb3949772cb8cc5315dafb43120 100644 (file)
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1025,7 +1025,7 @@ int fuse_notify_poll_wakeup(struct fuse_conn *fc,
 /**
  * Initialize file operations on a regular file
  */
-void fuse_init_file_inode(struct inode *inode);
+void fuse_init_file_inode(struct inode *inode, unsigned int flags);
 
 /**
  * Initialize inode operations on regular files and special files
@@ -1291,7 +1291,7 @@ int fuse_dax_conn_alloc(struct fuse_conn *fc, enum fuse_dax_mode mode,
                        struct dax_device *dax_dev);
 void fuse_dax_conn_free(struct fuse_conn *fc);
 bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi);
-void fuse_dax_inode_init(struct inode *inode);
+void fuse_dax_inode_init(struct inode *inode, unsigned int flags);
 void fuse_dax_inode_cleanup(struct inode *inode);
 bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
 void fuse_dax_cancel_work(struct fuse_conn *fc);

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d83589ef11c034ad9d1adb26d394f20b7fdb6db0..dc6714350f2138329902950d5ae198bc286fd273 100644 (file)
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -313,7 +313,7 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
        inode->i_ctime.tv_nsec = attr->ctimensec;
        if (S_ISREG(inode->i_mode)) {
                fuse_init_common(inode);
-               fuse_init_file_inode(inode);
+               fuse_init_file_inode(inode, attr->flags);
        } else if (S_ISDIR(inode->i_mode))
                fuse_init_dir(inode);
        else if (S_ISLNK(inode->i_mode))