In the append-write scenario, after ensuring that the dirty inode can be
seen by the writeback process, there is no need to execute
"mark_inode_dirty" for every write. Instead, we can rely on
"ext4_mark_inode_dirty" executed when updating i_disksize in
"mpage_map_and_submit_extent" to ensure data consistency, which can
significantly improve performance in high-frequency append-write
scenarios.
In test scenarios of Kafka version 2.6.2, using packet size of 2K
resulted in a 10% performance improvement.
Signed-off-by: Liu Song <liusong@xxxxxxxxxxxxxxxxx>
---
fs/ext4/inode.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 56 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9d9f414f99fe..d1aa775c9936 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3128,6 +3128,57 @@ static int ext4_da_should_update_i_disksize(struct page *page,
return 1;
}
+/*
+ * Copy from generic_write_end, add conditions to execute mark_inode_dirty
+ * to avoid additional overhead caused by frequent dirty inode operations
+ */
+static int ext4_da_generic_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied, bool need_dirty,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = mapping->host;
+ loff_t old_size = inode->i_size;
+ bool i_size_changed = false;
+ int was_dirty;
+
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+ /*
+ * No need to use i_size_read() here, the i_size cannot change under us
+ * because we hold i_rwsem.
+ *
+ * But it's important to update i_size while still holding page lock:
+ * page writeout could otherwise come in and zero beyond i_size.
+ */
+ if (pos + copied > inode->i_size) {
+ i_size_write(inode, pos + copied);
+ i_size_changed = true;
+ }
+
+ unlock_page(page);
+ put_page(page);
+
+ if (old_size < pos)
+ pagecache_isize_extended(inode, old_size, pos);
+
+ /*
+ * In the append-write scenario, if the inode is marked as dirty,
+ * it is ensured that the inode will be seen by the writeback process.
+ * In the ext4_writepages process, when updating i_disksize,
+ * corresponding metadata updates are also performed.
+ * Therefore, it is unnecessary to repeatedly execute mark_inode_dirty
+ * to improve performance.
+ */
+ if (i_size_changed) {
+ spin_lock(&inode->i_lock);
+ was_dirty = inode->i_state & I_DIRTY;
+ spin_unlock(&inode->i_lock);
+ if (!was_dirty || need_dirty)
+ mark_inode_dirty(inode);
+ }
+ return copied;
+}
+
static int ext4_da_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
@@ -3137,6 +3188,7 @@ static int ext4_da_write_end(struct file *file,
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
+ bool need_dirty = false;
if (write_mode == FALL_BACK_TO_NONDELALLOC)
return ext4_write_end(file, mapping, pos,
@@ -3169,10 +3221,12 @@ static int ext4_da_write_end(struct file *file,
*/
new_i_size = pos + copied;
if (copied && new_i_size > inode->i_size &&
- ext4_da_should_update_i_disksize(page, end))
+ ext4_da_should_update_i_disksize(page, end)) {
ext4_update_i_disksize(inode, new_i_size);
+ need_dirty = true;
+ }
- return generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+ return ext4_da_generic_write_end(file, mapping, pos, len, copied, need_dirty, page, fsdata);
}
/*
--
2.19.1.6.gb485710b
