ext4: Speedup WB_SYNC_ALL pass called from sync(2)

When doing filesystem wide sync, there's no need to force transaction
commit (or synchronously write inode buffer) separately for each inode
because ext4_sync_fs() takes care of forcing commit at the end (VFS
takes care of flushing buffer cache, respectively). Most of the time
this slowness doesn't manifest because previous WB_SYNC_NONE writeback
doesn't leave much to write but when there are processes aggressively
creating new files and several filesystems to sync, the sync slowness
can be noticeable. In the following test script sync(1) takes around 6
minutes when there are two ext4 filesystems mounted on a standard SATA
drive. After this patch sync takes a couple of seconds so we have about
two orders of magnitude improvement.

      function run_writers
      {
        for (( i = 0; i < 10; i++ )); do
          mkdir $1/dir$i
          for (( j = 0; j < 40000; j++ )); do
            dd if=/dev/zero of=$1/dir$i/$j bs=4k count=4 &>/dev/null
          done &
        done
      }

      for dir in "$@"; do
        run_writers $dir
      done

      sleep 40
      time sync

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5324a38d848d0fdb8a9e5de2be6c1b02c75d9375..ab3e8357929d35fedb779e964d41f02ceb862297 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4455,7 +4455,12 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
                        return -EIO;
                }
 
-               if (wbc->sync_mode != WB_SYNC_ALL)
+               /*
+                * No need to force transaction in WB_SYNC_NONE mode. Also
+                * ext4_sync_fs() will force the commit after everything is
+                * written.
+                */
+               if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
                        return 0;
 
                err = ext4_force_commit(inode->i_sb);
@@ -4465,7 +4470,11 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
                err = __ext4_get_inode_loc(inode, &iloc, 0);
                if (err)
                        return err;
-               if (wbc->sync_mode == WB_SYNC_ALL)
+               /*
+                * sync(2) will flush the whole buffer cache. No need to do
+                * it here separately for each inode.
+                */
+               if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
                        sync_dirty_buffer(iloc.bh);
                if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
                        EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,