ext4: update writeback_index based on last page scanned

As pointed out in a prior patch, updating the mapping's
writeback_index based on pages written isn't quite right;
what the writeback index is really supposed to reflect is
the next page which should be scanned for writeback during
periodic flush.

As in write_cache_pages(), write_cache_pages_da() does
this scanning for us as we assemble the mpd for later
writeout.  If we keep track of the next page after the
current scan, we can easily update writeback_index without
worrying about pages written vs. pages skipped, etc.

Without this, an fsync will reset writeback_index to
0 (its starting index) + however many pages it wrote, which
can mess up the progress of periodic flush.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c9ea95b..45fc5bd 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2800,12 +2800,13 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
  */
 static int write_cache_pages_da(struct address_space *mapping,
                                struct writeback_control *wbc,
-                               struct mpage_da_data *mpd)
+                               struct mpage_da_data *mpd,
+                               pgoff_t *done_index)
 {
        int ret = 0;
        int done = 0;
        struct pagevec pvec;
-       int nr_pages;
+       unsigned nr_pages;
        pgoff_t index;
        pgoff_t end;            /* Inclusive */
        long nr_to_write = wbc->nr_to_write;
@@ -2820,6 +2821,7 @@ static int write_cache_pages_da(struct address_space *mapping,
        else
                tag = PAGECACHE_TAG_DIRTY;
 
+       *done_index = index;
        while (!done && (index <= end)) {
                int i;
 
@@ -2843,6 +2845,8 @@ static int write_cache_pages_da(struct address_space *mapping,
                                break;
                        }
 
+                       *done_index = page->index + 1;
+
                        lock_page(page);
 
                        /*
@@ -2928,6 +2932,7 @@ static int ext4_da_writepages(struct address_space *mapping,
        long desired_nr_to_write, nr_to_writebump = 0;
        loff_t range_start = wbc->range_start;
        struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+       pgoff_t done_index = 0;
        pgoff_t end;
 
        trace_ext4_da_writepages(inode, wbc);
@@ -3050,7 +3055,7 @@ retry:
                mpd.io_done = 0;
                mpd.pages_written = 0;
                mpd.retval = 0;
-               ret = write_cache_pages_da(mapping, wbc, &mpd);
+               ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index);
                /*
                 * If we have a contiguous extent of pages and we
                 * haven't done the I/O yet, map the blocks and submit
@@ -3104,14 +3109,13 @@ retry:
                         __func__, wbc->nr_to_write, ret);
 
        /* Update index */
-       index += pages_written;
        wbc->range_cyclic = range_cyclic;
        if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
                /*
                 * set the writeback_index so that range_cyclic
                 * mode will write it back later
                 */
-               mapping->writeback_index = index;
+               mapping->writeback_index = done_index;
 
 out_writepages:
        wbc->nr_to_write -= nr_to_writebump;