| Message ID | 20230724132701.816771-3-hch@lst.de (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [1/9] btrfs: don't stop integrity writeback too early | expand |
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 231e620e6c497d..1cc46bbbd888cd 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2075,6 +2075,12 @@ static int extent_write_cache_pages(struct address_space *mapping, continue; } + if (!folio_test_dirty(folio)) { + /* someone wrote it for us */ + folio_unlock(folio); + continue; + } + if (wbc->sync_mode != WB_SYNC_NONE) { if (folio_test_writeback(folio)) submit_write_bio(bio_ctrl, 0);
__extent_writepage can have started on more pages than the one it was called for. This happens regularly for zoned file systems, and in theory could happen for compressed I/O if the worker thread was executed very quicky. For such pages extent_write_cache_pages waits for writeback to complete before moving on to the next page, which is highly inefficient as it blocks the flusher thread Port over the PageDirty check that was added to write_cache_pages in commit 515f4a037fb ("mm: write_cache_pages optimise page cleaning") to fix this. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Josef Bacik <josef@toxicpanda.com> --- fs/btrfs/extent_io.c | 6 ++++++ 1 file changed, 6 insertions(+)