From 539f358a30d5113bad81c41a2e7ba8770d6c9f6e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 7 Oct 2013 13:42:57 +0300 Subject: [PATCH] Btrfs: fix the dev-replace suspend sequence Replace progresses strictly from lower to higher offsets, and the progress is tracked in chunks, by storing the physical offset of the dev_extent which is being copied in the cursor_left field of btrfs_dev_replace_item. When we are done copying the chunk, left_cursor is updated to point one byte past the dev_extent, so that on resume we can skip the dev_extents that have already been copied. There is a major bug (which goes all the way back to the inception of dev-replace in 3.8) in the way left_cursor is bumped: the bump is done unconditionally, without any regard to the scrub_chunk return value. On suspend (and also on any kind of error) scrub_chunk returns early, i.e. without completing the copy. This leads to us skipping the chunk that hasn't been fully copied yet when resuming. Fix this by doing the cursor_left update only if scrub_chunk ret is 0. (On suspend scrub_chunk returns with -ECANCELED, so this fix covers both suspend and error cases.) Cc: Stefan Behrens Signed-off-by: Ilya Dryomov Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/scrub.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a18e0e2..f21e2df 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2717,8 +2717,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, mutex_unlock(&fs_info->scrub_lock); wake_up(&fs_info->scrub_pause_wait); - dev_replace->cursor_left = dev_replace->cursor_right; - dev_replace->item_needs_writeback = 1; btrfs_put_block_group(cache); if (ret) break; @@ -2732,6 +2730,9 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, break; } + dev_replace->cursor_left = dev_replace->cursor_right; + dev_replace->item_needs_writeback = 1; + key.offset = found_key.offset + length; btrfs_release_path(path); } -- 2.7.4