summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/scrub.c33
1 files changed, 28 insertions, 5 deletions
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 21de630b0730..fd266a2d15ec 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3577,17 +3577,27 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
* This can easily boost the amount of SYSTEM chunks if cleaner
* thread can't be triggered fast enough, and use up all space
* of btrfs_super_block::sys_chunk_array
+ *
+ * While for dev replace, we need to try our best to mark block
+ * group RO, to prevent race between:
+ * - Write duplication
+ * Contains latest data
+ * - Scrub copy
+ * Contains data from commit tree
+ *
+ * If target block group is not marked RO, nocow writes can
+ * be overwritten by scrub copy, causing data corruption.
+ * So for dev-replace, it's not allowed to continue if a block
+ * group is not RO.
*/
- ret = btrfs_inc_block_group_ro(cache, false);
- scrub_pause_off(fs_info);
-
+ ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace);
if (ret == 0) {
ro_set = 1;
- } else if (ret == -ENOSPC) {
+ } else if (ret == -ENOSPC && !sctx->is_dev_replace) {
/*
* btrfs_inc_block_group_ro return -ENOSPC when it
* failed in creating new chunk for metadata.
- * It is not a problem for scrub/replace, because
+ * It is not a problem for scrub, because
* metadata are always cowed, and our scrub paused
* commit_transactions.
*/
@@ -3596,9 +3606,22 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
btrfs_warn(fs_info,
"failed setting block group ro: %d", ret);
btrfs_put_block_group(cache);
+ scrub_pause_off(fs_info);
break;
}
+ /*
+ * Now the target block is marked RO, wait for nocow writes to
+ * finish before dev-replace.
+ * COW is fine, as COW never overwrites extents in commit tree.
+ */
+ if (sctx->is_dev_replace) {
+ btrfs_wait_nocow_writers(cache);
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start,
+ cache->length);
+ }
+
+ scrub_pause_off(fs_info);
down_write(&dev_replace->rwsem);
dev_replace->cursor_right = found_key.offset + length;
dev_replace->cursor_left = found_key.offset;