Merge pull request #3274 from ThomasWaldmann/chunks-healthy-recreate-fix-1.1

recreate / chunks_healthy fixes (1.1-maint)

src/borg/archive.py

@@ -917,6 +917,10 @@ Utilization of max. archive size: {csize_max:.0%}
                 return chunk_entry
 
         item.chunks = []
+        # if we rechunkify, we'll get a fundamentally different chunks list, thus we need
+        # to get rid of .chunks_healthy, as it might not correspond to .chunks any more.
+        if getattr(self, 'recreate_rechunkify', False) and 'chunks_healthy' in item:
+            del item.chunks_healthy
         from_chunk = 0
         part_number = 1
         for data in chunk_iter:
@@ -1374,7 +1378,12 @@ class ArchiveChecker:
             has_chunks_healthy = 'chunks_healthy' in item
             chunks_current = item.chunks
             chunks_healthy = item.chunks_healthy if has_chunks_healthy else chunks_current
-            assert len(chunks_current) == len(chunks_healthy)
+            if has_chunks_healthy and len(chunks_current) != len(chunks_healthy):
+                # should never happen, but there was issue #3218.
+                logger.warning('{}: Invalid chunks_healthy metadata removed!'.format(item.path))
+                del item.chunks_healthy
+                has_chunks_healthy = False
+                chunks_healthy = chunks_current
             for chunk_current, chunk_healthy in zip(chunks_current, chunks_healthy):
                 chunk_id, size, csize = chunk_healthy
                 if chunk_id not in self.chunks:
@@ -1630,15 +1639,17 @@ class ArchiveRecreater:
             if not matcher.match(item.path):
                 self.print_file_status('x', item.path)
                 if item_is_hardlink_master(item):
-                    hardlink_masters[item.path] = (item.get('chunks'), None)
+                    hardlink_masters[item.path] = (item.get('chunks'), item.get('chunks_healthy'), None)
                 continue
             if target_is_subset and hardlinkable(item.mode) and item.get('source') in hardlink_masters:
                 # master of this hard link is outside the target subset
-                chunks, new_source = hardlink_masters[item.source]
+                chunks, chunks_healthy, new_source = hardlink_masters[item.source]
                 if new_source is None:
                     # First item to use this master, move the chunks
                     item.chunks = chunks
-                    hardlink_masters[item.source] = (None, item.path)
+                    if chunks_healthy is not None:
+                        item.chunks_healthy = chunks_healthy
+                    hardlink_masters[item.source] = (None, None, item.path)
                     del item.source
                 else:
                     # Master was already moved, only update this item's source

src/borg/archiver.py

@@ -3563,6 +3563,17 @@ class Archiver:
         deduplicated size of the archives using the previous chunker params.
         When recompressing expect approx. (throughput / checkpoint-interval) in space usage,
         assuming all chunks are recompressed.
+
+        If you recently ran borg check --repair and it had to fix lost chunks with all-zero
+        replacement chunks, please first run another backup for the same data and re-run
+        borg check --repair afterwards to heal any archives that had lost chunks which are
+        still generated from the input data.
+
+        Important: running borg recreate to re-chunk will remove the chunks_healthy
+        metadata of all items with replacement chunks, so healing will not be possible
+        any more after re-chunking (it is also unlikely it would ever work: due to the
+        change of chunking parameters, the missing chunk likely will never be seen again
+        even if you still have the data that produced it).
         """)
         subparser = subparsers.add_parser('recreate', parents=[common_parser], add_help=False,
                                           description=self.do_recreate.__doc__,