get rid of chunks_healthy when rechunking, fixes #3218

src/borg/archive.py

@@ -967,13 +967,14 @@ class ChunksProcessor:
 
     def __init__(self, *, key, cache,
                  add_item, write_checkpoint,
-                 checkpoint_interval):
+                 checkpoint_interval, rechunkify):
         self.key = key
         self.cache = cache
         self.add_item = add_item
         self.write_checkpoint = write_checkpoint
         self.checkpoint_interval = checkpoint_interval
         self.last_checkpoint = time.monotonic()
+        self.rechunkify = rechunkify
 
     def write_part_file(self, item, from_chunk, number):
         item = Item(internal_dict=item.as_dict())
@@ -998,6 +999,10 @@ class ChunksProcessor:
                 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 self.rechunkify and 'chunks_healthy' in item:
+            del item.chunks_healthy
         from_chunk = 0
         part_number = 1
         for data in chunk_iter:
@@ -1891,7 +1896,7 @@ class ArchiveRecreater:
         target.process_file_chunks = ChunksProcessor(
             cache=self.cache, key=self.key,
             add_item=target.add_item, write_checkpoint=target.write_checkpoint,
-            checkpoint_interval=self.checkpoint_interval).process_file_chunks
+            checkpoint_interval=self.checkpoint_interval, rechunkify=target.recreate_rechunkify).process_file_chunks
         target.chunker = Chunker(self.key.chunk_seed, *target.chunker_params)
         return target
 

src/borg/archiver.py

@@ -519,7 +519,7 @@ class Archiver:
                     nobsdflags=args.nobsdflags, numeric_owner=args.numeric_owner)
                 cp = ChunksProcessor(cache=cache, key=key,
                     add_item=archive.add_item, write_checkpoint=archive.write_checkpoint,
-                    checkpoint_interval=args.checkpoint_interval)
+                    checkpoint_interval=args.checkpoint_interval, rechunkify=False)
                 fso = FilesystemObjectProcessors(metadata_collector=metadata_collector, cache=cache, key=key,
                     process_file_chunks=cp.process_file_chunks, add_item=archive.add_item,
                     chunker_params=args.chunker_params)
@@ -3371,6 +3371,17 @@ 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__,