revlog-split: make sure the self._indexfile attribut is reset (issue6811) stable 6.4.2
authorPierre-Yves David <pierre-yves.david@octobus.net>
Tue, 18 Apr 2023 01:23:27 +0200
branchstable
changeset 50348 f952be90b051
parent 50347 2bb2a1ff4d8f
child 50349 98ddff854d8a
revlog-split: make sure the self._indexfile attribut is reset (issue6811) Before this change, after a transaction committing a file split, a revlog object would have its `self._indexfile` attribute desynchronised from the actual file storing the data. If that same object is reused (as we do for the manifest during clone bundles), this lead to the data being writting in the wrong location and the repository to go corrupt. We not properly reset the attribut when applicable and everything is back in working order.
mercurial/revlog.py
tests/test-clonebundles.t
--- a/mercurial/revlog.py	Tue Apr 18 00:07:52 2023 +0200
+++ b/mercurial/revlog.py	Tue Apr 18 01:23:27 2023 +0200
@@ -19,6 +19,7 @@
 import io
 import os
 import struct
+import weakref
 import zlib
 
 # import stuff from node for others to import from revlog
@@ -2057,6 +2058,7 @@
             old_index_file_path = self._indexfile
             new_index_file_path = self._indexfile + b'.s'
             opener = self.opener
+            weak_self = weakref.ref(self)
 
             fncache = getattr(opener, 'fncache', None)
             if fncache is not None:
@@ -2069,13 +2071,22 @@
                     old_index_file_path,
                     checkambig=True,
                 )
+                maybe_self = weak_self()
+                if maybe_self is not None:
+                    maybe_self._indexfile = old_index_file_path
+
+            def abort_callback(tr):
+                maybe_self = weak_self()
+                if maybe_self is not None:
+                    maybe_self._indexfile = old_index_file_path
 
             tr.registertmp(new_index_file_path)
             if self.target[1] is not None:
-                finalize_id = b'000-revlog-split-%d-%s' % self.target
+                callback_id = b'000-revlog-split-%d-%s' % self.target
             else:
-                finalize_id = b'000-revlog-split-%d' % self.target[0]
-            tr.addfinalize(finalize_id, finalize_callback)
+                callback_id = b'000-revlog-split-%d' % self.target[0]
+            tr.addfinalize(callback_id, finalize_callback)
+            tr.addabort(callback_id, abort_callback)
 
         new_dfh = self._datafp(b'w+')
         new_dfh.truncate(0)  # drop any potentially existing data
--- a/tests/test-clonebundles.t	Tue Apr 18 00:07:52 2023 +0200
+++ b/tests/test-clonebundles.t	Tue Apr 18 01:23:27 2023 +0200
@@ -733,9 +733,7 @@
   $ cd revlog-split-in-the-bundle
   $ f --size .hg/store/00manifest.*
   .hg/store/00manifest.d: size=499037
-  .hg/store/00manifest.i: size=192 (missing-correct-output !)
-  .hg/store/00manifest.i: size=128 (known-bad-output !)
-  .hg/store/00manifest.i.s: size=64 (known-bad-output !)
+  .hg/store/00manifest.i: size=192
   $ f --size .hg/store/data/_a.*
   .hg/store/data/_a.d: size=588917
   .hg/store/data/_a.i: size=192
@@ -743,15 +741,11 @@
 manifest should work
 
   $ hg  files -r tip | wc -l
-  \s*10001 (re) (missing-correct-output !)
-  abort: 00manifest@4941afd6b8e298d932227572c5c303cbc14301bd: no node (known-bad-output !)
-  0 (known-bad-output !)
+  \s*10001 (re)
 
 file content should work
 
   $ hg  cat -r tip A | wc -l
-  \s*100001 (re) (missing-correct-output !)
-  abort: 00manifest@4941afd6b8e298d932227572c5c303cbc14301bd: no node (known-bad-output !)
-  0 (known-bad-output !)
+  \s*100001 (re)