Rev 3876: Don't optimize btree indexes that are just spillover. in http://bzr.arbash-meinel.com/branches/bzr/brisbane/hack3

[John Arbash Meinel]

At http://bzr.arbash-meinel.com/branches/bzr/brisbane/hack3

------------------------------------------------------------
revno: 3876
revision-id: john at arbash-meinel.com-20090319183945-2gia2u0k0lhzcu7n
parent: john at arbash-meinel.com-20090319183849-b0kcdjhn0god2srn
committer: John Arbash Meinel <john at arbash-meinel.com>
branch nick: hack3
timestamp: Thu 2009-03-19 13:39:45 -0500
message:
  Don't optimize btree indexes that are just spillover.
-------------- next part --------------
=== modified file 'bzrlib/btree_index.py'
--- a/bzrlib/btree_index.py	2009-02-18 05:40:39 +0000
+++ b/bzrlib/btree_index.py	2009-03-19 18:39:45 +0000
@@ -189,7 +189,8 @@
             iterators_to_combine.append(backing.iter_all_entries())
         backing_pos = pos + 1
         new_backing_file, size = \
-            self._write_nodes(self._iter_smallest(iterators_to_combine))
+            self._write_nodes(self._iter_smallest(iterators_to_combine),
+                              allow_optimize=False)
         dir_path, base_name = osutils.split(new_backing_file.name)
         # Note: The transport here isn't strictly needed, because we will use
         #       direct access to the new_backing._file object
@@ -262,11 +263,14 @@
             except StopIteration:
                 current_values[pos] = None
 
-    def _add_key(self, string_key, line, rows):
+    def _add_key(self, string_key, line, rows, allow_optimize=True):
         """Add a key to the current chunk.
 
         :param string_key: The key to add.
         :param line: The fully serialised key and value.
+        :param allow_optimize: If set to False, prevent setting the optimize
+            flag when writing out. This is used by the _spill_mem_keys_to_disk
+            functionality.
         """
         if rows[-1].writer is None:
             # opening a new leaf chunk;
@@ -277,8 +281,12 @@
                     length = _PAGE_SIZE
                     if internal_row.nodes == 0:
                         length -= _RESERVED_HEADER_BYTES # padded
+                    if allow_optimize:
+                        optimize_for_size = self._optimize_for_size
+                    else:
+                        optimize_for_size = False
                     internal_row.writer = chunk_writer.ChunkWriter(length, 0,
-                        optimize_for_size=self._optimize_for_size)
+                        optimize_for_size=optimize_for_size)
                     internal_row.writer.write(_INTERNAL_FLAG)
                     internal_row.writer.write(_INTERNAL_OFFSET +
                         str(rows[pos + 1].nodes) + "\n")
@@ -322,13 +330,16 @@
                 new_row.writer.write(_INTERNAL_OFFSET +
                     str(rows[1].nodes - 1) + "\n")
                 new_row.writer.write(key_line)
-            self._add_key(string_key, line, rows)
+            self._add_key(string_key, line, rows, allow_optimize=allow_optimize)
 
-    def _write_nodes(self, node_iterator):
+    def _write_nodes(self, node_iterator, allow_optimize=True):
         """Write node_iterator out as a B+Tree.
 
         :param node_iterator: An iterator of sorted nodes. Each node should
             match the output given by iter_all_entries.
+        :param allow_optimize: If set to False, prevent setting the optimize
+            flag when writing out. This is used by the _spill_mem_keys_to_disk
+            functionality.
         :return: A file handle for a temporary file containing a B+Tree for
             the nodes.
         """
@@ -353,7 +364,7 @@
             key_count += 1
             string_key, line = _btree_serializer._flatten_node(node,
                                     self.reference_lists)
-            self._add_key(string_key, line, rows)
+            self._add_key(string_key, line, rows, allow_optimize=allow_optimize)
         for row in reversed(rows):
             pad = (type(row) != _LeafBuilderRow)
             row.finish_node(pad=pad)