D8193: nodemap: automatically "vacuum" the persistent nodemap when too sparse

[marmoute (Pierre-Yves David)]

marmoute updated this revision to Diff 20744.

REPOSITORY
  rHG Mercurial

CHANGES SINCE LAST UPDATE
  https://phab.mercurial-scm.org/D8193?vs=20688&id=20744

BRANCH
  default

CHANGES SINCE LAST ACTION
  https://phab.mercurial-scm.org/D8193/new/

REVISION DETAIL
  https://phab.mercurial-scm.org/D8193

AFFECTED FILES
  mercurial/configitems.py
  mercurial/revlogutils/nodemap.py
  tests/test-persistent-nodemap.t

CHANGE DETAILS

diff --git a/tests/test-persistent-nodemap.t b/tests/test-persistent-nodemap.t
--- a/tests/test-persistent-nodemap.t
+++ b/tests/test-persistent-nodemap.t
@@ -278,12 +278,12 @@
   tip-rev: 5002
   tip-node: 42bf3068c7ddfdfded53c4eb11d02266faeebfee
   data-length: 123456 (pure !)
-  data-length: 246464 (rust !)
+  data-length: 123008 (rust !)
   data-length: 123008 (no-pure no-rust !)
   data-unused: 448 (pure !)
-  data-unused: 123904 (rust !)
+  data-unused: 0 (rust !)
   data-unused: 0 (no-pure no-rust !)
-  data-unused: 50.273% (rust !)
+  data-unused: 0.000% (rust !)
   data-unused: 0.363% (pure !)
   data-unused: 0.000% (no-pure no-rust !)
 
diff --git a/mercurial/revlogutils/nodemap.py b/mercurial/revlogutils/nodemap.py
--- a/mercurial/revlogutils/nodemap.py
+++ b/mercurial/revlogutils/nodemap.py
@@ -143,13 +143,16 @@
             data_changed_count,
             data,
         ) = revlog.index.nodemap_data_incremental()
+        new_length = target_docket.data_length + len(data)
+        new_unused = target_docket.data_unused + data_changed_count
         if src_docket != target_docket:
             data = None
+        elif (new_length // new_unused) < 10:  # under 10% of unused data
+            data = None
         else:
             datafile = _rawdata_filepath(revlog, target_docket)
             # EXP-TODO: if this is a cache, this should use a cache vfs, not a
             # store vfs
-            new_length = target_docket.data_length + len(data)
             tr.add(datafile, target_docket.data_length)
             with revlog.opener(datafile, b'r+') as fd:
                 fd.seek(target_docket.data_length)
@@ -162,7 +165,7 @@
                         fd.flush()
                         new_data = util.buffer(util.mmapread(fd, new_length))
             target_docket.data_length = new_length
-            target_docket.data_unused += data_changed_count
+            target_docket.data_unused = new_unused
 
     if data is None:
         # otherwise fallback to a full new export
diff --git a/mercurial/configitems.py b/mercurial/configitems.py
--- a/mercurial/configitems.py
+++ b/mercurial/configitems.py
@@ -407,7 +407,6 @@
 )
 # TODO before getting `persistent-nodemap` out of experimental
 #
-# * regenerate a new nodemap when the unused/total ration is to high
 # * decide for a "status" of the persistent nodemap and associated location
 #   - part of the store next the revlog itself (new requirements)
 #   - part of the cache directory



To: marmoute, #hg-reviewers
Cc: mercurial-devel