Patchwork D7894: nodemap: introduce an option to use mmap to read the nodemap mapping

login
register
mail settings
Submitter phabricator
Date Feb. 11, 2020, 12:03 p.m.
Message ID <079453de61e34438507e38e9ee0bb12e@localhost.localdomain>
Download mbox | patch
Permalink /patch/45184/
State Not Applicable
Headers show

Comments

phabricator - Feb. 11, 2020, 12:03 p.m.
Herald added a reviewer: indygreg.
marmoute updated this revision to Diff 20165.

REPOSITORY
  rHG Mercurial

CHANGES SINCE LAST UPDATE
  https://phab.mercurial-scm.org/D7894?vs=20018&id=20165

CHANGES SINCE LAST ACTION
  https://phab.mercurial-scm.org/D7894/new/

REVISION DETAIL
  https://phab.mercurial-scm.org/D7894

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

CHANGE DETAILS




To: marmoute, #hg-reviewers, durin42, indygreg
Cc: durin42, gracinet, martinvonz, mercurial-devel

Patch

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
@@ -84,3 +84,37 @@ 
   $ hg debugnodemap --check
   revision in index:   5002
   revision in nodemap: 5002
+
+Test code path without mmap
+---------------------------
+
+  $ echo bar > bar
+  $ hg add bar
+  $ hg ci -m 'bar' --config experimental.exp-persistent-nodemap.mmap=no
+
+  $ hg debugnodemap --check --config experimental.exp-persistent-nodemap.mmap=yes
+  revision in index:   5003
+  revision in nodemap: 5003
+  $ hg debugnodemap --check --config experimental.exp-persistent-nodemap.mmap=no
+  revision in index:   5003
+  revision in nodemap: 5003
+
+
+#if pure
+  $ hg debugnodemap --metadata
+  uid: ???????????????? (glob)
+  tip-rev: 5002
+  data-length: 123328
+  data-unused: 384
+  $ f --sha256 .hg/store/00changelog-*.nd --size
+  .hg/store/00changelog-????????????????.nd: size=123328, sha256=10d26e9776b6596af0f89143a54eba8cc581e929c38242a02a7b0760698c6c70 (glob)
+
+#else
+  $ hg debugnodemap --metadata
+  uid: ???????????????? (glob)
+  tip-rev: 5002
+  data-length: 122944
+  data-unused: 0
+  $ f --sha256 .hg/store/00changelog-*.nd --size
+  .hg/store/00changelog-????????????????.nd: size=122944, sha256=755976b22b64ab680401b45395953504e64e7fa8c31ac570f58dee21e15f9bc0 (glob)
+#endif
diff --git a/mercurial/revlogutils/nodemap.py b/mercurial/revlogutils/nodemap.py
--- a/mercurial/revlogutils/nodemap.py
+++ b/mercurial/revlogutils/nodemap.py
@@ -8,6 +8,7 @@ 
 
 from __future__ import absolute_import
 
+import errno
 import os
 import re
 import struct
@@ -45,11 +46,18 @@ 
     docket.data_unused = data_unused
 
     filename = _rawdata_filepath(revlog, docket)
-    data = revlog.opener.tryread(filename)
+    use_mmap = revlog.opener.options.get("exp-persistent-nodemap.mmap")
+    try:
+        with revlog.opener(filename) as fd:
+            if use_mmap:
+                data = util.buffer(util.mmapread(fd, data_length))
+            else:
+                data = fd.read(data_length)
+    except OSError as e:
+        if e.errno != errno.ENOENT:
+            raise
     if len(data) < data_length:
         return None
-    elif len(data) > data_length:
-        data = data[:data_length]
     return docket, data
 
 
@@ -81,6 +89,8 @@ 
 
     can_incremental = util.safehasattr(revlog.index, "nodemap_data_incremental")
     ondisk_docket = revlog._nodemap_docket
+    feed_data = util.safehasattr(revlog.index, "update_nodemap_data")
+    use_mmap = revlog.opener.options.get("exp-persistent-nodemap.mmap")
 
     data = None
     # first attemp an incremental update of the data
@@ -97,12 +107,18 @@ 
             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)
             with revlog.opener(datafile, b'r+') as fd:
                 fd.seek(target_docket.data_length)
                 fd.write(data)
-                fd.seek(0)
-                new_data = fd.read(target_docket.data_length + len(data))
-            target_docket.data_length += len(data)
+                if feed_data:
+                    if use_mmap:
+                        fd.seek(0)
+                        new_data = fd.read(new_length)
+                    else:
+                        fd.flush()
+                        new_data = util.buffer(util.mmapread(fd, new_length))
+            target_docket.data_length = new_length
             target_docket.data_unused += data_changed_count
 
     if data is None:
@@ -115,9 +131,14 @@ 
             data = persistent_data(revlog.index)
         # EXP-TODO: if this is a cache, this should use a cache vfs, not a
         # store vfs
-        new_data = data
-        with revlog.opener(datafile, b'w') as fd:
+        with revlog.opener(datafile, b'w+') as fd:
             fd.write(data)
+            if feed_data:
+                if use_mmap:
+                    new_data = data
+                else:
+                    fd.flush()
+                    new_data = util.buffer(util.mmapread(fd, len(data)))
         target_docket.data_length = len(data)
     target_docket.tip_rev = revlog.tiprev()
     # EXP-TODO: if this is a cache, this should use a cache vfs, not a
@@ -125,7 +146,7 @@ 
     with revlog.opener(revlog.nodemap_file, b'w', atomictemp=True) as fp:
         fp.write(target_docket.serialize())
     revlog._nodemap_docket = target_docket
-    if util.safehasattr(revlog.index, "update_nodemap_data"):
+    if feed_data:
         revlog.index.update_nodemap_data(target_docket, new_data)
 
     # EXP-TODO: if the transaction abort, we should remove the new data and
diff --git a/mercurial/revlog.py b/mercurial/revlog.py
--- a/mercurial/revlog.py
+++ b/mercurial/revlog.py
@@ -545,9 +545,6 @@ 
         indexdata = b''
         self._initempty = True
         try:
-            nodemap_data = nodemaputil.persisted_data(self)
-            if nodemap_data is not None:
-                self._nodemap_docket = nodemap_data[0]
             with self._indexfp() as f:
                 if (
                     mmapindexthreshold is not None
@@ -639,6 +636,7 @@ 
             if use_nodemap:
                 nodemap_data = nodemaputil.persisted_data(self)
                 if nodemap_data is not None:
+                    self._nodemap_docket = nodemap_data[0]
                     index.update_nodemap_data(*nodemap_data)
         except (ValueError, IndexError):
             raise error.RevlogError(
diff --git a/mercurial/localrepo.py b/mercurial/localrepo.py
--- a/mercurial/localrepo.py
+++ b/mercurial/localrepo.py
@@ -934,6 +934,8 @@ 
         options[b'rust.index'] = True
     if ui.configbool(b'experimental', b'exp-persistent-nodemap'):
         options[b'exp-persistent-nodemap'] = True
+    if ui.configbool(b'experimental', b'exp-persistent-nodemap.mmap'):
+        options[b'exp-persistent-nodemap.mmap'] = True
     if ui.configbool(b'devel', b'persistent-nodemap'):
         options[b'devel-force-nodemap'] = True
 
diff --git a/mercurial/debugcommands.py b/mercurial/debugcommands.py
--- a/mercurial/debugcommands.py
+++ b/mercurial/debugcommands.py
@@ -2122,7 +2122,7 @@ 
         nm_data = nodemap.persisted_data(cl)
         if nm_data is not None:
             docket, data = nm_data
-            ui.write(data)
+            ui.write(data[:])
     elif opts['check']:
         unfi = repo.unfiltered()
         cl = unfi.changelog
diff --git a/mercurial/configitems.py b/mercurial/configitems.py
--- a/mercurial/configitems.py
+++ b/mercurial/configitems.py
@@ -666,6 +666,9 @@ 
     b'experimental', b'exp-persistent-nodemap', default=False,
 )
 coreconfigitem(
+    b'experimental', b'exp-persistent-nodemap.mmap', default=True,
+)
+coreconfigitem(
     b'experimental', b'server.filesdata.recommended-batch-size', default=50000,
 )
 coreconfigitem(