restructure changelog file appending

- make appending code proper part of changelog with delayupdate/finalize
- use simplified appender that tracks pending data in memory
- eliminate old appendfile and helper classes
- update addchangegroup to use new interface and reuse the existing changelog

mercurial/changelog.py

@@ -26,10 +26,89 b' def _string_escape(text):'
 def _string_unescape(text):
     return text.decode('string_escape')
 
+class appender:
+    '''the changelog index must be update last on disk, so we use this class
+    to delay writes to it'''
+    def __init__(self, fp, buf):
+        self.data = buf
+        self.fp = fp
+        self.offset = fp.tell()
+        self.size = util.fstat(fp).st_size
+
+    def end(self):
+        return self.size + len("".join(self.data))
+    def tell(self):
+        return self.offset
+    def flush(self):
+        pass
+    def close(self):
+        close(self.fp)
+
+    def seek(self, offset, whence=0):
+        '''virtual file offset spans real file and data'''
+        if whence == 0:
+            self.offset = offset
+        elif whence == 1:
+            self.offset += offset
+        elif whence == 2:
+            self.offset = self.end() + offset
+        if self.offset < self.size:
+            self.fp.seek(self.offset)
+
+    def read(self, count=-1):
+        '''only trick here is reads that span real file and data'''
+        ret = ""
+        old_offset = self.offset
+        if self.offset < self.size:
+            s = self.fp.read(count)
+            ret = s
+            self.offset += len(s)
+            if count > 0:
+                count -= len(s)
+        if count != 0:
+            doff = self.offset - self.size
+            self.data.insert(0, "".join(self.data))
+            del self.data[1:]
+            s = self.data[0][doff:doff+count]
+            self.offset += len(s)
+            ret += s
+        return ret
+
+    def write(self, s):
+        self.data.append(s)
+        self.offset += len(s)
+
 class changelog(revlog):
     def __init__(self, opener):
         revlog.__init__(self, opener, "00changelog.i")
 
+    def delayupdate(self):
+        "delay visibility of index updates to other readers"
+        self._realopener = self.opener
+        self.opener = self._appendopener
+        self._delaybuf = []
+
+    def finalize(self, tr):
+        "finalize index updates"
+        self.opener = self._realopener
+        if self._delaybuf:
+            fp = self.opener(self.indexfile, 'a')
+            fp.write("".join(self._delaybuf))
+            fp.close()
+            del self._delaybuf
+        self.checkinlinesize(tr)
+
+    def _appendopener(self, name, mode='r'):
+        fp = self._realopener(name, mode)
+        if not name == self.indexfile:
+            return fp
+        return appender(fp, self._delaybuf)
+
+    def checkinlinesize(self, tr, fp=None):
+        if self.opener == self._appendopener:
+            return
+        return revlog.checkinlinesize(self, tr, fp)
+
     def decode_extra(self, text):
         extra = {}
         for l in text.split('\0'):

mercurial/localrepo.py

@@ -7,7 +7,7 b''
 
 from node import *
 from i18n import _
-import repo, appendfile, changegroup
+import repo, changegroup
 import changelog, dirstate, filelog, manifest, context
 import re, lock, transaction, tempfile, stat, mdiff, errno, ui
 import os, revlog, time, util
@@ -1782,52 +1782,45 b' class localrepository(repo.repository):'
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
-        cl = None
-        try:
-            cl = appendfile.appendchangelog(self.sopener)
-            oldheads = len(cl.heads())
+        cl = self.changelog
+        cl.delayupdate()
+        oldheads = len(cl.heads())
+
+        # pull off the changeset group
+        self.ui.status(_("adding changesets\n"))
+        cor = cl.count() - 1
+        chunkiter = changegroup.chunkiter(source)
+        if cl.addgroup(chunkiter, csmap, tr, 1) is None:
+            raise util.Abort(_("received changelog group is empty"))
+        cnr = cl.count() - 1
+        changesets = cnr - cor
 
-            # pull off the changeset group
-            self.ui.status(_("adding changesets\n"))
-            cor = cl.count() - 1
-            chunkiter = changegroup.chunkiter(source)
-            if cl.addgroup(chunkiter, csmap, tr, 1) is None:
-                raise util.Abort(_("received changelog group is empty"))
-            cnr = cl.count() - 1
-            changesets = cnr - cor
+        # pull off the manifest group
+        self.ui.status(_("adding manifests\n"))
+        chunkiter = changegroup.chunkiter(source)
+        # no need to check for empty manifest group here:
+        # if the result of the merge of 1 and 2 is the same in 3 and 4,
+        # no new manifest will be created and the manifest group will
+        # be empty during the pull
+        self.manifest.addgroup(chunkiter, revmap, tr)
 
-            # pull off the manifest group
-            self.ui.status(_("adding manifests\n"))
+        # process the files
+        self.ui.status(_("adding file changes\n"))
+        while 1:
+            f = changegroup.getchunk(source)
+            if not f:
+                break
+            self.ui.debug(_("adding %s revisions\n") % f)
+            fl = self.file(f)
+            o = fl.count()
             chunkiter = changegroup.chunkiter(source)
-            # no need to check for empty manifest group here:
-            # if the result of the merge of 1 and 2 is the same in 3 and 4,
-            # no new manifest will be created and the manifest group will
-            # be empty during the pull
-            self.manifest.addgroup(chunkiter, revmap, tr)
-
-            # process the files
-            self.ui.status(_("adding file changes\n"))
-            while 1:
-                f = changegroup.getchunk(source)
-                if not f:
-                    break
-                self.ui.debug(_("adding %s revisions\n") % f)
-                fl = self.file(f)
-                o = fl.count()
-                chunkiter = changegroup.chunkiter(source)
-                if fl.addgroup(chunkiter, revmap, tr) is None:
-                    raise util.Abort(_("received file revlog group is empty"))
-                revisions += fl.count() - o
-                files += 1
-
-            cl.writedata()
-        finally:
-            if cl:
-                cl.cleanup()
+            if fl.addgroup(chunkiter, revmap, tr) is None:
+                raise util.Abort(_("received file revlog group is empty"))
+            revisions += fl.count() - o
+            files += 1
 
         # make changelog see real files again
-        self.changelog = changelog.changelog(self.sopener)
-        self.changelog.checkinlinesize(tr)
+        cl.finalize(tr)
 
         newheads = len(self.changelog.heads())
         heads = ""