D1568: lfs: using workers in lfs prefetch

[wlis (Wojciech Lis)]

wlis created this revision.
Herald added a subscriber: mercurial-devel.
Herald added a reviewer: hg-reviewers.

REVISION SUMMARY
  This significantly speeds up lfs prefetch. With fast network we are
  seeing ~50% improvement of overall prefetch times
  Because of worker's API in posix we do lose finegrained progress update and only
  see progress when a file finished downloading.

TEST PLAN
  Run tests:
  ./run-tests.py -l test-lfs*
  ..s.
  Skipped test-lfs-test-server.t: missing feature: git-lfs test server
  
  Ran 3 tests, 1 skipped, 0 failed.
  =================================
  
  Run commands resulting in lfs prefetch e.g. hg sparse --enable-profile

REPOSITORY
  rHG Mercurial

REVISION DETAIL
  https://phab.mercurial-scm.org/D1568

AFFECTED FILES
  hgext/lfs/blobstore.py

CHANGE DETAILS

diff --git a/hgext/lfs/blobstore.py b/hgext/lfs/blobstore.py
--- a/hgext/lfs/blobstore.py
+++ b/hgext/lfs/blobstore.py
@@ -18,6 +18,7 @@
     url as urlmod,
     util,
     vfs as vfsmod,
+    worker,
 )
 
 # 64 bytes for SHA256
@@ -171,7 +172,7 @@
 
         return filteredobjects
 
-    def _basictransfer(self, obj, action, localstore, progress=None):
+    def _basictransfer(self, obj, action, localstore):
         """Download or upload a single object using basic transfer protocol
 
         obj: dict, an object description returned by batch API
@@ -189,7 +190,7 @@
         request = util.urlreq.request(href)
         if action == 'upload':
             # If uploading blobs, read data from local blobstore.
-            request.data = filewithprogress(localstore.vfs(oid), progress)
+            request.data = localstore.vfs(oid)
             request.get_method = lambda: 'PUT'
 
         for k, v in headers:
@@ -202,8 +203,6 @@
                 data = req.read(1048576)
                 if not data:
                     break
-                if action == 'download' and progress:
-                    progress(len(data))
                 response += data
         except util.urlerr.httperror as ex:
             raise LfsRemoteError(_('HTTP error: %s (oid=%s, action=%s)')
@@ -218,45 +217,51 @@
             raise error.ProgrammingError('invalid Git-LFS action: %s' % action)
 
         response = self._batchrequest(pointers, action)
-        prunningsize = [0]
         objects = self._extractobjects(response, pointers, action)
         total = sum(x.get('size', 0) for x in objects)
+        sizes = {}
+        for obj in objects:
+            sizes[obj.get('oid')] = obj.get('size', 0)
         topic = {'upload': _('lfs uploading'),
                  'download': _('lfs downloading')}[action]
         if self.ui.verbose and len(objects) > 1:
             self.ui.write(_('lfs: need to transfer %d objects (%s)\n')
                           % (len(objects), util.bytecount(total)))
         self.ui.progress(topic, 0, total=total)
-        def progress(size):
-            # advance progress bar by "size" bytes
-            prunningsize[0] += size
-            self.ui.progress(topic, prunningsize[0], total=total)
-        for obj in sorted(objects, key=lambda o: o.get('oid')):
-            objsize = obj.get('size', 0)
+        def transfer(chunk):
+            for obj in chunk:
+                objsize = obj.get('size', 0)
+                if self.ui.verbose:
+                    if action == 'download':
+                        msg = _('lfs: downloading %s (%s)\n')
+                    elif action == 'upload':
+                        msg = _('lfs: uploading %s (%s)\n')
+                    self.ui.write(msg % (obj.get('oid'),
+                                  util.bytecount(objsize)))
+                retry = self.retry
+                while True:
+                    try:
+                        self._basictransfer(obj, action, localstore)
+                        yield 1, obj.get('oid')
+                        break
+                    except Exception as ex:
+                        if retry > 0:
+                            if self.ui.verbose:
+                                self.ui.write(
+                                    _('lfs: failed: %r (remaining retry %d)\n')
+                                    % (ex, retry))
+                            retry -= 1
+                            continue
+                        raise
+
+        oids = worker.worker(self.ui, 0.1, transfer, (),
+                             sorted(objects, key=lambda o: o.get('oid')))
+        processed = 0
+        for _one, oid in oids:
+            processed += sizes[oid]
+            self.ui.progress(topic, processed, total=total)
             if self.ui.verbose:
-                if action == 'download':
-                    msg = _('lfs: downloading %s (%s)\n')
-                elif action == 'upload':
-                    msg = _('lfs: uploading %s (%s)\n')
-                self.ui.write(msg % (obj.get('oid'), util.bytecount(objsize)))
-            origrunningsize = prunningsize[0]
-            retry = self.retry
-            while True:
-                prunningsize[0] = origrunningsize
-                try:
-                    self._basictransfer(obj, action, localstore,
-                                        progress=progress)
-                    break
-                except Exception as ex:
-                    if retry > 0:
-                        if self.ui.verbose:
-                            self.ui.write(
-                                _('lfs: failed: %r (remaining retry %d)\n')
-                                % (ex, retry))
-                        retry -= 1
-                        continue
-                    raise
-
+                self.ui.write(_('lfs: processed: %s\n') % oid)
         self.ui.progress(topic, pos=None, total=total)
 
     def __del__(self):



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