changeset 29218:fd288d118074

largefiles: send statlfile remote calls only for nonexisting locally files

Files that are already in local store should be checked locally. The problem
with this implementation is how difference in messages between local and remote
checks should look like. For now local errors for file missing and content
corrupted looks like this:

'changeset cset: filename references missing storepath\n'
'changeset cset: filename references corrupted storepath\n'

for remote it looks like:

'changeset cset: filename missing\n'
'changeset cset: filename: contents differ\n'

Contents differ error for remote calls is never raised currently - for now
statlfile implementation lacks checking file content.

--- a/hgext/largefiles/remotestore.py	Mon May 16 21:18:59 2016 +0000
+++ b/hgext/largefiles/remotestore.py	Mon May 09 10:05:32 2016 +0200
@@ -14,11 +14,13 @@
 
 import lfutil
 import basestore
+import localstore
 
 class remotestore(basestore.basestore):
     '''a largefile store accessed over a network'''
     def __init__(self, ui, repo, url):
         super(remotestore, self).__init__(ui, repo, url)
+        self._lstore = localstore.localstore(self.ui, self.repo, self.repo)
 
     def put(self, source, hash):
         if self.sendfile(source, hash):
@@ -65,27 +67,42 @@
 
         return lfutil.copyandhash(chunks, tmpfile)
 
+    def _hashesavailablelocally(self, hashes):
+        existslocallymap = self._lstore.exists(hashes)
+        localhashes = [hash for hash in hashes if existslocallymap[hash]]
+        return localhashes
+
     def _verifyfiles(self, contents, filestocheck):
         failed = False
         expectedhashes = [expectedhash
                           for cset, filename, expectedhash in filestocheck]
-        stats = self._stat(expectedhashes)
+        localhashes = self._hashesavailablelocally(expectedhashes)
+        stats = self._stat([expectedhash for expectedhash in expectedhashes
+                            if expectedhash not in localhashes])
+
         for cset, filename, expectedhash in filestocheck:
-            stat = stats[expectedhash]
-            if stat:
-                if stat == 1:
-                    self.ui.warn(
-                        _('changeset %s: %s: contents differ\n')
-                        % (cset, filename))
+            if expectedhash in localhashes:
+                filetocheck = (cset, filename, expectedhash)
+                verifyresult = self._lstore._verifyfiles(contents,
+                                                         [filetocheck])
+                if verifyresult:
                     failed = True
-                elif stat == 2:
-                    self.ui.warn(
-                        _('changeset %s: %s missing\n')
-                        % (cset, filename))
-                    failed = True
-                else:
-                    raise RuntimeError('verify failed: unexpected response '
-                                       'from statlfile (%r)' % stat)
+            else:
+                stat = stats[expectedhash]
+                if stat:
+                    if stat == 1:
+                        self.ui.warn(
+                            _('changeset %s: %s: contents differ\n')
+                            % (cset, filename))
+                        failed = True
+                    elif stat == 2:
+                        self.ui.warn(
+                            _('changeset %s: %s missing\n')
+                            % (cset, filename))
+                        failed = True
+                    else:
+                        raise RuntimeError('verify failed: unexpected response '
+                                           'from statlfile (%r)' % stat)
         return failed
 
     def batch(self):

--- a/tests/test-largefiles-wireproto.t	Mon May 16 21:18:59 2016 +0000
+++ b/tests/test-largefiles-wireproto.t	Mon May 09 10:05:32 2016 +0200
@@ -324,27 +324,59 @@
   $ hg serve -R batchverifymain -d -p $HGPORT --pid-file hg.pid \
   > -A access.log
   $ cat hg.pid >> $DAEMON_PIDS
-  $ hg clone http://localhost:$HGPORT batchverifyclone
+  $ hg clone --noupdate http://localhost:$HGPORT batchverifyclone
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 2 changes to 2 files
-  updating to branch default
-  getting changed largefiles
-  2 largefiles updated, 0 removed
-  2 files updated, 0 files merged, 0 files removed, 0 files unresolved
-  $ hg -R batchverifyclone verify --large
+  $ hg -R batchverifyclone verify --large --lfa
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   2 files, 2 changesets, 2 total revisions
-  searching 1 changesets for largefiles
+  searching 2 changesets for largefiles
   verified existence of 2 revisions of 2 largefiles
   $ tail -1 access.log
   127.0.0.1 - - [*] "GET /?cmd=batch HTTP/1.1" 200 - x-hgarg-1:cmds=statlfile+sha%3D972a1a11f19934401291cc99117ec614933374ce%3Bstatlfile+sha%3Dc801c9cfe94400963fcb683246217d5db77f9a9a (glob)
-  $ rm access.log
+  $ hg -R batchverifyclone update
+  getting changed largefiles
+  2 largefiles updated, 0 removed
+  2 files updated, 0 files merged, 0 files removed, 0 files unresolved
+
+Clear log file before next test
+
+  $ printf "" > access.log
+
+Verify should check file on remote server only when file is not
+available locally.
+
+  $ echo "ccc" >> batchverifymain/c
+  $ hg -R batchverifymain status
+  ? c
+  $ hg -R batchverifymain add --large batchverifymain/c
+  $ hg -R batchverifymain commit -m "c"
+  Invoking status precommit hook
+  A c
+  $ hg -R batchverifyclone pull
+  pulling from http://localhost:$HGPORT/
+  searching for changes
+  adding changesets
+  adding manifests
+  adding file changes
+  added 1 changesets with 1 changes to 1 files
+  (run 'hg update' to get a working copy)
+  $ hg -R batchverifyclone verify --lfa
+  checking changesets
+  checking manifests
+  crosschecking files in changesets and manifests
+  checking files
+  3 files, 3 changesets, 3 total revisions
+  searching 3 changesets for largefiles
+  verified existence of 3 revisions of 3 largefiles
+  $ tail -1 access.log
+  127.0.0.1 - - [*] "GET /?cmd=batch HTTP/1.1" 200 - x-hgarg-1:cmds=statlfile+sha%3Dc8559c3c9cfb42131794b7d8009230403b9b454c (glob)
 
   $ killdaemons.py