diff hgext/lfs/blobstore.py @ 44085:0ee0a3f6a990

lfs: check content length after downloading content

Adapted from the Facebook repo[1].  The intent is to distinguish between the
connection dying and getting served a corrupt blob.

The original message:

HTTP makes no provision to tell your client that you failed halfway through
producing your response and won't have the answer they're looking for. So, if a
LFS server fails while producing a response, then we'll report an OID mismatch.

We can do a little better and disambiguate between "the server sent us the
wrong blob" (very scary) and "the server crashed" (merely annoying) by looking
at the content length of the response we got back. If it's not what was
advertised, we can reasonably safely assume the server crashed.

[1] https://github.com/facebookexperimental/eden/commit/2a4a6fab4e882ed89b948bfc1e7d56d7c3c99dd2

Differential Revision: https://phab.mercurial-scm.org/D7881

--- a/hgext/lfs/blobstore.py	Tue Jan 14 18:02:20 2020 -0500
+++ b/hgext/lfs/blobstore.py	Tue Jan 14 19:42:24 2020 -0500
@@ -155,15 +155,29 @@
 
         return self.vfs(oid, b'rb')
 
-    def download(self, oid, src):
+    def download(self, oid, src, content_length):
         """Read the blob from the remote source in chunks, verify the content,
         and write to this local blobstore."""
         sha256 = hashlib.sha256()
+        size = 0
 
         with self.vfs(oid, b'wb', atomictemp=True) as fp:
             for chunk in util.filechunkiter(src, size=1048576):
                 fp.write(chunk)
                 sha256.update(chunk)
+                size += len(chunk)
+
+            # If the server advertised a length longer than what we actually
+            # received, then we should expect that the server crashed while
+            # producing the response (but the server has no way of telling us
+            # that), and we really don't need to try to write the response to
+            # the localstore, because it's not going to match the expected.
+            if content_length is not None and int(content_length) != size:
+                msg = (
+                    b"Response length (%s) does not match Content-Length "
+                    b"header (%d): likely server-side crash"
+                )
+                raise LfsRemoteError(_(msg) % (size, int(content_length)))
 
             realoid = node.hex(sha256.digest())
             if realoid != oid:
@@ -492,6 +506,7 @@
         response = b''
         try:
             with contextlib.closing(self.urlopener.open(request)) as res:
+                contentlength = res.info().get(b"content-length")
                 ui = self.ui  # Shorten debug lines
                 if self.ui.debugflag:
                     ui.debug(b'Status: %d\n' % res.status)
@@ -503,7 +518,7 @@
                 if action == b'download':
                     # If downloading blobs, store downloaded data to local
                     # blobstore
-                    localstore.download(oid, res)
+                    localstore.download(oid, res, contentlength)
                 else:
                     while True:
                         data = res.read(1048576)
@@ -637,7 +652,7 @@
     def readbatch(self, pointers, tostore):
         for p in _deduplicate(pointers):
             with self.vfs(p.oid(), b'rb') as fp:
-                tostore.download(p.oid(), fp)
+                tostore.download(p.oid(), fp, None)
 
 
 class _nullremote(object):