mercurial/filelog.py
author Mads Kiilerich <madski@unity3d.com>
Mon, 28 Jan 2013 15:19:44 +0100
branchstable
changeset 18488 a977b42df8b3
parent 14287 7c231754a621
child 19148 3bda242bf244
permissions -rw-r--r--
largefiles: don't verify largefile hashes on servers when processing statlfile When changesets referencing largefiles are pushed then the corresponding largefiles will be pushed too - unless the target already has them. The client will use statlfile to make sure it only sends largefiles that the target doesn't have. The server would however on every statlfile check that the content of the largefile had the expected hash. What should be cheap thus became an expensive operation that trashed the disk and the cache. Largefile hashes are already checked by putlfile before being stored on the server. A server should thus be able to keep its largefile store free of errors - even more than it can keep revlogs free of errors. Verification should happen when running 'hg verify' locally on the server. Rehashing every largefile on every remote stat is too expensive. Clients will also stat lfiles before downloading them. When the server verified the hash in stat it meant that it had to read the file twice to serve it. With this change the server will assume its own hashes are ok without checking them on every statlfile. Some consequences of this change: - in case of server side corruption the problem will be detected by the existing check on the client side - not on server side - clients that could upload an uncorrupted largefile when pushing will no longer magically heal the server (and break hardlinks) - a client will now only upload its uncorrupted files after the corrupted file has been removed on the server side - client side verify will no longer report corruption in files it doesn't have (Issue3123 discussed related problems - and how they have been fixed.)

# filelog.py - file history class for mercurial
#
# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import revlog
import re

_mdre = re.compile('\1\n')
def _parsemeta(text):
    """return (metadatadict, keylist, metadatasize)"""
    # text can be buffer, so we can't use .startswith or .index
    if text[:2] != '\1\n':
        return None, None, None
    s = _mdre.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    keys = []
    for l in mtext.splitlines():
        k, v = l.split(": ", 1)
        meta[k] = v
        keys.append(k)
    return meta, keys, (s + 2)

def _packmeta(meta, keys=None):
    if not keys:
        keys = sorted(meta.iterkeys())
    return "".join("%s: %s\n" % (k, meta[k]) for k in keys)

class filelog(revlog.revlog):
    def __init__(self, opener, path):
        revlog.revlog.__init__(self, opener,
                        "/".join(("data", path + ".i")))

    def read(self, node):
        t = self.revision(node)
        if not t.startswith('\1\n'):
            return t
        s = t.index('\1\n', 2)
        return t[s + 2:]

    def add(self, text, meta, transaction, link, p1=None, p2=None):
        if meta or text.startswith('\1\n'):
            text = "\1\n%s\1\n%s" % (_packmeta(meta), text)
        return self.addrevision(text, transaction, link, p1, p2)

    def renamed(self, node):
        if self.parents(node)[0] != revlog.nullid:
            return False
        t = self.revision(node)
        m = _parsemeta(t)[0]
        if m and "copy" in m:
            return (m["copy"], revlog.bin(m["copyrev"]))
        return False

    def size(self, rev):
        """return the size of a given revision"""

        # for revisions with renames, we have to go the slow way
        node = self.node(rev)
        if self.renamed(node):
            return len(self.read(node))

        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
        return revlog.revlog.size(self, rev)

    def cmp(self, node, text):
        """compare text with a given file revision

        returns True if text is different than what is stored.
        """

        t = text
        if text.startswith('\1\n'):
            t = '\1\n\1\n' + text

        samehashes = not revlog.revlog.cmp(self, node, t)
        if samehashes:
            return False

        # renaming a file produces a different hash, even if the data
        # remains unchanged. Check if it's the case (slow):
        if self.renamed(node):
            t2 = self.read(node)
            return t2 != text

        return True

    def _file(self, f):
        return filelog(self.opener, f)