view tests/test-remotefilelog-histpack.py @ 41247:a89b20a49c13

rust-cpython: using MissingAncestors from Python code As precedently done with LazyAncestors on cpython.rs, we test for the presence of the 'rustext' module. incrementalmissingrevs() has two callers within the Mercurial core: `setdiscovery.partialdiscovery` and the `only()` revset. This move shows a significant discovery performance improvement in cases where the baseline is slow: using perfdiscovery on the PyPy repos, prepared with `contrib/discovery-helper <repo> 50 100`, we get averaged medians of 403ms with the Rust version vs 742ms without (about 45% better). But there are still indications that performance can be worse in cases the baseline is fast, possibly due to the conversion from Python to Rust and back becoming the bottleneck. We could measure this on mozilla-central in cases were the delta is just a few changesets. This requires confirmation, but if that's the reason, then an upcoming `partialdiscovery` fully in Rust should solve the problem. Differential Revision: https://phab.mercurial-scm.org/D5551
author Georges Racinet <georges.racinet@octobus.net>
date Fri, 30 Nov 2018 14:35:57 +0100
parents ba706e3082bd
children 878084a495ef
line wrap: on
line source

#!/usr/bin/env python
from __future__ import absolute_import

import hashlib
import os
import random
import shutil
import stat
import struct
import sys
import tempfile
import unittest

import silenttestrunner

from mercurial.node import nullid
from mercurial import (
    pycompat,
    ui as uimod,
)
# Load the local remotefilelog, not the system one
sys.path[0:0] = [os.path.join(os.path.dirname(__file__), '..')]
from hgext.remotefilelog import (
    basepack,
    historypack,
)

class histpacktests(unittest.TestCase):
    def setUp(self):
        self.tempdirs = []

    def tearDown(self):
        for d in self.tempdirs:
            shutil.rmtree(d)

    def makeTempDir(self):
        tempdir = tempfile.mkdtemp()
        self.tempdirs.append(tempdir)
        return pycompat.fsencode(tempdir)

    def getHash(self, content):
        return hashlib.sha1(content).digest()

    def getFakeHash(self):
        return b''.join(pycompat.bytechr(random.randint(0, 255))
                        for _ in range(20))

    def createPack(self, revisions=None):
        """Creates and returns a historypack containing the specified revisions.

        `revisions` is a list of tuples, where each tuple contains a filanem,
        node, p1node, p2node, and linknode.
        """
        if revisions is None:
            revisions = [("filename", self.getFakeHash(), nullid, nullid,
                          self.getFakeHash(), None)]

        packdir = pycompat.fsencode(self.makeTempDir())
        packer = historypack.mutablehistorypack(uimod.ui(), packdir,
                                                version=2)

        for filename, node, p1, p2, linknode, copyfrom in revisions:
            packer.add(filename, node, p1, p2, linknode, copyfrom)

        path = packer.close()
        return historypack.historypack(path)

    def testAddSingle(self):
        """Test putting a single entry into a pack and reading it out.
        """
        filename = "foo"
        node = self.getFakeHash()
        p1 = self.getFakeHash()
        p2 = self.getFakeHash()
        linknode = self.getFakeHash()

        revisions = [(filename, node, p1, p2, linknode, None)]
        pack = self.createPack(revisions)

        actual = pack.getancestors(filename, node)[node]
        self.assertEquals(p1, actual[0])
        self.assertEquals(p2, actual[1])
        self.assertEquals(linknode, actual[2])

    def testAddMultiple(self):
        """Test putting multiple unrelated revisions into a pack and reading
        them out.
        """
        revisions = []
        for i in range(10):
            filename = "foo-%s" % i
            node = self.getFakeHash()
            p1 = self.getFakeHash()
            p2 = self.getFakeHash()
            linknode = self.getFakeHash()
            revisions.append((filename, node, p1, p2, linknode, None))

        pack = self.createPack(revisions)

        for filename, node, p1, p2, linknode, copyfrom in revisions:
            actual = pack.getancestors(filename, node)[node]
            self.assertEquals(p1, actual[0])
            self.assertEquals(p2, actual[1])
            self.assertEquals(linknode, actual[2])
            self.assertEquals(copyfrom, actual[3])

    def testAddAncestorChain(self):
        """Test putting multiple revisions in into a pack and read the ancestor
        chain.
        """
        revisions = []
        filename = b"foo"
        lastnode = nullid
        for i in range(10):
            node = self.getFakeHash()
            revisions.append((filename, node, lastnode, nullid, nullid, None))
            lastnode = node

        # revisions must be added in topological order, newest first
        revisions = list(reversed(revisions))
        pack = self.createPack(revisions)

        # Test that the chain has all the entries
        ancestors = pack.getancestors(revisions[0][0], revisions[0][1])
        for filename, node, p1, p2, linknode, copyfrom in revisions:
            ap1, ap2, alinknode, acopyfrom = ancestors[node]
            self.assertEquals(ap1, p1)
            self.assertEquals(ap2, p2)
            self.assertEquals(alinknode, linknode)
            self.assertEquals(acopyfrom, copyfrom)

    def testPackMany(self):
        """Pack many related and unrelated ancestors.
        """
        # Build a random pack file
        allentries = {}
        ancestorcounts = {}
        revisions = []
        random.seed(0)
        for i in range(100):
            filename = b"filename-%d" % i
            entries = []
            p2 = nullid
            linknode = nullid
            for j in range(random.randint(1, 100)):
                node = self.getFakeHash()
                p1 = nullid
                if len(entries) > 0:
                    p1 = entries[random.randint(0, len(entries) - 1)]
                entries.append(node)
                revisions.append((filename, node, p1, p2, linknode, None))
                allentries[(filename, node)] = (p1, p2, linknode)
                if p1 == nullid:
                    ancestorcounts[(filename, node)] = 1
                else:
                    newcount = ancestorcounts[(filename, p1)] + 1
                    ancestorcounts[(filename, node)] = newcount

        # Must add file entries in reverse topological order
        revisions = list(reversed(revisions))
        pack = self.createPack(revisions)

        # Verify the pack contents
        for (filename, node), (p1, p2, lastnode) in allentries.items():
            ancestors = pack.getancestors(filename, node)
            self.assertEquals(ancestorcounts[(filename, node)],
                              len(ancestors))
            for anode, (ap1, ap2, alinknode, copyfrom) in ancestors.items():
                ep1, ep2, elinknode = allentries[(filename, anode)]
                self.assertEquals(ap1, ep1)
                self.assertEquals(ap2, ep2)
                self.assertEquals(alinknode, elinknode)
                self.assertEquals(copyfrom, None)

    def testGetNodeInfo(self):
        revisions = []
        filename = b"foo"
        lastnode = nullid
        for i in range(10):
            node = self.getFakeHash()
            revisions.append((filename, node, lastnode, nullid, nullid, None))
            lastnode = node

        pack = self.createPack(revisions)

        # Test that getnodeinfo returns the expected results
        for filename, node, p1, p2, linknode, copyfrom in revisions:
            ap1, ap2, alinknode, acopyfrom = pack.getnodeinfo(filename, node)
            self.assertEquals(ap1, p1)
            self.assertEquals(ap2, p2)
            self.assertEquals(alinknode, linknode)
            self.assertEquals(acopyfrom, copyfrom)

    def testGetMissing(self):
        """Test the getmissing() api.
        """
        revisions = []
        filename = b"foo"
        for i in range(10):
            node = self.getFakeHash()
            p1 = self.getFakeHash()
            p2 = self.getFakeHash()
            linknode = self.getFakeHash()
            revisions.append((filename, node, p1, p2, linknode, None))

        pack = self.createPack(revisions)

        missing = pack.getmissing([(filename, revisions[0][1])])
        self.assertFalse(missing)

        missing = pack.getmissing([(filename, revisions[0][1]),
                                   (filename, revisions[1][1])])
        self.assertFalse(missing)

        fakenode = self.getFakeHash()
        missing = pack.getmissing([(filename, revisions[0][1]),
                                   (filename, fakenode)])
        self.assertEquals(missing, [(filename, fakenode)])

        # Test getmissing on a non-existant filename
        missing = pack.getmissing([("bar", fakenode)])
        self.assertEquals(missing, [("bar", fakenode)])

    def testAddThrows(self):
        pack = self.createPack()

        try:
            pack.add(b'filename', nullid, nullid, nullid, nullid, None)
            self.assertTrue(False, "historypack.add should throw")
        except RuntimeError:
            pass

    def testBadVersionThrows(self):
        pack = self.createPack()
        path = pack.path + '.histpack'
        with open(path) as f:
            raw = f.read()
        raw = struct.pack('!B', 255) + raw[1:]
        os.chmod(path, os.stat(path).st_mode | stat.S_IWRITE)
        with open(path, 'w+') as f:
            f.write(raw)

        try:
            pack = historypack.historypack(pack.path)
            self.assertTrue(False, "bad version number should have thrown")
        except RuntimeError:
            pass

    def testLargePack(self):
        """Test creating and reading from a large pack with over X entries.
        This causes it to use a 2^16 fanout table instead."""
        total = basepack.SMALLFANOUTCUTOFF + 1
        revisions = []
        for i in pycompat.xrange(total):
            filename = b"foo-%d" % i
            node = self.getFakeHash()
            p1 = self.getFakeHash()
            p2 = self.getFakeHash()
            linknode = self.getFakeHash()
            revisions.append((filename, node, p1, p2, linknode, None))

        pack = self.createPack(revisions)
        self.assertEquals(pack.params.fanoutprefix, basepack.LARGEFANOUTPREFIX)

        for filename, node, p1, p2, linknode, copyfrom in revisions:
            actual = pack.getancestors(filename, node)[node]
            self.assertEquals(p1, actual[0])
            self.assertEquals(p2, actual[1])
            self.assertEquals(linknode, actual[2])
            self.assertEquals(copyfrom, actual[3])
# TODO:
# histpack store:
# - repack two packs into one

if __name__ == '__main__':
    silenttestrunner.main(__name__)