bisect: avoid copying ancestor list for non-merge commits
During a bisection, hg needs to compute a list of all ancestors for every
candidate commit. This is accomplished via a bottom-up traversal of the set of
candidates, during which each revision's ancestor list is populated using the
ancestor list of its parent(s). Previously, this involved copying the entire
list, which could be very long in if the bisection range was large.
To help improve this, we can observe that each candidate commit is visited
exactly once, at which point its ancestor list is copied into its children's
lists and then dropped. In the case of non-merge commits, a commit's ancestor
list consists exactly of its parent's list plus itself. This means that we can
trivially reuse the parent's existing list for one of its non-merge children,
which avoids copying entirely if that commit is the parent's only child. This
makes bisections over linear ranges of commits much faster.
During some informal testing in the large publicly-available `mozilla-central`
repository, this noticeably sped up bisections over large ranges of history:
Setup:
$ cd mozilla-central
$ hg bisect --reset
$ hg bisect --good 0
$ hg log -r tip -T '{rev}\n'
628417
Test:
$ time hg bisect --bad tip --noupdate
Before:
real 3m35.927s
user 3m35.553s
sys 0m0.319s
After:
real 1m41.142s
user 1m40.810s
sys 0m0.285s
# Tests to ensure that sha1dc.sha1 is exactly a drop-in for
# hashlib.sha1 for our needs.
import hashlib
import unittest
import silenttestrunner
try:
from mercurial.thirdparty import sha1dc
except ImportError:
sha1dc = None
class hashertestsbase:
def test_basic_hash(self):
h = self.hasher()
h.update(b'foo')
self.assertEqual(
'0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33', h.hexdigest()
)
h.update(b'bar')
self.assertEqual(
'8843d7f92416211de9ebb963ff4ce28125932878', h.hexdigest()
)
def test_copy_hasher(self):
h = self.hasher()
h.update(b'foo')
h2 = h.copy()
h.update(b'baz')
h2.update(b'bar')
self.assertEqual(
'21eb6533733a5e4763acacd1d45a60c2e0e404e1', h.hexdigest()
)
self.assertEqual(
'8843d7f92416211de9ebb963ff4ce28125932878', h2.hexdigest()
)
def test_init_hasher(self):
h = self.hasher(b'initial string')
self.assertEqual(
b'\xc9y|n\x1f3S\xa4:\xbaJ\xca,\xc1\x1a\x9e\xb8\xd8\xdd\x86',
h.digest(),
)
def test_bytes_like_types(self):
h = self.hasher()
h.update(bytearray(b'foo'))
h.update(memoryview(b'baz'))
self.assertEqual(
'21eb6533733a5e4763acacd1d45a60c2e0e404e1', h.hexdigest()
)
h = self.hasher(bytearray(b'foo'))
h.update(b'baz')
self.assertEqual(
'21eb6533733a5e4763acacd1d45a60c2e0e404e1', h.hexdigest()
)
h = self.hasher(memoryview(b'foo'))
h.update(b'baz')
self.assertEqual(
'21eb6533733a5e4763acacd1d45a60c2e0e404e1', h.hexdigest()
)
class hashlibtests(unittest.TestCase, hashertestsbase):
hasher = hashlib.sha1
if sha1dc:
class sha1dctests(unittest.TestCase, hashertestsbase):
hasher = sha1dc.sha1
if __name__ == '__main__':
silenttestrunner.main(__name__)