revset: stop serializing node when using "%ln"
Turning hundred of thousand of node from node to hex and back can be slow… what
about we stop doing it?
In many case were we are using node id we should be using revision id. However
this is not a good reason to have a stupidly slow implementation of "%ln".
This caught my attention again because the phase discovery during push make an
extensive use of "%ln" or huge set. In absolute, that phase discovery probably
should use "%ld" and need to improves its algorithmic complexity, but improving
"%ln" seems simple and long overdue. This greatly speeds up `hg push` on
repository with many drafts.
Here are some relevant poulpe benchmarks:
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = default
## benchmark.variants.revs = any-1-extra-rev
before: 44.235070
after: 20.416329 (-53.85%, -23.82)
## benchmark.variants.revs = any-100-extra-rev
before: 49.234697
after: 26.519829 (-46.14%, -22.71)
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 10.138396
after: 7.750458 (-23.55%, -2.39)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 1.263859
after: 0.700229 (-44.60%, -0.56)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 399.484481
after: 346.5089 (-13.26%, -52.98)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 4.540080
after: 3.401700 (-25.07%, -1.14)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 2.975765
after: 1.870798 (-37.13%, -1.10)
import unittest
from mercurial import (
util,
wireprotoframing as framing,
)
ffs = framing.makeframefromhumanstring
class FrameHumanStringTests(unittest.TestCase):
def testbasic(self):
self.assertEqual(
ffs(b'1 1 0 1 0 '), b'\x00\x00\x00\x01\x00\x01\x00\x10'
)
self.assertEqual(
ffs(b'2 4 0 1 0 '), b'\x00\x00\x00\x02\x00\x04\x00\x10'
)
self.assertEqual(
ffs(b'2 4 0 1 0 foo'), b'\x03\x00\x00\x02\x00\x04\x00\x10foo'
)
def testcborint(self):
self.assertEqual(
ffs(b'1 1 0 1 0 cbor:15'), b'\x01\x00\x00\x01\x00\x01\x00\x10\x0f'
)
self.assertEqual(
ffs(b'1 1 0 1 0 cbor:42'), b'\x02\x00\x00\x01\x00\x01\x00\x10\x18*'
)
self.assertEqual(
ffs(b'1 1 0 1 0 cbor:1048576'),
b'\x05\x00\x00\x01\x00\x01\x00\x10\x1a' b'\x00\x10\x00\x00',
)
self.assertEqual(
ffs(b'1 1 0 1 0 cbor:0'), b'\x01\x00\x00\x01\x00\x01\x00\x10\x00'
)
self.assertEqual(
ffs(b'1 1 0 1 0 cbor:-1'), b'\x01\x00\x00\x01\x00\x01\x00\x10 '
)
self.assertEqual(
ffs(b'1 1 0 1 0 cbor:-342542'),
b'\x05\x00\x00\x01\x00\x01\x00\x10:\x00\x05:\r',
)
def testcborstrings(self):
self.assertEqual(
ffs(b"1 1 0 1 0 cbor:b'foo'"),
b'\x04\x00\x00\x01\x00\x01\x00\x10Cfoo',
)
def testcborlists(self):
self.assertEqual(
ffs(b"1 1 0 1 0 cbor:[None, True, False, 42, b'foo']"),
b'\n\x00\x00\x01\x00\x01\x00\x10\x85\xf6\xf5\xf4' b'\x18*Cfoo',
)
def testcbordicts(self):
self.assertEqual(
ffs(b"1 1 0 1 0 " b"cbor:{b'foo': b'val1', b'bar': b'val2'}"),
b'\x13\x00\x00\x01\x00\x01\x00\x10\xa2' b'CbarDval2CfooDval1',
)
class FrameTests(unittest.TestCase):
def testdataexactframesize(self):
data = util.bytesio(b'x' * framing.DEFAULT_MAX_FRAME_SIZE)
stream = framing.stream(1)
frames = list(
framing.createcommandframes(stream, 1, b'command', {}, data)
)
self.assertEqual(
frames,
[
ffs(
b'1 1 stream-begin command-request new|have-data '
b"cbor:{b'name': b'command'}"
),
ffs(b'1 1 0 command-data continuation %s' % data.getvalue()),
ffs(b'1 1 0 command-data eos '),
],
)
def testdatamultipleframes(self):
data = util.bytesio(b'x' * (framing.DEFAULT_MAX_FRAME_SIZE + 1))
stream = framing.stream(1)
frames = list(
framing.createcommandframes(stream, 1, b'command', {}, data)
)
self.assertEqual(
frames,
[
ffs(
b'1 1 stream-begin command-request new|have-data '
b"cbor:{b'name': b'command'}"
),
ffs(
b'1 1 0 command-data continuation %s'
% (b'x' * framing.DEFAULT_MAX_FRAME_SIZE)
),
ffs(b'1 1 0 command-data eos x'),
],
)
def testargsanddata(self):
data = util.bytesio(b'x' * 100)
stream = framing.stream(1)
frames = list(
framing.createcommandframes(
stream,
1,
b'command',
{
b'key1': b'key1value',
b'key2': b'key2value',
b'key3': b'key3value',
},
data,
)
)
self.assertEqual(
frames,
[
ffs(
b'1 1 stream-begin command-request new|have-data '
b"cbor:{b'name': b'command', b'args': {b'key1': b'key1value', "
b"b'key2': b'key2value', b'key3': b'key3value'}}"
),
ffs(b'1 1 0 command-data eos %s' % data.getvalue()),
],
)
if not getattr(unittest.TestCase, 'assertRaisesRegex', False):
# Python 3.7 deprecates the regex*p* version, but 2.7 lacks
# the regex version.
assertRaisesRegex = ( # camelcase-required
unittest.TestCase.assertRaisesRegexp
)
def testtextoutputformattingstringtype(self):
"""Formatting string must be bytes."""
with self.assertRaisesRegex(ValueError, 'must use bytes formatting '):
list(
framing.createtextoutputframe(
None, 1, [(b'foo'.decode('ascii'), [], [])]
)
)
def testtextoutputargumentbytes(self):
with self.assertRaisesRegex(ValueError, 'must use bytes for argument'):
list(
framing.createtextoutputframe(
None, 1, [(b'foo', [b'foo'.decode('ascii')], [])]
)
)
def testtextoutputlabelbytes(self):
with self.assertRaisesRegex(ValueError, 'must use bytes for labels'):
list(
framing.createtextoutputframe(
None, 1, [(b'foo', [], [b'foo'.decode('ascii')])]
)
)
def testtextoutput1simpleatom(self):
stream = framing.stream(1)
val = list(framing.createtextoutputframe(stream, 1, [(b'foo', [], [])]))
self.assertEqual(
val,
[
ffs(
b'1 1 stream-begin text-output 0 '
b"cbor:[{b'msg': b'foo'}]"
),
],
)
def testtextoutput2simpleatoms(self):
stream = framing.stream(1)
val = list(
framing.createtextoutputframe(
stream,
1,
[
(b'foo', [], []),
(b'bar', [], []),
],
)
)
self.assertEqual(
val,
[
ffs(
b'1 1 stream-begin text-output 0 '
b"cbor:[{b'msg': b'foo'}, {b'msg': b'bar'}]"
)
],
)
def testtextoutput1arg(self):
stream = framing.stream(1)
val = list(
framing.createtextoutputframe(
stream,
1,
[
(b'foo %s', [b'val1'], []),
],
)
)
self.assertEqual(
val,
[
ffs(
b'1 1 stream-begin text-output 0 '
b"cbor:[{b'msg': b'foo %s', b'args': [b'val1']}]"
)
],
)
def testtextoutput2arg(self):
stream = framing.stream(1)
val = list(
framing.createtextoutputframe(
stream,
1,
[
(b'foo %s %s', [b'val', b'value'], []),
],
)
)
self.assertEqual(
val,
[
ffs(
b'1 1 stream-begin text-output 0 '
b"cbor:[{b'msg': b'foo %s %s', b'args': [b'val', b'value']}]"
)
],
)
def testtextoutput1label(self):
stream = framing.stream(1)
val = list(
framing.createtextoutputframe(
stream,
1,
[
(b'foo', [], [b'label']),
],
)
)
self.assertEqual(
val,
[
ffs(
b'1 1 stream-begin text-output 0 '
b"cbor:[{b'msg': b'foo', b'labels': [b'label']}]"
)
],
)
def testargandlabel(self):
stream = framing.stream(1)
val = list(
framing.createtextoutputframe(
stream,
1,
[
(b'foo %s', [b'arg'], [b'label']),
],
)
)
self.assertEqual(
val,
[
ffs(
b'1 1 stream-begin text-output 0 '
b"cbor:[{b'msg': b'foo %s', b'args': [b'arg'], "
b"b'labels': [b'label']}]"
)
],
)
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)