phases: rework the logic of _pushdiscoveryphase to bound complexity
This rework the various graph traversal in _pushdiscoveryphase to keep the
complexity in check.
This is done though a couple of things:
- first, limiting the space we have to explore, for example, if we are not in
publishing push, we don't need to consider remote draft roots that are also
draft locally, as there is nothing to be moved there.
- avoid unbounded descendant computation, and use the faster "rev between"
computation.
This provide a massive boost to performance when exchanging with repository with
a massive amount of draft, like mozilla-try:
### 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: 20.346590 seconds
after: 11.232059 seconds (-38.15%, -7.48 seconds)
## benchmark.variants.revs = any-100-extra-rev
before: 24.752051 seconds
after: 15.367412 seconds (-37.91%, -9.38 seconds)
After this changes, the push operation is still quite too slow. Some of this
can be attributed to general phases slowness (reading all the roots from disk
for example) and other know slowness (not using persistent-nodemap, branchmap,
tags, etc. We are also working on them, but with this series, phase discovery
during push no longer showing up in profile and this is a pretty nice and bit
low-hanging fruit out of the way.
### (same case as the above)
# benchmark.variants.revs = any-1-extra-rev
pre-%ln-change: 44.235070
this-changeset: 11.232059 seconds (-74.61%, -33.00 seconds)
# benchmark.variants.revs = any-100-extra-rev
pre-%ln-change: 49.234697
this-changeset: 15.367412 seconds (-68.79%, -33.87 seconds)
Note that with this change, the `hg push` performance is now much closer to the
`hg pull` performance, even it still lagging behind a bit. (and the overall
performance are still too slow).
### data-env-vars.name = mozilla-try-2023-03-22-ds2-pnm
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.pulled-delta-reuse-policy = default
# bin-env-vars.hg.flavor = rust
## benchmark.variants.revs = any-1-extra-rev
hg.command.pull: 6.517450
hg.command.push: 11.219888
## benchmark.variants.revs = any-100-extra-rev
hg.command.pull: 10.160991
hg.command.push: 14.251107
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# 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.pulled-delta-reuse-policy = default
## bin-env-vars.hg.flavor = default
## benchmark.variants.revs = any-1-extra-rev
hg.command.pull: 8.577772
hg.command.push: 11.232059
## bin-env-vars.hg.flavor = default
## benchmark.variants.revs = any-100-extra-rev
hg.command.pull: 13.152976
hg.command.push: 15.367412
## bin-env-vars.hg.flavor = rust
## benchmark.variants.revs = any-1-extra-rev
hg.command.pull: 8.731982
hg.command.push: 11.178751
## bin-env-vars.hg.flavor = rust
## benchmark.variants.revs = any-100-extra-rev
hg.command.pull: 13.184236
hg.command.push: 15.620843
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__)