##// END OF EJS Templates
branchmap-v3: filter topo heads using node for performance reason...
branchmap-v3: filter topo heads using node for performance reason The branchmap currently contains heads as nodeid. If we build a set of revnum with the topological heads, we need to turn the nodeid in the branchmap to revnum to be able to check if they are topo-heads. That nodeid → revnum lookup is "expensive" and adds up to something noticeable if you do it hundreds of thousand of time. Instead we turn all the topo-heads revnums into nodes and build a set. So we can directly test membership of the nodeids stored in the branchmap. That is much faster. Ideally we would have revnum in the branchmap and could directly test revnum against a revnum set and that would be even faster. However that's an adventure for another time. Without this change, the branchmap format "v3" was significantly slower than the "v2" format. With this changes, some of that gap is recovered With rust + persistent nodemap, this overhead was smaller because the extra lookup did not had to to build the nodemap from scratch. In addition the mozilla-unified repository is able to use the "pure_top" mode of branchmap v3, so it was not really affected by this. Future changeset will work of the remaining of the performance gap. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.380994 (+63.02%, +0.15) branch-v3 after: 0.368769 (+57.79%, +0.14) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.385060 (+63.70%, +0.15) branch-v3 after: 0.372460 (+58.34%, +0.14) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.317524 (+24.23%, +0.06) branch-v3 after: 0.318907 (+24.78%, +0.06) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.410007 (+20.94%, +0.07) branch-v3 after: 0.349752 (+3.17%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.410428 (+18.44%, +0.06) branch-v3 after: 0.354300 (+2.24%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.393871 (+3.60%, +0.01) branch-v3 after: 0.396293 (+4.23%, +0.02) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.438105 (+6.29%, +0.03) branch-v3 after: 0.424769 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.438405 (+6.31%, +0.03) branch-v3 after: 0.421796 (+2.28%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.452692 (+5.40%, +0.02) branch-v3 after: 0.443849 (+3.34%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.562345 (+92.83%, +3.16) branch-v3 after: 6.234055 (+83.18%, +2.83) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.160248 (+78.31%, +2.71) branch-v3 after: 6.307813 (+82.58%, +2.85) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.381648 (+55.30%, +1.92) branch-v3 after: 5.176076 (+49.36%, +1.71)

File last commit:

r52827:09f3a679 default
r52869:41b8892a default
Show More
bdiff.py
104 lines | 2.8 KiB | text/x-python | PythonLexer
Yuya Nishihara
cffi: split modules from pure...
r32512 # bdiff.py - CFFI implementation of bdiff.c
#
# Copyright 2016 Maciej Fijalkowski <fijall@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
Matt Harbison
typing: add `from __future__ import annotations` to most files...
r52756 from __future__ import annotations
Yuya Nishihara
cffi: split modules from pure...
r32512
import struct
Matt Harbison
interfaces: add the optional `bdiff.xdiffblocks()` method...
r52827 import typing
Yuya Nishihara
cffi: split modules from pure...
r32512
Matt Harbison
typing: add type hints to bdiff implementations...
r50493 from typing import (
List,
Matt Harbison
interfaces: add the optional `bdiff.xdiffblocks()` method...
r52827 Optional,
Matt Harbison
typing: add type hints to bdiff implementations...
r50493 Tuple,
)
Yuya Nishihara
cffi: split modules from pure...
r32512 from ..pure.bdiff import *
Matt Harbison
interfaces: add the optional `bdiff.xdiffblocks()` method...
r52827
from ..interfaces import (
modules as intmod,
)
Matt Harbison
typing: disable import error warnings that are already handled...
r47543 from . import _bdiff # pytype: disable=import-error
Yuya Nishihara
cffi: split modules from pure...
r32512
ffi = _bdiff.ffi
lib = _bdiff.lib
Augie Fackler
formatting: blacken the codebase...
r43346
Matt Harbison
typing: add type hints to bdiff implementations...
r50493 def blocks(sa: bytes, sb: bytes) -> List[Tuple[int, int, int, int]]:
Manuel Jacob
cffi: pass C type and attribute names as str instead of bytes
r52683 a = ffi.new("struct bdiff_line**")
b = ffi.new("struct bdiff_line**")
Manuel Jacob
cffi: pass bytes instead of str to ffi.new("char[]", …)...
r52685 ac = ffi.new("char[]", bytes(sa))
bc = ffi.new("char[]", bytes(sb))
Manuel Jacob
cffi: pass C type and attribute names as str instead of bytes
r52683 l = ffi.new("struct bdiff_hunk*")
Yuya Nishihara
cffi: remove superfluous "if True" blocks
r32513 try:
an = lib.bdiff_splitlines(ac, len(sa), a)
bn = lib.bdiff_splitlines(bc, len(sb), b)
if not a[0] or not b[0]:
raise MemoryError
count = lib.bdiff_diff(a[0], an, b[0], bn, l)
if count < 0:
raise MemoryError
Matt Harbison
cffi: adjust the list returned by bdiff.blocks to never have a None entry...
r50492 rl = [(0, 0, 0, 0)] * count
Yuya Nishihara
cffi: remove superfluous "if True" blocks
r32513 h = l.next
i = 0
while h:
rl[i] = (h.a1, h.a2, h.b1, h.b2)
h = h.next
i += 1
finally:
lib.free(a[0])
lib.free(b[0])
lib.bdiff_freehunks(l.next)
return rl
Yuya Nishihara
cffi: split modules from pure...
r32512
Augie Fackler
formatting: blacken the codebase...
r43346
Matt Harbison
typing: add type hints to bdiff implementations...
r50493 def bdiff(sa: bytes, sb: bytes) -> bytes:
Manuel Jacob
cffi: pass C type and attribute names as str instead of bytes
r52683 a = ffi.new("struct bdiff_line**")
b = ffi.new("struct bdiff_line**")
Manuel Jacob
cffi: pass bytes instead of str to ffi.new("char[]", …)...
r52685 ac = ffi.new("char[]", bytes(sa))
bc = ffi.new("char[]", bytes(sb))
Manuel Jacob
cffi: pass C type and attribute names as str instead of bytes
r52683 l = ffi.new("struct bdiff_hunk*")
Yuya Nishihara
cffi: remove superfluous "if True" blocks
r32513 try:
an = lib.bdiff_splitlines(ac, len(sa), a)
bn = lib.bdiff_splitlines(bc, len(sb), b)
if not a[0] or not b[0]:
raise MemoryError
count = lib.bdiff_diff(a[0], an, b[0], bn, l)
if count < 0:
raise MemoryError
rl = []
h = l.next
la = lb = 0
while h:
if h.a1 != la or h.b1 != lb:
lgt = (b[0] + h.b1).l - (b[0] + lb).l
Augie Fackler
formatting: blacken the codebase...
r43346 rl.append(
struct.pack(
Augie Fackler
formatting: byteify all mercurial/ and hgext/ string literals...
r43347 b">lll",
Augie Fackler
formatting: blacken the codebase...
r43346 (a[0] + la).l - a[0].l,
(a[0] + h.a1).l - a[0].l,
lgt,
)
)
Manuel Jacob
cffi: call bytes() instead of str() on CFFI buffer instances
r52684 rl.append(bytes(ffi.buffer((b[0] + lb).l, lgt)))
Yuya Nishihara
cffi: remove superfluous "if True" blocks
r32513 la = h.a2
lb = h.b2
h = h.next
Yuya Nishihara
cffi: split modules from pure...
r32512
Yuya Nishihara
cffi: remove superfluous "if True" blocks
r32513 finally:
lib.free(a[0])
lib.free(b[0])
lib.bdiff_freehunks(l.next)
Augie Fackler
formatting: byteify all mercurial/ and hgext/ string literals...
r43347 return b"".join(rl)
Matt Harbison
interfaces: add the optional `bdiff.xdiffblocks()` method...
r52827
# In order to adhere to the module protocol, these functions must be visible to
# the type checker, though they aren't actually implemented by this
# implementation of the module protocol. Callers are responsible for
# checking that the implementation is available before using them.
if typing.TYPE_CHECKING:
xdiffblocks: Optional[intmod.BDiffBlocksFnc] = None