GeezerVison is showing github.com — GitPython/test/performance/bench_repository.py at main · gitpython-developers/GitPython

Expand file tree

bench_repository.py

Copy path

More file actions

Latest commit

History

207 lines (163 loc) · 7.19 KB

bench_repository.py

Copy path

File metadata and controls

207 lines (163 loc) · 7.19 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

"""Read-only GitPython journeys, measured with pyperf against an existing checkout.

Run as a module from the source root so pyperf workers import this checkout:

python -m test.performance.bench_repository --repo /path/to/repo --expect-backend gix -o gix.json

"""

from hashlib import sha256

from importlib.metadata import version

import json

import os

from pathlib import Path

import subprocess

import pyperf

from git import Repo, _backend

def inventory(repo):

return {

"head": repo.head.commit.hexsha if repo.head.is_detached else repo.head.reference.path,

"refs": sorted(ref.path for ref in repo.references),

}

def history(repo):

return [

[commit.hexsha, str(commit.author), commit.authored_date, commit.message]

for commit in repo.iter_commits("HEAD", max_count=25, first_parent=True)

]

def browse(repo):

tree = repo.commit("HEAD").tree

blob = tree / "README.md"

content = blob.data_stream.read()

return {

"entries": [[entry.path, entry.mode, entry.hexsha] for entry in tree],

"readme": sha256(content).hexdigest(),

}

def index(repo):

return sorted([entry.path, entry.stage, entry.mode, entry.hexsha] for entry in repo.index.iter_entries())

def submodules(repo):

return [[module.name, module.path, module.hexsha, module.url, module.branch_path] for module in repo.submodules]

def revision_paths(repo):

objects = [repo.rev_parse(revision) for revision in ("HEAD:README.md", "HEAD:git", ":README.md")]

return [[obj.hexsha, obj.path, obj.mode] for obj in objects]

def object_readback(repo):

commit = repo.commit("HEAD")

# Read the same bytes used by serialization, without writing objects or stripping signatures.

return [sha256(obj.data_stream.read()).hexdigest() for obj in (commit, commit.tree)]

def graph(repo):

tip, parent = repo.commit("HEAD"), repo.commit("HEAD~1")

return {

"count": tip.count(),

"merge_base": [commit.hexsha for commit in repo.merge_base(parent, tip)],

"is_ancestor": repo.is_ancestor(parent, tip),

}

def changes(repo):

tip = repo.commit("HEAD")

return {

"diff": [[diff.change_type, diff.a_path, diff.b_path] for diff in tip.parents[0].diff(tip)],

"stats": tip.stats.total,

}

def patch(repo):

tip = repo.commit("HEAD")

return [sha256(diff.diff).hexdigest() for diff in tip.parents[0].diff(tip, create_patch=True)]

def worktree(repo):

return {

"dirty": repo.is_dirty(untracked_files=True),

"untracked": sorted(repo.untracked_files),

"ignored": repo.ignored(".benchmark-cache/probe"),

}

# Add a named public-API operation here: it is measured separately and joins the

# complete journey automatically. Return JSON-compatible data for parity checks.

MEASUREMENTS = {

"inventory": inventory,

"history_25": history,

"browse_tree_and_blob": browse,

"read_index": index,

"submodule_inventory": submodules,

"revision_paths": revision_paths,

"object_readback": object_readback,

"revision_graph": graph,

"diff_and_stats": changes,

"patch_diff": patch,

"worktree_status": worktree,

}

def journey(repo):

return {name: operation(repo) for name, operation in MEASUREMENTS.items()}

def open_repository(path):

with Repo(path) as opened:

return [opened.bare, opened.object_format, opened.ref_format]

def discover_repository(path):

with Repo(path, search_parent_directories=True) as opened:

return [opened.bare, opened.object_format, opened.ref_format]

def worker_arguments(cmd, args):

cmd.extend(["--repo", str(args.repo), "--expect-backend", args.expect_backend])

def source_digest(root):

digest = sha256()

sources = [root / "VERSION", *(root / "git").rglob("*.py"), *(root / "test" / "performance").glob("*.py")]

for path in sorted(sources):

digest.update(path.relative_to(root).as_posix().encode() + b"\0" + path.read_bytes() + b"\0")

return digest.hexdigest()

def main():

runner = pyperf.Runner(

processes=6,

values=3,

program_args=("-m", "test.performance.bench_repository"),

add_cmdline_args=worker_arguments,

)

runner.argparser.add_argument("--repo", type=Path, required=True, help="Existing worktree; never modified")

runner.argparser.add_argument("--expect-backend", choices=("cli", "gix"), required=True)

args = runner.parse_args()

args.repo = args.repo.resolve()

if _backend.name != args.expect_backend:

raise RuntimeError(f"Expected {args.expect_backend}, imported {_backend.name}; set GIT_PYTHON_BACKEND")

# The manager and every worker use the same isolated Git environment.

for key in list(os.environ):

if key.startswith("GIT_"):

del os.environ[key]

os.environ.update(

GIT_CONFIG_NOSYSTEM="1",

GIT_CONFIG_GLOBAL=os.devnull,

GIT_OPTIONAL_LOCKS="0",

GIT_PYTHON_BACKEND=args.expect_backend,

)

args.inherit_environ = [*(args.inherit_environ or []), "GIT_PYTHON_BACKEND"]

def git(*arguments, cwd=args.repo):

return subprocess.check_output(["git", *arguments], cwd=cwd, text=True).strip()

runner.metadata.update(

backend=_backend.name,

gixpython=version("GixPython"),

git_version=git("version"),

gitpython_source=source_digest(Path(__file__).resolve().parents[2]),

fixture_revision=git("rev-parse", "HEAD"),

fixture_tree=git("rev-parse", "HEAD^{tree}"),

fixture_status=git("status", "--porcelain") or "clean",

fixture_object_format=git("rev-parse", "--show-object-format"),

fixture_ref_format=git("rev-parse", "--show-ref-format"),

)

with Repo(args.repo) as repo:

measurements = [("journey", journey, repo)]

measurements.extend((name, operation, repo) for name, operation in MEASUREMENTS.items())

measurements.extend(

[

("open_repository", open_repository, args.repo),

("discover_repository", discover_repository, args.repo / "git" / "objects"),

]

)

for name, operation, target in measurements:

operation(target) # Warm persistent CLI processes before counting.

# Untimed preflight validates parity and records native/fallback

# decisions for ONE invocation, rather than calibrated loop counts.

before = _backend.statistics()

result = operation(target)

decisions = [

{"method": method, "outcome": outcome, "count": count - before.get((method, outcome), 0)}

for (method, outcome), count in sorted(_backend.statistics().items())

if count > before.get((method, outcome), 0)

]

metadata = {

"result_digest": sha256(json.dumps(result, sort_keys=True).encode()).hexdigest(),

"backend_decisions": json.dumps(decisions, sort_keys=True),

"cli_processes": sum(

item["count"]

for item in decisions

if (item["method"], item["outcome"]) == ("Git.execute", "CLI process")

}

runner.bench_func(name, operation, target, metadata=metadata)

if __name__ == "__main__":

main()