From 8da4861b3860c505e39341b4135c21f67569e4d8 Mon Sep 17 00:00:00 2001 From: Kuang-che Wu Date: Tue, 22 Oct 2024 21:04:41 +0800 Subject: subcmds: reduce multiprocessing serialization overhead Follow the same approach as 39ffd9977e to reduce serialization overhead. Below benchmarks are tested with 2.7k projects on my workstation (warm cache). git tracing is disabled for benchmark. (seconds) | v2.48 | v2.48 | this CL | this CL | | -j32 | | -j32 ----------------------------------------------------------- with clean tree state: branches (none) | 5.6 | 5.9 | 1.0 | 0.9 status (clean) | 21.3 | 9.4 | 19.4 | 4.7 diff (none) | 7.6 | 7.2 | 5.7 | 2.2 prune (none) | 5.7 | 6.1 | 1.3 | 1.2 abandon (none) | 19.4 | 18.6 | 0.9 | 0.8 upload (none) | 19.7 | 18.7 | 0.9 | 0.8 forall -c true | 7.5 | 7.6 | 0.6 | 0.6 forall -c "git log -1" | 11.3 | 11.1 | 0.6 | 0.6 with branches: start BRANCH --all | 21.9 | 20.3 | 13.6 | 2.6 checkout BRANCH | 29.1 | 27.8 | 1.1 | 1.0 branches (2) | 28.0 | 28.6 | 1.5 | 1.3 abandon BRANCH | 29.2 | 27.5 | 9.7 | 2.2 Bug: b/371638995 Change-Id: I53989a3d1e43063587b3f52f852b1c2c56b49412 Reviewed-on: https://gerrit-review.googlesource.com/c/git-repo/+/440221 Reviewed-by: Josip Sokcevic Tested-by: Kuang-che Wu Commit-Queue: Kuang-che Wu --- subcmds/prune.py | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'subcmds/prune.py') diff --git a/subcmds/prune.py b/subcmds/prune.py index f99082a4..18bfc680 100644 --- a/subcmds/prune.py +++ b/subcmds/prune.py @@ -27,8 +27,10 @@ class Prune(PagedCommand): """ PARALLEL_JOBS = DEFAULT_LOCAL_JOBS - def _ExecuteOne(self, project): + @classmethod + def _ExecuteOne(cls, project_idx): """Process one project.""" + project = cls.get_parallel_context()["projects"][project_idx] return project.PruneHeads() def Execute(self, opt, args): @@ -41,13 +43,15 @@ class Prune(PagedCommand): def _ProcessResults(_pool, _output, results): return list(itertools.chain.from_iterable(results)) - all_branches = self.ExecuteInParallel( - opt.jobs, - self._ExecuteOne, - projects, - callback=_ProcessResults, - ordered=True, - ) + with self.ParallelContext(): + self.get_parallel_context()["projects"] = projects + all_branches = self.ExecuteInParallel( + opt.jobs, + self._ExecuteOne, + range(len(projects)), + callback=_ProcessResults, + ordered=True, + ) if not all_branches: return -- cgit v1.2.3-54-g00ecf