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/upload.py | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'subcmds/upload.py') diff --git a/subcmds/upload.py b/subcmds/upload.py index 8039a1cd..6344ee31 100644 --- a/subcmds/upload.py +++ b/subcmds/upload.py @@ -713,16 +713,17 @@ Gerrit Code Review: https://www.gerritcodereview.com/ merge_branch = p.stdout.strip() return merge_branch - @staticmethod - def _GatherOne(opt, project): + @classmethod + def _GatherOne(cls, opt, project_idx): """Figure out the upload status for |project|.""" + project = cls.get_parallel_context()["projects"][project_idx] if opt.current_branch: cbr = project.CurrentBranch up_branch = project.GetUploadableBranch(cbr) avail = [up_branch] if up_branch else None else: avail = project.GetUploadableBranches(opt.branch) - return (project, avail) + return (project_idx, avail) def Execute(self, opt, args): projects = self.GetProjects( @@ -732,8 +733,9 @@ Gerrit Code Review: https://www.gerritcodereview.com/ def _ProcessResults(_pool, _out, results): pending = [] for result in results: - project, avail = result + project_idx, avail = result if avail is None: + project = projects[project_idx] logger.error( 'repo: error: %s: Unable to upload branch "%s". ' "You might be able to fix the branch by running:\n" @@ -746,12 +748,14 @@ Gerrit Code Review: https://www.gerritcodereview.com/ pending.append(result) return pending - pending = self.ExecuteInParallel( - opt.jobs, - functools.partial(self._GatherOne, opt), - projects, - callback=_ProcessResults, - ) + with self.ParallelContext(): + self.get_parallel_context()["projects"] = projects + pending = self.ExecuteInParallel( + opt.jobs, + functools.partial(self._GatherOne, opt), + range(len(projects)), + callback=_ProcessResults, + ) if not pending: if opt.branch is None: -- cgit v1.2.3-54-g00ecf