From 2057d75038541cd16debb1c55f3f897fd244965c Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Thu, 17 Sep 2020 18:11:42 +0000 Subject: [PATCH] maintenance: create basic maintenance runner The 'gc' builtin is our current entrypoint for automatically maintaining a repository. This one tool does many operations, such as repacking the repository, packing refs, and rewriting the commit-graph file. The name implies it performs "garbage collection" which means several different things, and some users may not want to use this operation that rewrites the entire object database. Create a new 'maintenance' builtin that will become a more general- purpose command. To start, it will only support the 'run' subcommand, but will later expand to add subcommands for scheduling maintenance in the background. For now, the 'maintenance' builtin is a thin shim over the 'gc' builtin. In fact, the only option is the '--auto' toggle, which is handed directly to the 'gc' builtin. The current change is isolated to this simple operation to prevent more interesting logic from being lost in all of the boilerplate of adding a new builtin. Use existing builtin/gc.c file because we want to share code between the two builtins. It is possible that we will have 'maintenance' replace the 'gc' builtin entirely at some point, leaving 'git gc' as an alias for some specific arguments to 'git maintenance run'. Create a new test_subcommand helper that allows us to test if a certain subcommand was run. It requires storing the GIT_TRACE2_EVENT logs in a file. A negation mode is available that will be used in later tests. Helped-by: Jonathan Nieder Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- .gitignore | 1 + Documentation/git-maintenance.txt | 57 ++++++++++++++++++++++++++++++ builtin.h | 1 + builtin/gc.c | 58 +++++++++++++++++++++++++++++++ command-list.txt | 1 + git.c | 1 + t/t7900-maintenance.sh | 23 ++++++++++++ t/test-lib-functions.sh | 33 ++++++++++++++++++ 8 files changed, 175 insertions(+) create mode 100644 Documentation/git-maintenance.txt create mode 100755 t/t7900-maintenance.sh diff --git a/.gitignore b/.gitignore index ee509a2ad2..a5808fa30d 100644 --- a/.gitignore +++ b/.gitignore @@ -90,6 +90,7 @@ /git-ls-tree /git-mailinfo /git-mailsplit +/git-maintenance /git-merge /git-merge-base /git-merge-index diff --git a/Documentation/git-maintenance.txt b/Documentation/git-maintenance.txt new file mode 100644 index 0000000000..ff47fb3641 --- /dev/null +++ b/Documentation/git-maintenance.txt @@ -0,0 +1,57 @@ +git-maintenance(1) +================== + +NAME +---- +git-maintenance - Run tasks to optimize Git repository data + + +SYNOPSIS +-------- +[verse] +'git maintenance' run [] + + +DESCRIPTION +----------- +Run tasks to optimize Git repository data, speeding up other Git commands +and reducing storage requirements for the repository. + +Git commands that add repository data, such as `git add` or `git fetch`, +are optimized for a responsive user experience. These commands do not take +time to optimize the Git data, since such optimizations scale with the full +size of the repository while these user commands each perform a relatively +small action. + +The `git maintenance` command provides flexibility for how to optimize the +Git repository. + +SUBCOMMANDS +----------- + +run:: + Run one or more maintenance tasks. + +TASKS +----- + +gc:: + Clean up unnecessary files and optimize the local repository. "GC" + stands for "garbage collection," but this task performs many + smaller tasks. This task can be expensive for large repositories, + as it repacks all Git objects into a single pack-file. It can also + be disruptive in some situations, as it deletes stale data. See + linkgit:git-gc[1] for more details on garbage collection in Git. + +OPTIONS +------- +--auto:: + When combined with the `run` subcommand, run maintenance tasks + only if certain thresholds are met. For example, the `gc` task + runs when the number of loose objects exceeds the number stored + in the `gc.auto` config setting, or when the number of pack-files + exceeds the `gc.autoPackLimit` config setting. + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/builtin.h b/builtin.h index a5ae15bfe5..17c1c0ce49 100644 --- a/builtin.h +++ b/builtin.h @@ -167,6 +167,7 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix); int cmd_ls_remote(int argc, const char **argv, const char *prefix); int cmd_mailinfo(int argc, const char **argv, const char *prefix); int cmd_mailsplit(int argc, const char **argv, const char *prefix); +int cmd_maintenance(int argc, const char **argv, const char *prefix); int cmd_merge(int argc, const char **argv, const char *prefix); int cmd_merge_base(int argc, const char **argv, const char *prefix); int cmd_merge_index(int argc, const char **argv, const char *prefix); diff --git a/builtin/gc.c b/builtin/gc.c index aafa0946f5..ec064e8686 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -699,3 +699,61 @@ int cmd_gc(int argc, const char **argv, const char *prefix) return 0; } + +static const char * const builtin_maintenance_run_usage[] = { + N_("git maintenance run [--auto]"), + NULL +}; + +struct maintenance_run_opts { + int auto_flag; +}; + +static int maintenance_task_gc(struct maintenance_run_opts *opts) +{ + struct child_process child = CHILD_PROCESS_INIT; + + child.git_cmd = 1; + strvec_push(&child.args, "gc"); + + if (opts->auto_flag) + strvec_push(&child.args, "--auto"); + + close_object_store(the_repository->objects); + return run_command(&child); +} + +static int maintenance_run(int argc, const char **argv, const char *prefix) +{ + struct maintenance_run_opts opts; + struct option builtin_maintenance_run_options[] = { + OPT_BOOL(0, "auto", &opts.auto_flag, + N_("run tasks based on the state of the repository")), + OPT_END() + }; + memset(&opts, 0, sizeof(opts)); + + argc = parse_options(argc, argv, prefix, + builtin_maintenance_run_options, + builtin_maintenance_run_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (argc != 0) + usage_with_options(builtin_maintenance_run_usage, + builtin_maintenance_run_options); + return maintenance_task_gc(&opts); +} + +static const char builtin_maintenance_usage[] = N_("git maintenance run []"); + +int cmd_maintenance(int argc, const char **argv, const char *prefix) +{ + if (argc < 2 || + (argc == 2 && !strcmp(argv[1], "-h"))) + usage(builtin_maintenance_usage); + + if (!strcmp(argv[1], "run")) + return maintenance_run(argc - 1, argv + 1, prefix); + + die(_("invalid subcommand: %s"), argv[1]); +} diff --git a/command-list.txt b/command-list.txt index e5901f2213..0e3204e7d1 100644 --- a/command-list.txt +++ b/command-list.txt @@ -117,6 +117,7 @@ git-ls-remote plumbinginterrogators git-ls-tree plumbinginterrogators git-mailinfo purehelpers git-mailsplit purehelpers +git-maintenance mainporcelain git-merge mainporcelain history git-merge-base plumbinginterrogators git-merge-file plumbingmanipulators diff --git a/git.c b/git.c index 8bd1d7551d..24f250d29a 100644 --- a/git.c +++ b/git.c @@ -529,6 +529,7 @@ static struct cmd_struct commands[] = { { "ls-tree", cmd_ls_tree, RUN_SETUP }, { "mailinfo", cmd_mailinfo, RUN_SETUP_GENTLY | NO_PARSEOPT }, { "mailsplit", cmd_mailsplit, NO_PARSEOPT }, + { "maintenance", cmd_maintenance, RUN_SETUP_GENTLY | NO_PARSEOPT }, { "merge", cmd_merge, RUN_SETUP | NEED_WORK_TREE }, { "merge-base", cmd_merge_base, RUN_SETUP }, { "merge-file", cmd_merge_file, RUN_SETUP_GENTLY }, diff --git a/t/t7900-maintenance.sh b/t/t7900-maintenance.sh new file mode 100755 index 0000000000..c2f0b1d0c0 --- /dev/null +++ b/t/t7900-maintenance.sh @@ -0,0 +1,23 @@ +#!/bin/sh + +test_description='git maintenance builtin' + +. ./test-lib.sh + +test_expect_success 'help text' ' + test_expect_code 129 git maintenance -h 2>err && + test_i18ngrep "usage: git maintenance run" err && + test_expect_code 128 git maintenance barf 2>err && + test_i18ngrep "invalid subcommand: barf" err && + test_expect_code 129 git maintenance 2>err && + test_i18ngrep "usage: git maintenance" err +' + +test_expect_success 'run [--auto]' ' + GIT_TRACE2_EVENT="$(pwd)/run-no-auto.txt" git maintenance run && + GIT_TRACE2_EVENT="$(pwd)/run-auto.txt" git maintenance run --auto && + test_subcommand git gc ... < +# +# For example, to look for an invocation of "git upload-pack +# /path/to/repo" +# +# GIT_TRACE2_EVENT=event.log git fetch ... && +# test_subcommand git upload-pack "$PATH"