maintenance: add start/stop subcommands

Add new subcommands to 'git maintenance' that start or stop background
maintenance using 'cron', when available. This integration is as simple
as I could make it, barring some implementation complications.

The schedule is laid out as follows:

  0 1-23 * * *   $cmd maintenance run --schedule=hourly
  0 0    * * 1-6 $cmd maintenance run --schedule=daily
  0 0    * * 0   $cmd maintenance run --schedule=weekly

where $cmd is a properly-qualified 'git for-each-repo' execution:

$cmd=$path/git --exec-path=$path for-each-repo --config=maintenance.repo

where $path points to the location of the Git executable running 'git
maintenance start'. This is critical for systems with multiple versions
of Git. Specifically, macOS has a system version at '/usr/bin/git' while
the version that users can install resides at '/usr/local/bin/git'
(symlinked to '/usr/local/libexec/git-core/git'). This will also use
your locally-built version if you build and run this in your development
environment without installing first.

This conditional schedule avoids having cron launch multiple 'git
for-each-repo' commands in parallel. Such parallel commands would likely
lead to the 'hourly' and 'daily' tasks competing over the object
database lock. This could lead to to some tasks never being run! Since
the --schedule=<frequency> argument will run all tasks with _at least_
the given frequency, the daily runs will also run the hourly tasks.
Similarly, the weekly runs will also run the daily and hourly tasks.

The GIT_TEST_CRONTAB environment variable is not intended for users to
edit, but instead as a way to mock the 'crontab [-l]' command. This
variable is set in test-lib.sh to avoid a future test from accidentally
running anything with the cron integration from modifying the user's
schedule. We use GIT_TEST_CRONTAB='test-tool crontab <file>' in our
tests to check how the schedule is modified in 'git maintenance
(start|stop)' commands.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 124 insertions, 0 deletions

diff --git a/builtin/gc.c b/builtin/gc.c
index edf1d35ce5..a387f46585 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -31,6 +31,7 @@
 #include "refs.h"
 #include "remote.h"
 #include "object-store.h"
+#include "exec-cmd.h"
 
 #define FAILED_RUN "failed to run %s"
 
@@ -1456,6 +1457,125 @@ static int maintenance_unregister(void)
 	return run_command(&config_unset);
 }
 
+#define BEGIN_LINE "# BEGIN GIT MAINTENANCE SCHEDULE"
+#define END_LINE "# END GIT MAINTENANCE SCHEDULE"
+
+static int update_background_schedule(int run_maintenance)
+{
+	int result = 0;
+	int in_old_region = 0;
+	struct child_process crontab_list = CHILD_PROCESS_INIT;
+	struct child_process crontab_edit = CHILD_PROCESS_INIT;
+	FILE *cron_list, *cron_in;
+	const char *crontab_name;
+	struct strbuf line = STRBUF_INIT;
+	struct lock_file lk;
+	char *lock_path = xstrfmt("%s/schedule", the_repository->objects->odb->path);
+
+	if (hold_lock_file_for_update(&lk, lock_path, LOCK_NO_DEREF) < 0)
+		return error(_("another process is scheduling background maintenance"));
+
+	crontab_name = getenv("GIT_TEST_CRONTAB");
+	if (!crontab_name)
+		crontab_name = "crontab";
+
+	strvec_split(&crontab_list.args, crontab_name);
+	strvec_push(&crontab_list.args, "-l");
+	crontab_list.in = -1;
+	crontab_list.out = dup(lk.tempfile->fd);
+	crontab_list.git_cmd = 0;
+
+	if (start_command(&crontab_list)) {
+		result = error(_("failed to run 'crontab -l'; your system might not support 'cron'"));
+		goto cleanup;
+	}
+
+	/* Ignore exit code, as an empty crontab will return error. */
+	finish_command(&crontab_list);
+
+	/*
+	 * Read from the .lock file, filtering out the old
+	 * schedule while appending the new schedule.
+	 */
+	cron_list = fdopen(lk.tempfile->fd, "r");
+	rewind(cron_list);
+
+	strvec_split(&crontab_edit.args, crontab_name);
+	crontab_edit.in = -1;
+	crontab_edit.git_cmd = 0;
+
+	if (start_command(&crontab_edit)) {
+		result = error(_("failed to run 'crontab'; your system might not support 'cron'"));
+		goto cleanup;
+	}
+
+	cron_in = fdopen(crontab_edit.in, "w");
+	if (!cron_in) {
+		result = error(_("failed to open stdin of 'crontab'"));
+		goto done_editing;
+	}
+
+	while (!strbuf_getline_lf(&line, cron_list)) {
+		if (!in_old_region && !strcmp(line.buf, BEGIN_LINE))
+			in_old_region = 1;
+		if (in_old_region)
+			continue;
+		fprintf(cron_in, "%s\n", line.buf);
+		if (in_old_region && !strcmp(line.buf, END_LINE))
+			in_old_region = 0;
+	}
+
+	if (run_maintenance) {
+		struct strbuf line_format = STRBUF_INIT;
+		const char *exec_path = git_exec_path();
+
+		fprintf(cron_in, "%s\n", BEGIN_LINE);
+		fprintf(cron_in,
+			"# The following schedule was created by Git\n");
+		fprintf(cron_in, "# Any edits made in this region might be\n");
+		fprintf(cron_in,
+			"# replaced in the future by a Git command.\n\n");
+
+		strbuf_addf(&line_format,
+			    "%%s %%s * * %%s \"%s/git\" --exec-path=\"%s\" for-each-repo --config=maintenance.repo maintenance run --schedule=%%s\n",
+			    exec_path, exec_path);
+		fprintf(cron_in, line_format.buf, "0", "1-23", "*", "hourly");
+		fprintf(cron_in, line_format.buf, "0", "0", "1-6", "daily");
+		fprintf(cron_in, line_format.buf, "0", "0", "0", "weekly");
+		strbuf_release(&line_format);
+
+		fprintf(cron_in, "\n%s\n", END_LINE);
+	}
+
+	fflush(cron_in);
+	fclose(cron_in);
+	close(crontab_edit.in);
+
+done_editing:
+	if (finish_command(&crontab_edit)) {
+		result = error(_("'crontab' died"));
+		goto cleanup;
+	}
+	fclose(cron_list);
+
+cleanup:
+	rollback_lock_file(&lk);
+	return result;
+}
+
+static int maintenance_start(void)
+{
+	if (maintenance_register())
+		warning(_("failed to add repo to global config"));
+
+	return update_background_schedule(1);
+}
+
+static int maintenance_stop(void)
+{
+	return update_background_schedule(0);
+}
+
 static const char builtin_maintenance_usage[] =	N_("git maintenance <subcommand> [<options>]");
 
 int cmd_maintenance(int argc, const char **argv, const char *prefix)
@@ -1466,6 +1586,10 @@ int cmd_maintenance(int argc, const char **argv, const char *prefix)
 
 	if (!strcmp(argv[1], "run"))
 		return maintenance_run(argc - 1, argv + 1, prefix);
+	if (!strcmp(argv[1], "start"))
+		return maintenance_start();
+	if (!strcmp(argv[1], "stop"))
+		return maintenance_stop();
 	if (!strcmp(argv[1], "register"))
 		return maintenance_register();
 	if (!strcmp(argv[1], "unregister"))