maintenance: add --schedule option and config
Maintenance currently triggers when certain data-size thresholds are met, such as number of pack-files or loose objects. Users may want to run certain maintenance tasks based on frequency instead. For example, a user may want to perform a 'prefetch' task every hour, or 'gc' task every day. To help these users, update the 'git maintenance run' command to include a '--schedule=<frequency>' option. The allowed frequencies are 'hourly', 'daily', and 'weekly'. These values are also allowed in a new config value 'maintenance.<task>.schedule'. The 'git maintenance run --schedule=<frequency>' checks the '*.schedule' config value for each enabled task to see if the configured frequency is at least as frequent as the frequency from the '--schedule' argument. We use the following order, for full clarity: 'hourly' > 'daily' > 'weekly' Use new 'enum schedule_priority' to track these values numerically. The following cron table would run the scheduled tasks with the correct frequencies: 0 1-23 * * * git -C <repo> maintenance run --schedule=hourly 0 0 * * 1-6 git -C <repo> maintenance run --schedule=daily 0 0 * * 0 git -C <repo> maintenance run --schedule=weekly This cron schedule will run --schedule=hourly every hour except at midnight. This avoids a concurrent run with the --schedule=daily that runs at midnight every day except the first day of the week. This avoids a concurrent run with the --schedule=weekly that runs at midnight on the first day of the week. Since --schedule=daily also runs the 'hourly' tasks and --schedule=weekly runs the 'hourly' and 'daily' tasks, we will still see all tasks run with the proper frequencies. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Derrick Stolee committed
Sep 11, 2020 at 17:49 UTC
b08ff1fee000230ad22fee823aabff2613bd4e62
4 files changed
+118
-4
Documentation/config/maintenance.txt
+5
@@ -10,6 +10,11 @@ maintenance.<task>.enabled::
10
`--task` option exists. By default, only `maintenance.gc.enabled`
11
is true.
12
13
+maintenance.<task>.schedule::
14
+ This config option controls whether or not the given `<task>` runs
15
+ during a `git maintenance run --schedule=<frequency>` command. The
16
+ value must be one of "hourly", "daily", or "weekly".
17
+
18
maintenance.commit-graph.auto::
19
This integer config option controls how often the `commit-graph` task
20
should be run as part of `git maintenance run --auto`. If zero, then
Documentation/git-maintenance.txt
+12
-1
@@ -110,7 +110,18 @@ OPTIONS
110
only if certain thresholds are met. For example, the `gc` task
111
runs when the number of loose objects exceeds the number stored
112
in the `gc.auto` config setting, or when the number of pack-files
113
- exceeds the `gc.autoPackLimit` config setting.
113
+ exceeds the `gc.autoPackLimit` config setting. Not compatible with
114
+ the `--schedule` option.
115
+
116
+--schedule::
117
+ When combined with the `run` subcommand, run maintenance tasks
118
+ only if certain time conditions are met, as specified by the
119
+ `maintenance.<task>.schedule` config value for each `<task>`.
120
+ This config value specifies a number of seconds since the last
121
+ time that task ran, according to the `maintenance.<task>.lastRun`
122
+ config value. The tasks that are tested are those provided by
123
+ the `--task=<task>` option(s) or those with
124
+ `maintenance.<task>.enabled` set to true.
125
126
--quiet::
127
Do not report progress or other information over `stderr`.
builtin/gc.c
+61
-3
@@ -703,14 +703,51 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
703
return 0;
704
}
705
706
-static const char * const builtin_maintenance_run_usage[] = {
707
- N_("git maintenance run [--auto] [--[no-]quiet] [--task=<task>]"),
706
+static const char *const builtin_maintenance_run_usage[] = {
707
+ N_("git maintenance run [--auto] [--[no-]quiet] [--task=<task>] [--schedule]"),
708
NULL
709
};
710
711
+enum schedule_priority {
712
+ SCHEDULE_NONE = 0,
713
+ SCHEDULE_WEEKLY = 1,
714
+ SCHEDULE_DAILY = 2,
715
+ SCHEDULE_HOURLY = 3,
716
+};
717
+
718
+static enum schedule_priority parse_schedule(const char *value)
719
+{
720
+ if (!value)
721
+ return SCHEDULE_NONE;
722
+ if (!strcasecmp(value, "hourly"))
723
+ return SCHEDULE_HOURLY;
724
+ if (!strcasecmp(value, "daily"))
725
+ return SCHEDULE_DAILY;
726
+ if (!strcasecmp(value, "weekly"))
727
+ return SCHEDULE_WEEKLY;
728
+ return SCHEDULE_NONE;
729
+}
730
+
731
+static int maintenance_opt_schedule(const struct option *opt, const char *arg,
732
+ int unset)
733
+{
734
+ enum schedule_priority *priority = opt->value;
735
+
736
+ if (unset)
737
+ die(_("--no-schedule is not allowed"));
738
+
739
+ *priority = parse_schedule(arg);
740
+
741
+ if (!*priority)
742
+ die(_("unrecognized --schedule argument '%s'"), arg);
743
+
744
+ return 0;
745
+}
746
+
747
struct maintenance_run_opts {
748
int auto_flag;
749
int quiet;
750
+ enum schedule_priority schedule;
751
};
752
753
/* Remember to update object flag allocation in object.h */
@@ -1158,6 +1195,8 @@ struct maintenance_task {
1195
maintenance_auto_fn *auto_condition;
1196
unsigned enabled:1;
1197
1198
+ enum schedule_priority schedule;
1199
+
1200
/* -1 if not selected. */
1201
int selected_order;
1202
};
@@ -1253,6 +1292,9 @@ static int maintenance_run_tasks(struct maintenance_run_opts *opts)
1292
!tasks[i].auto_condition()))
1293
continue;
1294
1295
+ if (opts->schedule && tasks[i].schedule < opts->schedule)
1296
+ continue;
1297
+
1298
trace2_region_enter("maintenance", tasks[i].name, r);
1299
if (tasks[i].fn(opts)) {
1300
error(_("task '%s' failed"), tasks[i].name);
@@ -1273,13 +1315,23 @@ static void initialize_task_config(void)
1315
1316
for (i = 0; i < TASK__COUNT; i++) {
1317
int config_value;
1318
+ char *config_str;
1319
1277
- strbuf_setlen(&config_name, 0);
1320
+ strbuf_reset(&config_name);
1321
strbuf_addf(&config_name, "maintenance.%s.enabled",
1322
tasks[i].name);
1323
1324
if (!git_config_get_bool(config_name.buf, &config_value))
1325
tasks[i].enabled = config_value;
1326
+
1327
+ strbuf_reset(&config_name);
1328
+ strbuf_addf(&config_name, "maintenance.%s.schedule",
1329
+ tasks[i].name);
1330
+
1331
+ if (!git_config_get_string(config_name.buf, &config_str)) {
1332
+ tasks[i].schedule = parse_schedule(config_str);
1333
+ free(config_str);
1334
+ }
1335
}
1336
1337
strbuf_release(&config_name);
@@ -1323,6 +1375,9 @@ static int maintenance_run(int argc, const char **argv, const char *prefix)
1375
struct option builtin_maintenance_run_options[] = {
1376
OPT_BOOL(0, "auto", &opts.auto_flag,
1377
N_("run tasks based on the state of the repository")),
1378
+ OPT_CALLBACK(0, "schedule", &opts.schedule, N_("frequency"),
1379
+ N_("run tasks based on frequency"),
1380
+ maintenance_opt_schedule),
1381
OPT_BOOL(0, "quiet", &opts.quiet,
1382
N_("do not report progress or other information over stderr")),
1383
OPT_CALLBACK_F(0, "task", NULL, N_("task"),
@@ -1343,6 +1398,9 @@ static int maintenance_run(int argc, const char **argv, const char *prefix)
1398
builtin_maintenance_run_usage,
1399
PARSE_OPT_STOP_AT_NON_OPTION);
1400
1401
+ if (opts.auto_flag && opts.schedule)
1402
+ die(_("use at most one of --auto and --schedule=<frequency>"));
1403
+
1404
if (argc != 0)
1405
usage_with_options(builtin_maintenance_run_usage,
1406
builtin_maintenance_run_options);
t/t7900-maintenance.sh
+40
@@ -260,4 +260,44 @@ test_expect_success 'maintenance.incremental-repack.auto' '
260
test_subcommand git multi-pack-index write --no-progress <trace-B
261
'
262
263
+test_expect_success '--auto and --schedule incompatible' '
264
+ test_must_fail git maintenance run --auto --schedule=daily 2>err &&
265
+ test_i18ngrep "at most one" err
266
+'
267
+
268
+test_expect_success 'invalid --schedule value' '
269
+ test_must_fail git maintenance run --schedule=annually 2>err &&
270
+ test_i18ngrep "unrecognized --schedule" err
271
+'
272
+
273
+test_expect_success '--schedule inheritance weekly -> daily -> hourly' '
274
+ git config maintenance.loose-objects.enabled true &&
275
+ git config maintenance.loose-objects.schedule hourly &&
276
+ git config maintenance.commit-graph.enabled true &&
277
+ git config maintenance.commit-graph.schedule daily &&
278
+ git config maintenance.incremental-repack.enabled true &&
279
+ git config maintenance.incremental-repack.schedule weekly &&
280
+
281
+ GIT_TRACE2_EVENT="$(pwd)/hourly.txt" \
282
+ git maintenance run --schedule=hourly 2>/dev/null &&
283
+ test_subcommand git prune-packed --quiet <hourly.txt &&
284
+ test_subcommand ! git commit-graph write --split --reachable \
285
+ --no-progress <hourly.txt &&
286
+ test_subcommand ! git multi-pack-index write --no-progress <hourly.txt &&
287
+
288
+ GIT_TRACE2_EVENT="$(pwd)/daily.txt" \
289
+ git maintenance run --schedule=daily 2>/dev/null &&
290
+ test_subcommand git prune-packed --quiet <daily.txt &&
291
+ test_subcommand git commit-graph write --split --reachable \
292
+ --no-progress <daily.txt &&
293
+ test_subcommand ! git multi-pack-index write --no-progress <daily.txt &&
294
+
295
+ GIT_TRACE2_EVENT="$(pwd)/weekly.txt" \
296
+ git maintenance run --schedule=weekly 2>/dev/null &&
297
+ test_subcommand git prune-packed --quiet <weekly.txt &&
298
+ test_subcommand git commit-graph write --split --reachable \
299
+ --no-progress <weekly.txt &&
300
+ test_subcommand git multi-pack-index write --no-progress <weekly.txt
301
+'
302
+
303
test_done