Merge branch 'kn/maintenance-is-needed'

"git maintenance" command learned "is-needed" subcommand to tell if
it is necessary to perform various maintenance tasks.

* kn/maintenance-is-needed:
  maintenance: add 'is-needed' subcommand
  maintenance: add checking logic in `pack_refs_condition()`
  refs: add a `optimize_required` field to `struct ref_storage_be`
  reftable/stack: add function to check if optimization is required
  reftable/stack: return stack segments directly

Author: gitster

Documentation/git-maintenance.adoc

@@ -12,6 +12,7 @@ SYNOPSIS
 'git maintenance' run [<options>]
 'git maintenance' start [--scheduler=<scheduler>]
 'git maintenance' (stop|register|unregister) [<options>]
+'git maintenance' is-needed [<options>]
 
 
 DESCRIPTION
@@ -84,6 +85,16 @@ The `unregister` subcommand will report an error if the current repository
 is not already registered. Use the `--force` option to return success even
 when the current repository is not registered.
 
+is-needed::
+    Check whether maintenance needs to be run without actually running it.
+    Exits with a 0 status code if maintenance needs to be run, 1 otherwise.
+    Ideally used with the '--auto' flag.
++
+If one or more `--task` options are specified, then those tasks are checked
+in that order. Otherwise, the tasks are determined by which
+`maintenance.<task>.enabled` config options are true. By default, only
+`maintenance.gc.enabled` is true.
+
 TASKS
 -----
 
@@ -183,6 +194,8 @@ OPTIONS
 	in the `gc.auto` config setting, or when the number of pack-files
 	exceeds the `gc.autoPackLimit` config setting. Not compatible with
 	the `--schedule` option.
+	When combined with the `is-needed` subcommand, check if the required
+	thresholds are met without actually running maintenance.
 
 --schedule::
 	When combined with the `run` subcommand, run maintenance tasks

builtin/gc.c

@@ -36,6 +36,7 @@
 #include "reflog.h"
 #include "repack.h"
 #include "rerere.h"
+#include "revision.h"
 #include "blob.h"
 #include "tree.h"
 #include "promisor-remote.h"
@@ -286,12 +287,26 @@ static void maintenance_run_opts_release(struct maintenance_run_opts *opts)
 
 static int pack_refs_condition(UNUSED struct gc_config *cfg)
 {
-	/*
-	 * The auto-repacking logic for refs is handled by the ref backends and
-	 * exposed via `git pack-refs --auto`. We thus always return truish
-	 * here and let the backend decide for us.
-	 */
-	return 1;
+	struct string_list included_refs = STRING_LIST_INIT_NODUP;
+	struct ref_exclusions excludes = REF_EXCLUSIONS_INIT;
+	struct refs_optimize_opts optimize_opts = {
+		.exclusions = &excludes,
+		.includes = &included_refs,
+		.flags = REFS_OPTIMIZE_PRUNE | REFS_OPTIMIZE_AUTO,
+	};
+	bool required;
+
+	/* Check for all refs, similar to 'git refs optimize --all'. */
+	string_list_append(optimize_opts.includes, "*");
+
+	if (refs_optimize_required(get_main_ref_store(the_repository),
+				   &optimize_opts, &required))
+		return 0;
+
+	clear_ref_exclusions(&excludes);
+	string_list_clear(&included_refs, 0);
+
+	return required;
 }
 
 static int maintenance_task_pack_refs(struct maintenance_run_opts *opts,
@@ -1095,9 +1110,6 @@ static int maintenance_opt_schedule(const struct option *opt, const char *arg,
 	return 0;
 }
 
-/* Remember to update object flag allocation in object.h */
-#define SEEN		(1u<<0)
-
 struct cg_auto_data {
 	int num_not_in_graph;
 	int limit;
@@ -3444,7 +3456,67 @@ static int maintenance_stop(int argc, const char **argv, const char *prefix,
 	return update_background_schedule(NULL, 0);
 }
 
-static const char * const builtin_maintenance_usage[] = {
+static const char *const builtin_maintenance_is_needed_usage[] = {
+	"git maintenance is-needed [--task=<task>] [--schedule]",
+	NULL
+};
+
+static int maintenance_is_needed(int argc, const char **argv, const char *prefix,
+				 struct repository *repo UNUSED)
+{
+	struct maintenance_run_opts opts = MAINTENANCE_RUN_OPTS_INIT;
+	struct string_list selected_tasks = STRING_LIST_INIT_DUP;
+	struct gc_config cfg = GC_CONFIG_INIT;
+	struct option options[] = {
+		OPT_BOOL(0, "auto", &opts.auto_flag,
+			 N_("run tasks based on the state of the repository")),
+		OPT_CALLBACK_F(0, "task", &selected_tasks, N_("task"),
+			       N_("check a specific task"),
+			       PARSE_OPT_NONEG, task_option_parse),
+		OPT_END()
+	};
+	bool is_needed = false;
+
+	argc = parse_options(argc, argv, prefix, options,
+			     builtin_maintenance_is_needed_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+	if (argc)
+		usage_with_options(builtin_maintenance_is_needed_usage, options);
+
+	gc_config(&cfg);
+	initialize_task_config(&opts, &selected_tasks);
+
+	if (opts.auto_flag) {
+		for (size_t i = 0; i < opts.tasks_nr; i++) {
+			if (tasks[opts.tasks[i]].auto_condition &&
+			    tasks[opts.tasks[i]].auto_condition(&cfg)) {
+				is_needed = true;
+				break;
+			}
+		}
+	} else {
+		/*
+		 * When not using --auto we always require maintenance right now.
+		 *
+		 * TODO: this certainly is too eager, as some maintenance tasks may
+		 * decide to not do anything because the data structures are already
+		 * fully optimized. We may eventually want to extend the auto
+		 * condition to also cover non-auto runs so that we can detect such
+		 * cases.
+		 */
+		is_needed = true;
+	}
+
+	string_list_clear(&selected_tasks, 0);
+	maintenance_run_opts_release(&opts);
+	gc_config_release(&cfg);
+
+	if (is_needed)
+		return 0;
+	return 1;
+}
+
+static const char *const builtin_maintenance_usage[] = {
 	N_("git maintenance <subcommand> [<options>]"),
 	NULL,
 };
@@ -3461,6 +3533,7 @@ int cmd_maintenance(int argc,
 		OPT_SUBCOMMAND("stop", &fn, maintenance_stop),
 		OPT_SUBCOMMAND("register", &fn, maintenance_register),
 		OPT_SUBCOMMAND("unregister", &fn, maintenance_unregister),
+		OPT_SUBCOMMAND("is-needed", &fn, maintenance_is_needed),
 		OPT_END(),
 	};
 

object.h

@@ -80,7 +80,6 @@ void object_array_init(struct object_array *array);
  * list-objects-filter.c:                                      21
  * bloom.c:                                                    2122
  * builtin/fsck.c:           0--3
- * builtin/gc.c:             0
  * builtin/index-pack.c:                                     2021
  * reflog.c:                           10--12
  * builtin/show-branch.c:    0-------------------------------------------26

refs.c

@@ -2318,6 +2318,13 @@ int refs_optimize(struct ref_store *refs, struct refs_optimize_opts *opts)
 	return refs->be->optimize(refs, opts);
 }
 
+int refs_optimize_required(struct ref_store *refs,
+			   struct refs_optimize_opts *opts,
+			   bool *required)
+{
+	return refs->be->optimize_required(refs, opts, required);
+}
+
 int reference_get_peeled_oid(struct repository *repo,
 			     const struct reference *ref,
 			     struct object_id *peeled_oid)

refs.h

@@ -520,6 +520,13 @@ struct refs_optimize_opts {
  */
 int refs_optimize(struct ref_store *refs, struct refs_optimize_opts *opts);
 
+/*
+ * Check if refs backend can be optimized by calling 'refs_optimize'.
+ */
+int refs_optimize_required(struct ref_store *ref_store,
+			   struct refs_optimize_opts *opts,
+			   bool *required);
+
 /*
  * Setup reflog before using. Fill in err and return -1 on failure.
  */

refs/debug.c

@@ -132,6 +132,17 @@ static int debug_optimize(struct ref_store *ref_store, struct refs_optimize_opts
 	return res;
 }
 
+static int debug_optimize_required(struct ref_store *ref_store,
+				   struct refs_optimize_opts *opts,
+				   bool *required)
+{
+	struct debug_ref_store *drefs = (struct debug_ref_store *)ref_store;
+	int res = drefs->refs->be->optimize_required(drefs->refs, opts, required);
+	trace_printf_key(&trace_refs, "optimize_required: %s, res: %d\n",
+			 required ? "yes" : "no", res);
+	return res;
+}
+
 static int debug_rename_ref(struct ref_store *ref_store, const char *oldref,
 			    const char *newref, const char *logmsg)
 {
@@ -440,6 +451,8 @@ struct ref_storage_be refs_be_debug = {
 	.transaction_abort = debug_transaction_abort,
 
 	.optimize = debug_optimize,
+	.optimize_required = debug_optimize_required,
+
 	.rename_ref = debug_rename_ref,
 	.copy_ref = debug_copy_ref,
 

refs/files-backend.c

@@ -1512,6 +1512,16 @@ static int files_optimize(struct ref_store *ref_store,
 	return 0;
 }
 
+static int files_optimize_required(struct ref_store *ref_store,
+				   struct refs_optimize_opts *opts,
+				   bool *required)
+{
+	struct files_ref_store *refs = files_downcast(ref_store, REF_STORE_READ,
+						      "optimize_required");
+	*required = should_pack_refs(refs, opts);
+	return 0;
+}
+
 /*
  * People using contrib's git-new-workdir have .git/logs/refs ->
  * /some/other/path/.git/logs/refs, and that may live on another device.
@@ -3982,6 +3992,7 @@ struct ref_storage_be refs_be_files = {
 	.transaction_abort = files_transaction_abort,
 
 	.optimize = files_optimize,
+	.optimize_required = files_optimize_required,
 	.rename_ref = files_rename_ref,
 	.copy_ref = files_copy_ref,
 

refs/packed-backend.c

@@ -1784,6 +1784,17 @@ static int packed_optimize(struct ref_store *ref_store UNUSED,
 	return 0;
 }
 
+static int packed_optimize_required(struct ref_store *ref_store UNUSED,
+				    struct refs_optimize_opts *opts UNUSED,
+				    bool *required)
+{
+	/*
+	 * Packed refs are already optimized.
+	 */
+	*required = false;
+	return 0;
+}
+
 static struct ref_iterator *packed_reflog_iterator_begin(struct ref_store *ref_store UNUSED)
 {
 	return empty_ref_iterator_begin();
@@ -2130,6 +2141,8 @@ struct ref_storage_be refs_be_packed = {
 	.transaction_abort = packed_transaction_abort,
 
 	.optimize = packed_optimize,
+	.optimize_required = packed_optimize_required,
+
 	.rename_ref = NULL,
 	.copy_ref = NULL,
 

refs/refs-internal.h

@@ -424,6 +424,11 @@ typedef int ref_transaction_commit_fn(struct ref_store *refs,
 
 typedef int optimize_fn(struct ref_store *ref_store,
 			struct refs_optimize_opts *opts);
+
+typedef int optimize_required_fn(struct ref_store *ref_store,
+				 struct refs_optimize_opts *opts,
+				 bool *required);
+
 typedef int rename_ref_fn(struct ref_store *ref_store,
 			  const char *oldref, const char *newref,
 			  const char *logmsg);
@@ -549,6 +554,7 @@ struct ref_storage_be {
 	ref_transaction_abort_fn *transaction_abort;
 
 	optimize_fn *optimize;
+	optimize_required_fn *optimize_required;
 	rename_ref_fn *rename_ref;
 	copy_ref_fn *copy_ref;
 

refs/reftable-backend.c

@@ -1733,6 +1733,29 @@ static int reftable_be_optimize(struct ref_store *ref_store,
 	return ret;
 }
 
+static int reftable_be_optimize_required(struct ref_store *ref_store,
+					 struct refs_optimize_opts *opts,
+					 bool *required)
+{
+	struct reftable_ref_store *refs = reftable_be_downcast(ref_store, REF_STORE_READ,
+							       "optimize_refs_required");
+	struct reftable_stack *stack;
+	bool use_heuristics = false;
+
+	if (refs->err)
+		return refs->err;
+
+	stack = refs->worktree_backend.stack;
+	if (!stack)
+		stack = refs->main_backend.stack;
+
+	if (opts->flags & REFS_OPTIMIZE_AUTO)
+		use_heuristics = true;
+
+	return reftable_stack_compaction_required(stack, use_heuristics,
+						  required);
+}
+
 struct write_create_symref_arg {
 	struct reftable_ref_store *refs;
 	struct reftable_stack *stack;
@@ -2756,6 +2779,8 @@ struct ref_storage_be refs_be_reftable = {
 	.transaction_abort = reftable_be_transaction_abort,
 
 	.optimize = reftable_be_optimize,
+	.optimize_required = reftable_be_optimize_required,
+
 	.rename_ref = reftable_be_rename_ref,
 	.copy_ref = reftable_be_copy_ref,