Revision 2057d75038541cd16debb1c55f3f897fd244965c authored by Derrick Stolee on 17 September 2020, 18:11:42 UTC, committed by Junio C Hamano on 17 September 2020, 18:30:04 UTC
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 <jrnieder@gmail.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent 887952b
Raw File
alloc.c
/*
 * alloc.c  - specialized allocator for internal objects
 *
 * Copyright (C) 2006 Linus Torvalds
 *
 * The standard malloc/free wastes too much space for objects, partly because
 * it maintains all the allocation infrastructure, but even more because it ends
 * up with maximal alignment because it doesn't know what the object alignment
 * for the new allocation is.
 */
#include "cache.h"
#include "object.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "tag.h"
#include "alloc.h"

#define BLOCKING 1024

union any_object {
	struct object object;
	struct blob blob;
	struct tree tree;
	struct commit commit;
	struct tag tag;
};

struct alloc_state {
	int count; /* total number of nodes allocated */
	int nr;    /* number of nodes left in current allocation */
	void *p;   /* first free node in current allocation */

	/* bookkeeping of allocations */
	void **slabs;
	int slab_nr, slab_alloc;
};

struct alloc_state *allocate_alloc_state(void)
{
	return xcalloc(1, sizeof(struct alloc_state));
}

void clear_alloc_state(struct alloc_state *s)
{
	while (s->slab_nr > 0) {
		s->slab_nr--;
		free(s->slabs[s->slab_nr]);
	}

	FREE_AND_NULL(s->slabs);
}

static inline void *alloc_node(struct alloc_state *s, size_t node_size)
{
	void *ret;

	if (!s->nr) {
		s->nr = BLOCKING;
		s->p = xmalloc(BLOCKING * node_size);

		ALLOC_GROW(s->slabs, s->slab_nr + 1, s->slab_alloc);
		s->slabs[s->slab_nr++] = s->p;
	}
	s->nr--;
	s->count++;
	ret = s->p;
	s->p = (char *)s->p + node_size;
	memset(ret, 0, node_size);

	return ret;
}

void *alloc_blob_node(struct repository *r)
{
	struct blob *b = alloc_node(r->parsed_objects->blob_state, sizeof(struct blob));
	b->object.type = OBJ_BLOB;
	return b;
}

void *alloc_tree_node(struct repository *r)
{
	struct tree *t = alloc_node(r->parsed_objects->tree_state, sizeof(struct tree));
	t->object.type = OBJ_TREE;
	return t;
}

void *alloc_tag_node(struct repository *r)
{
	struct tag *t = alloc_node(r->parsed_objects->tag_state, sizeof(struct tag));
	t->object.type = OBJ_TAG;
	return t;
}

void *alloc_object_node(struct repository *r)
{
	struct object *obj = alloc_node(r->parsed_objects->object_state, sizeof(union any_object));
	obj->type = OBJ_NONE;
	return obj;
}

/*
 * The returned count is to be used as an index into commit slabs,
 * that are *NOT* maintained per repository, and that is why a single
 * global counter is used.
 */
static unsigned int alloc_commit_index(void)
{
	static unsigned int parsed_commits_count;
	return parsed_commits_count++;
}

void init_commit_node(struct commit *c)
{
	c->object.type = OBJ_COMMIT;
	c->index = alloc_commit_index();
}

void *alloc_commit_node(struct repository *r)
{
	struct commit *c = alloc_node(r->parsed_objects->commit_state, sizeof(struct commit));
	init_commit_node(c);
	return c;
}

static void report(const char *name, unsigned int count, size_t size)
{
	fprintf(stderr, "%10s: %8u (%"PRIuMAX" kB)\n",
			name, count, (uintmax_t) size);
}

#define REPORT(name, type)	\
    report(#name, r->parsed_objects->name##_state->count, \
		  r->parsed_objects->name##_state->count * sizeof(type) >> 10)

void alloc_report(struct repository *r)
{
	REPORT(blob, struct blob);
	REPORT(tree, struct tree);
	REPORT(commit, struct commit);
	REPORT(tag, struct tag);
	REPORT(object, union any_object);
}
back to top