#define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
#define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
#define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
+#define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
#define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
char *get_commit_graph_filename(const char *obj_dir)
{
- return xstrfmt("%s/info/commit-graph", obj_dir);
+ char *filename = xstrfmt("%s/info/commit-graph", obj_dir);
+ char *normalized = xmalloc(strlen(filename) + 1);
+ normalize_path_copy(normalized, filename);
+ free(filename);
+ return normalized;
+}
+
+static char *get_split_graph_filename(const char *obj_dir,
+ const char *oid_hex)
+{
+ char *filename = xstrfmt("%s/info/commit-graphs/graph-%s.graph",
+ obj_dir,
+ oid_hex);
+ char *normalized = xmalloc(strlen(filename) + 1);
+ normalize_path_copy(normalized, filename);
+ free(filename);
+ return normalized;
+}
+
+static char *get_chain_filename(const char *obj_dir)
+{
+ return xstrfmt("%s/info/commit-graphs/commit-graph-chain", obj_dir);
}
static uint8_t oid_version(void)
else
graph->chunk_extra_edges = data + chunk_offset;
break;
+
+ case GRAPH_CHUNKID_BASE:
+ if (graph->chunk_base_graphs)
+ chunk_repeated = 1;
+ else
+ graph->chunk_base_graphs = data + chunk_offset;
}
if (chunk_repeated) {
last_chunk_offset = chunk_offset;
}
+ hashcpy(graph->oid.hash, graph->data + graph->data_len - graph->hash_len);
+
if (verify_commit_graph_lite(graph)) {
free(graph);
return NULL;
struct stat st;
int fd;
+ struct commit_graph *g;
int open_ok = open_commit_graph(graph_file, &fd, &st);
if (!open_ok)
return NULL;
- return load_commit_graph_one_fd_st(fd, &st);
+ g = load_commit_graph_one_fd_st(fd, &st);
+
+ if (g)
+ g->filename = xstrdup(graph_file);
+
+ return g;
+}
+
+static struct commit_graph *load_commit_graph_v1(struct repository *r, const char *obj_dir)
+{
+ char *graph_name = get_commit_graph_filename(obj_dir);
+ struct commit_graph *g = load_commit_graph_one(graph_name);
+ free(graph_name);
+
+ if (g)
+ g->obj_dir = obj_dir;
+
+ return g;
+}
+
+static int add_graph_to_chain(struct commit_graph *g,
+ struct commit_graph *chain,
+ struct object_id *oids,
+ int n)
+{
+ struct commit_graph *cur_g = chain;
+
+ if (n && !g->chunk_base_graphs) {
+ warning(_("commit-graph has no base graphs chunk"));
+ return 0;
+ }
+
+ while (n) {
+ n--;
+
+ if (!cur_g ||
+ !oideq(&oids[n], &cur_g->oid) ||
+ !hasheq(oids[n].hash, g->chunk_base_graphs + g->hash_len * n)) {
+ warning(_("commit-graph chain does not match"));
+ return 0;
+ }
+
+ cur_g = cur_g->base_graph;
+ }
+
+ g->base_graph = chain;
+
+ if (chain)
+ g->num_commits_in_base = chain->num_commits + chain->num_commits_in_base;
+
+ return 1;
+}
+
+static struct commit_graph *load_commit_graph_chain(struct repository *r, const char *obj_dir)
+{
+ struct commit_graph *graph_chain = NULL;
+ struct strbuf line = STRBUF_INIT;
+ struct stat st;
+ struct object_id *oids;
+ int i = 0, valid = 1, count;
+ char *chain_name = get_chain_filename(obj_dir);
+ FILE *fp;
+ int stat_res;
+
+ fp = fopen(chain_name, "r");
+ stat_res = stat(chain_name, &st);
+ free(chain_name);
+
+ if (!fp ||
+ stat_res ||
+ st.st_size <= the_hash_algo->hexsz)
+ return NULL;
+
+ count = st.st_size / (the_hash_algo->hexsz + 1);
+ oids = xcalloc(count, sizeof(struct object_id));
+
+ prepare_alt_odb(r);
+
+ for (i = 0; i < count; i++) {
+ struct object_directory *odb;
+
+ if (strbuf_getline_lf(&line, fp) == EOF)
+ break;
+
+ if (get_oid_hex(line.buf, &oids[i])) {
+ warning(_("invalid commit-graph chain: line '%s' not a hash"),
+ line.buf);
+ valid = 0;
+ break;
+ }
+
+ valid = 0;
+ for (odb = r->objects->odb; odb; odb = odb->next) {
+ char *graph_name = get_split_graph_filename(odb->path, line.buf);
+ struct commit_graph *g = load_commit_graph_one(graph_name);
+
+ free(graph_name);
+
+ if (g) {
+ g->obj_dir = odb->path;
+
+ if (add_graph_to_chain(g, graph_chain, oids, i)) {
+ graph_chain = g;
+ valid = 1;
+ }
+
+ break;
+ }
+ }
+
+ if (!valid) {
+ warning(_("unable to find all commit-graph files"));
+ break;
+ }
+ }
+
+ free(oids);
+ fclose(fp);
+ strbuf_release(&line);
+
+ return graph_chain;
+}
+
+struct commit_graph *read_commit_graph_one(struct repository *r, const char *obj_dir)
+{
+ struct commit_graph *g = load_commit_graph_v1(r, obj_dir);
+
+ if (!g)
+ g = load_commit_graph_chain(r, obj_dir);
+
+ return g;
}
static void prepare_commit_graph_one(struct repository *r, const char *obj_dir)
{
- char *graph_name;
if (r->objects->commit_graph)
return;
- graph_name = get_commit_graph_filename(obj_dir);
- r->objects->commit_graph =
- load_commit_graph_one(graph_name);
-
- FREE_AND_NULL(graph_name);
+ r->objects->commit_graph = read_commit_graph_one(r, obj_dir);
}
/*
return !!first_generation;
}
-void close_commit_graph(struct repository *r)
+static void close_commit_graph_one(struct commit_graph *g)
+{
+ if (!g)
+ return;
+
+ close_commit_graph_one(g->base_graph);
+ free_commit_graph(g);
+}
+
+void close_commit_graph(struct raw_object_store *o)
{
- free_commit_graph(r->objects->commit_graph);
- r->objects->commit_graph = NULL;
+ close_commit_graph_one(o->commit_graph);
+ o->commit_graph = NULL;
}
static int bsearch_graph(struct commit_graph *g, struct object_id *oid, uint32_t *pos)
g->chunk_oid_lookup, g->hash_len, pos);
}
+static void load_oid_from_graph(struct commit_graph *g,
+ uint32_t pos,
+ struct object_id *oid)
+{
+ uint32_t lex_index;
+
+ while (g && pos < g->num_commits_in_base)
+ g = g->base_graph;
+
+ if (!g)
+ BUG("NULL commit-graph");
+
+ if (pos >= g->num_commits + g->num_commits_in_base)
+ die(_("invalid commit position. commit-graph is likely corrupt"));
+
+ lex_index = pos - g->num_commits_in_base;
+
+ hashcpy(oid->hash, g->chunk_oid_lookup + g->hash_len * lex_index);
+}
+
static struct commit_list **insert_parent_or_die(struct repository *r,
struct commit_graph *g,
- uint64_t pos,
+ uint32_t pos,
struct commit_list **pptr)
{
struct commit *c;
struct object_id oid;
- if (pos >= g->num_commits)
- die("invalid parent position %"PRIu64, pos);
+ if (pos >= g->num_commits + g->num_commits_in_base)
+ die("invalid parent position %"PRIu32, pos);
- hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * pos);
+ load_oid_from_graph(g, pos, &oid);
c = lookup_commit(r, &oid);
if (!c)
die(_("could not find commit %s"), oid_to_hex(&oid));
static void fill_commit_graph_info(struct commit *item, struct commit_graph *g, uint32_t pos)
{
- const unsigned char *commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * pos;
+ const unsigned char *commit_data;
+ uint32_t lex_index;
+
+ while (pos < g->num_commits_in_base)
+ g = g->base_graph;
+
+ lex_index = pos - g->num_commits_in_base;
+ commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * lex_index;
item->graph_pos = pos;
item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
}
uint32_t *parent_data_ptr;
uint64_t date_low, date_high;
struct commit_list **pptr;
- const unsigned char *commit_data = g->chunk_commit_data + (g->hash_len + 16) * pos;
+ const unsigned char *commit_data;
+ uint32_t lex_index;
- item->object.parsed = 1;
+ while (pos < g->num_commits_in_base)
+ g = g->base_graph;
+
+ if (pos >= g->num_commits + g->num_commits_in_base)
+ die(_("invalid commit position. commit-graph is likely corrupt"));
+
+ /*
+ * Store the "full" position, but then use the
+ * "local" position for the rest of the calculation.
+ */
item->graph_pos = pos;
+ lex_index = pos - g->num_commits_in_base;
+
+ commit_data = g->chunk_commit_data + (g->hash_len + 16) * lex_index;
+
+ item->object.parsed = 1;
set_commit_tree(item, NULL);
*pos = item->graph_pos;
return 1;
} else {
- return bsearch_graph(g, &(item->object.oid), pos);
+ struct commit_graph *cur_g = g;
+ uint32_t lex_index;
+
+ while (cur_g && !bsearch_graph(cur_g, &(item->object.oid), &lex_index))
+ cur_g = cur_g->base_graph;
+
+ if (cur_g) {
+ *pos = lex_index + cur_g->num_commits_in_base;
+ return 1;
+ }
+
+ return 0;
}
}
struct commit *c)
{
struct object_id oid;
- const unsigned char *commit_data = g->chunk_commit_data +
- GRAPH_DATA_WIDTH * (c->graph_pos);
+ const unsigned char *commit_data;
+
+ while (c->graph_pos < g->num_commits_in_base)
+ g = g->base_graph;
+
+ commit_data = g->chunk_commit_data +
+ GRAPH_DATA_WIDTH * (c->graph_pos - g->num_commits_in_base);
hashcpy(oid.hash, commit_data);
set_commit_tree(c, lookup_tree(r, &oid));
return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
}
+struct packed_commit_list {
+ struct commit **list;
+ int nr;
+ int alloc;
+};
+
+struct packed_oid_list {
+ struct object_id *list;
+ int nr;
+ int alloc;
+};
+
+struct write_commit_graph_context {
+ struct repository *r;
+ char *obj_dir;
+ char *graph_name;
+ struct packed_oid_list oids;
+ struct packed_commit_list commits;
+ int num_extra_edges;
+ unsigned long approx_nr_objects;
+ struct progress *progress;
+ int progress_done;
+ uint64_t progress_cnt;
+
+ char *base_graph_name;
+ int num_commit_graphs_before;
+ int num_commit_graphs_after;
+ char **commit_graph_filenames_before;
+ char **commit_graph_filenames_after;
+ char **commit_graph_hash_after;
+ uint32_t new_num_commits_in_base;
+ struct commit_graph *new_base_graph;
+
+ unsigned append:1,
+ report_progress:1,
+ split:1;
+
+ const struct split_commit_graph_opts *split_opts;
+};
+
static void write_graph_chunk_fanout(struct hashfile *f,
- struct commit **commits,
- int nr_commits,
- struct progress *progress,
- uint64_t *progress_cnt)
+ struct write_commit_graph_context *ctx)
{
int i, count = 0;
- struct commit **list = commits;
+ struct commit **list = ctx->commits.list;
/*
* Write the first-level table (the list is sorted,
* having to do eight extra binary search iterations).
*/
for (i = 0; i < 256; i++) {
- while (count < nr_commits) {
+ while (count < ctx->commits.nr) {
if ((*list)->object.oid.hash[0] != i)
break;
- display_progress(progress, ++*progress_cnt);
+ display_progress(ctx->progress, ++ctx->progress_cnt);
count++;
list++;
}
}
static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
- struct commit **commits, int nr_commits,
- struct progress *progress,
- uint64_t *progress_cnt)
+ struct write_commit_graph_context *ctx)
{
- struct commit **list = commits;
+ struct commit **list = ctx->commits.list;
int count;
- for (count = 0; count < nr_commits; count++, list++) {
- display_progress(progress, ++*progress_cnt);
+ for (count = 0; count < ctx->commits.nr; count++, list++) {
+ display_progress(ctx->progress, ++ctx->progress_cnt);
hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
}
}
}
static void write_graph_chunk_data(struct hashfile *f, int hash_len,
- struct commit **commits, int nr_commits,
- struct progress *progress,
- uint64_t *progress_cnt)
+ struct write_commit_graph_context *ctx)
{
- struct commit **list = commits;
- struct commit **last = commits + nr_commits;
+ struct commit **list = ctx->commits.list;
+ struct commit **last = ctx->commits.list + ctx->commits.nr;
uint32_t num_extra_edges = 0;
while (list < last) {
struct commit_list *parent;
int edge_value;
uint32_t packedDate[2];
- display_progress(progress, ++*progress_cnt);
+ display_progress(ctx->progress, ++ctx->progress_cnt);
parse_commit_no_graph(*list);
hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len);
edge_value = GRAPH_PARENT_NONE;
else {
edge_value = sha1_pos(parent->item->object.oid.hash,
- commits,
- nr_commits,
+ ctx->commits.list,
+ ctx->commits.nr,
commit_to_sha1);
+ if (edge_value >= 0)
+ edge_value += ctx->new_num_commits_in_base;
+ else {
+ uint32_t pos;
+ if (find_commit_in_graph(parent->item,
+ ctx->new_base_graph,
+ &pos))
+ edge_value = pos;
+ }
+
if (edge_value < 0)
BUG("missing parent %s for commit %s",
oid_to_hex(&parent->item->object.oid),
edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges;
else {
edge_value = sha1_pos(parent->item->object.oid.hash,
- commits,
- nr_commits,
+ ctx->commits.list,
+ ctx->commits.nr,
commit_to_sha1);
+
+ if (edge_value >= 0)
+ edge_value += ctx->new_num_commits_in_base;
+ else {
+ uint32_t pos;
+ if (find_commit_in_graph(parent->item,
+ ctx->new_base_graph,
+ &pos))
+ edge_value = pos;
+ }
+
if (edge_value < 0)
BUG("missing parent %s for commit %s",
oid_to_hex(&parent->item->object.oid),
}
static void write_graph_chunk_extra_edges(struct hashfile *f,
- struct commit **commits,
- int nr_commits,
- struct progress *progress,
- uint64_t *progress_cnt)
+ struct write_commit_graph_context *ctx)
{
- struct commit **list = commits;
- struct commit **last = commits + nr_commits;
+ struct commit **list = ctx->commits.list;
+ struct commit **last = ctx->commits.list + ctx->commits.nr;
struct commit_list *parent;
while (list < last) {
int num_parents = 0;
- display_progress(progress, ++*progress_cnt);
+ display_progress(ctx->progress, ++ctx->progress_cnt);
for (parent = (*list)->parents; num_parents < 3 && parent;
parent = parent->next)
/* Since num_parents > 2, this initializer is safe. */
for (parent = (*list)->parents->next; parent; parent = parent->next) {
int edge_value = sha1_pos(parent->item->object.oid.hash,
- commits,
- nr_commits,
+ ctx->commits.list,
+ ctx->commits.nr,
commit_to_sha1);
+ if (edge_value >= 0)
+ edge_value += ctx->new_num_commits_in_base;
+ else {
+ uint32_t pos;
+ if (find_commit_in_graph(parent->item,
+ ctx->new_base_graph,
+ &pos))
+ edge_value = pos;
+ }
+
if (edge_value < 0)
BUG("missing parent %s for commit %s",
oid_to_hex(&parent->item->object.oid),
}
}
-static int commit_compare(const void *_a, const void *_b)
+static int oid_compare(const void *_a, const void *_b)
{
const struct object_id *a = (const struct object_id *)_a;
const struct object_id *b = (const struct object_id *)_b;
return oidcmp(a, b);
}
-struct packed_commit_list {
- struct commit **list;
- int nr;
- int alloc;
-};
-
-struct packed_oid_list {
- struct object_id *list;
- int nr;
- int alloc;
- struct progress *progress;
- int progress_done;
-};
-
static int add_packed_commits(const struct object_id *oid,
struct packed_git *pack,
uint32_t pos,
void *data)
{
- struct packed_oid_list *list = (struct packed_oid_list*)data;
+ struct write_commit_graph_context *ctx = (struct write_commit_graph_context*)data;
enum object_type type;
off_t offset = nth_packed_object_offset(pack, pos);
struct object_info oi = OBJECT_INFO_INIT;
- if (list->progress)
- display_progress(list->progress, ++list->progress_done);
+ if (ctx->progress)
+ display_progress(ctx->progress, ++ctx->progress_done);
oi.typep = &type;
- if (packed_object_info(the_repository, pack, offset, &oi) < 0)
+ if (packed_object_info(ctx->r, pack, offset, &oi) < 0)
die(_("unable to get type of object %s"), oid_to_hex(oid));
if (type != OBJ_COMMIT)
return 0;
- ALLOC_GROW(list->list, list->nr + 1, list->alloc);
- oidcpy(&(list->list[list->nr]), oid);
- list->nr++;
+ ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+ oidcpy(&(ctx->oids.list[ctx->oids.nr]), oid);
+ ctx->oids.nr++;
return 0;
}
-static void add_missing_parents(struct packed_oid_list *oids, struct commit *commit)
+static void add_missing_parents(struct write_commit_graph_context *ctx, struct commit *commit)
{
struct commit_list *parent;
for (parent = commit->parents; parent; parent = parent->next) {
if (!(parent->item->object.flags & UNINTERESTING)) {
- ALLOC_GROW(oids->list, oids->nr + 1, oids->alloc);
- oidcpy(&oids->list[oids->nr], &(parent->item->object.oid));
- oids->nr++;
+ ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+ oidcpy(&ctx->oids.list[ctx->oids.nr], &(parent->item->object.oid));
+ ctx->oids.nr++;
parent->item->object.flags |= UNINTERESTING;
}
}
}
-static void close_reachable(struct packed_oid_list *oids, int report_progress)
+static void close_reachable(struct write_commit_graph_context *ctx)
{
int i;
struct commit *commit;
- struct progress *progress = NULL;
- if (report_progress)
- progress = start_delayed_progress(
- _("Loading known commits in commit graph"), oids->nr);
- for (i = 0; i < oids->nr; i++) {
- display_progress(progress, i + 1);
- commit = lookup_commit(the_repository, &oids->list[i]);
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
+ _("Loading known commits in commit graph"),
+ ctx->oids.nr);
+ for (i = 0; i < ctx->oids.nr; i++) {
+ display_progress(ctx->progress, i + 1);
+ commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
if (commit)
commit->object.flags |= UNINTERESTING;
}
- stop_progress(&progress);
+ stop_progress(&ctx->progress);
/*
- * As this loop runs, oids->nr may grow, but not more
+ * As this loop runs, ctx->oids.nr may grow, but not more
* than the number of missing commits in the reachable
* closure.
*/
- if (report_progress)
- progress = start_delayed_progress(
- _("Expanding reachable commits in commit graph"), oids->nr);
- for (i = 0; i < oids->nr; i++) {
- display_progress(progress, i + 1);
- commit = lookup_commit(the_repository, &oids->list[i]);
-
- if (commit && !parse_commit_no_graph(commit))
- add_missing_parents(oids, commit);
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
+ _("Expanding reachable commits in commit graph"),
+ ctx->oids.nr);
+ for (i = 0; i < ctx->oids.nr; i++) {
+ display_progress(ctx->progress, i + 1);
+ commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
+
+ if (!commit)
+ continue;
+ if (ctx->split) {
+ if (!parse_commit(commit) &&
+ commit->graph_pos == COMMIT_NOT_FROM_GRAPH)
+ add_missing_parents(ctx, commit);
+ } else if (!parse_commit_no_graph(commit))
+ add_missing_parents(ctx, commit);
}
- stop_progress(&progress);
+ stop_progress(&ctx->progress);
- if (report_progress)
- progress = start_delayed_progress(
- _("Clearing commit marks in commit graph"), oids->nr);
- for (i = 0; i < oids->nr; i++) {
- display_progress(progress, i + 1);
- commit = lookup_commit(the_repository, &oids->list[i]);
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
+ _("Clearing commit marks in commit graph"),
+ ctx->oids.nr);
+ for (i = 0; i < ctx->oids.nr; i++) {
+ display_progress(ctx->progress, i + 1);
+ commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
if (commit)
commit->object.flags &= ~UNINTERESTING;
}
- stop_progress(&progress);
+ stop_progress(&ctx->progress);
}
-static void compute_generation_numbers(struct packed_commit_list* commits,
- int report_progress)
+static void compute_generation_numbers(struct write_commit_graph_context *ctx)
{
int i;
struct commit_list *list = NULL;
- struct progress *progress = NULL;
- if (report_progress)
- progress = start_progress(
- _("Computing commit graph generation numbers"),
- commits->nr);
- for (i = 0; i < commits->nr; i++) {
- display_progress(progress, i + 1);
- if (commits->list[i]->generation != GENERATION_NUMBER_INFINITY &&
- commits->list[i]->generation != GENERATION_NUMBER_ZERO)
+ if (ctx->report_progress)
+ ctx->progress = start_progress(
+ _("Computing commit graph generation numbers"),
+ ctx->commits.nr);
+ for (i = 0; i < ctx->commits.nr; i++) {
+ display_progress(ctx->progress, i + 1);
+ if (ctx->commits.list[i]->generation != GENERATION_NUMBER_INFINITY &&
+ ctx->commits.list[i]->generation != GENERATION_NUMBER_ZERO)
continue;
- commit_list_insert(commits->list[i], &list);
+ commit_list_insert(ctx->commits.list[i], &list);
while (list) {
struct commit *current = list->item;
struct commit_list *parent;
}
}
}
- stop_progress(&progress);
+ stop_progress(&ctx->progress);
}
static int add_ref_to_list(const char *refname,
return 0;
}
-void write_commit_graph_reachable(const char *obj_dir, int append,
- int report_progress)
+int write_commit_graph_reachable(const char *obj_dir, unsigned int flags,
+ const struct split_commit_graph_opts *split_opts)
{
struct string_list list = STRING_LIST_INIT_DUP;
+ int result;
for_each_ref(add_ref_to_list, &list);
- write_commit_graph(obj_dir, NULL, &list, append, report_progress);
+ result = write_commit_graph(obj_dir, NULL, &list,
+ flags, split_opts);
string_list_clear(&list, 0);
+ return result;
}
-void write_commit_graph(const char *obj_dir,
- struct string_list *pack_indexes,
- struct string_list *commit_hex,
- int append, int report_progress)
+static int fill_oids_from_packs(struct write_commit_graph_context *ctx,
+ struct string_list *pack_indexes)
{
- struct packed_oid_list oids;
- struct packed_commit_list commits;
- struct hashfile *f;
- uint32_t i, count_distinct = 0;
- char *graph_name;
- struct lock_file lk = LOCK_INIT;
- uint32_t chunk_ids[5];
- uint64_t chunk_offsets[5];
- int num_chunks;
- int num_extra_edges;
- struct commit_list *parent;
- struct progress *progress = NULL;
- const unsigned hashsz = the_hash_algo->rawsz;
- uint64_t progress_cnt = 0;
+ uint32_t i;
struct strbuf progress_title = STRBUF_INIT;
- unsigned long approx_nr_objects;
-
- if (!commit_graph_compatible(the_repository))
- return;
+ struct strbuf packname = STRBUF_INIT;
+ int dirlen;
- oids.nr = 0;
- approx_nr_objects = approximate_object_count();
- oids.alloc = approx_nr_objects / 32;
- oids.progress = NULL;
- oids.progress_done = 0;
-
- if (append) {
- prepare_commit_graph_one(the_repository, obj_dir);
- if (the_repository->objects->commit_graph)
- oids.alloc += the_repository->objects->commit_graph->num_commits;
- }
-
- if (oids.alloc < 1024)
- oids.alloc = 1024;
- ALLOC_ARRAY(oids.list, oids.alloc);
-
- if (append && the_repository->objects->commit_graph) {
- struct commit_graph *commit_graph =
- the_repository->objects->commit_graph;
- for (i = 0; i < commit_graph->num_commits; i++) {
- const unsigned char *hash = commit_graph->chunk_oid_lookup +
- commit_graph->hash_len * i;
- hashcpy(oids.list[oids.nr++].hash, hash);
- }
+ strbuf_addf(&packname, "%s/pack/", ctx->obj_dir);
+ dirlen = packname.len;
+ if (ctx->report_progress) {
+ strbuf_addf(&progress_title,
+ Q_("Finding commits for commit graph in %d pack",
+ "Finding commits for commit graph in %d packs",
+ pack_indexes->nr),
+ pack_indexes->nr);
+ ctx->progress = start_delayed_progress(progress_title.buf, 0);
+ ctx->progress_done = 0;
}
-
- if (pack_indexes) {
- struct strbuf packname = STRBUF_INIT;
- int dirlen;
- strbuf_addf(&packname, "%s/pack/", obj_dir);
- dirlen = packname.len;
- if (report_progress) {
- strbuf_addf(&progress_title,
- Q_("Finding commits for commit graph in %d pack",
- "Finding commits for commit graph in %d packs",
- pack_indexes->nr),
- pack_indexes->nr);
- oids.progress = start_delayed_progress(progress_title.buf, 0);
- oids.progress_done = 0;
- }
- for (i = 0; i < pack_indexes->nr; i++) {
- struct packed_git *p;
- strbuf_setlen(&packname, dirlen);
- strbuf_addstr(&packname, pack_indexes->items[i].string);
- p = add_packed_git(packname.buf, packname.len, 1);
- if (!p)
- die(_("error adding pack %s"), packname.buf);
- if (open_pack_index(p))
- die(_("error opening index for %s"), packname.buf);
- for_each_object_in_pack(p, add_packed_commits, &oids,
- FOR_EACH_OBJECT_PACK_ORDER);
- close_pack(p);
- free(p);
+ for (i = 0; i < pack_indexes->nr; i++) {
+ struct packed_git *p;
+ strbuf_setlen(&packname, dirlen);
+ strbuf_addstr(&packname, pack_indexes->items[i].string);
+ p = add_packed_git(packname.buf, packname.len, 1);
+ if (!p) {
+ error(_("error adding pack %s"), packname.buf);
+ return -1;
}
- stop_progress(&oids.progress);
- strbuf_reset(&progress_title);
- strbuf_release(&packname);
- }
-
- if (commit_hex) {
- if (report_progress) {
- strbuf_addf(&progress_title,
- Q_("Finding commits for commit graph from %d ref",
- "Finding commits for commit graph from %d refs",
- commit_hex->nr),
- commit_hex->nr);
- progress = start_delayed_progress(progress_title.buf,
- commit_hex->nr);
- }
- for (i = 0; i < commit_hex->nr; i++) {
- const char *end;
- struct object_id oid;
- struct commit *result;
-
- display_progress(progress, i + 1);
- if (commit_hex->items[i].string &&
- parse_oid_hex(commit_hex->items[i].string, &oid, &end))
- continue;
-
- result = lookup_commit_reference_gently(the_repository, &oid, 1);
-
- if (result) {
- ALLOC_GROW(oids.list, oids.nr + 1, oids.alloc);
- oidcpy(&oids.list[oids.nr], &(result->object.oid));
- oids.nr++;
- }
+ if (open_pack_index(p)) {
+ error(_("error opening index for %s"), packname.buf);
+ return -1;
}
- stop_progress(&progress);
- strbuf_reset(&progress_title);
+ for_each_object_in_pack(p, add_packed_commits, ctx,
+ FOR_EACH_OBJECT_PACK_ORDER);
+ close_pack(p);
+ free(p);
}
- if (!pack_indexes && !commit_hex) {
- if (report_progress)
- oids.progress = start_delayed_progress(
- _("Finding commits for commit graph among packed objects"),
- approx_nr_objects);
- for_each_packed_object(add_packed_commits, &oids,
- FOR_EACH_OBJECT_PACK_ORDER);
- if (oids.progress_done < approx_nr_objects)
- display_progress(oids.progress, approx_nr_objects);
- stop_progress(&oids.progress);
+ stop_progress(&ctx->progress);
+ strbuf_release(&progress_title);
+ strbuf_release(&packname);
+
+ return 0;
+}
+
+static void fill_oids_from_commit_hex(struct write_commit_graph_context *ctx,
+ struct string_list *commit_hex)
+{
+ uint32_t i;
+ struct strbuf progress_title = STRBUF_INIT;
+
+ if (ctx->report_progress) {
+ strbuf_addf(&progress_title,
+ Q_("Finding commits for commit graph from %d ref",
+ "Finding commits for commit graph from %d refs",
+ commit_hex->nr),
+ commit_hex->nr);
+ ctx->progress = start_delayed_progress(
+ progress_title.buf,
+ commit_hex->nr);
}
+ for (i = 0; i < commit_hex->nr; i++) {
+ const char *end;
+ struct object_id oid;
+ struct commit *result;
+
+ display_progress(ctx->progress, i + 1);
+ if (commit_hex->items[i].string &&
+ parse_oid_hex(commit_hex->items[i].string, &oid, &end))
+ continue;
+
+ result = lookup_commit_reference_gently(ctx->r, &oid, 1);
+
+ if (result) {
+ ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc);
+ oidcpy(&ctx->oids.list[ctx->oids.nr], &(result->object.oid));
+ ctx->oids.nr++;
+ }
+ }
+ stop_progress(&ctx->progress);
+ strbuf_release(&progress_title);
+}
- close_reachable(&oids, report_progress);
+static void fill_oids_from_all_packs(struct write_commit_graph_context *ctx)
+{
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
+ _("Finding commits for commit graph among packed objects"),
+ ctx->approx_nr_objects);
+ for_each_packed_object(add_packed_commits, ctx,
+ FOR_EACH_OBJECT_PACK_ORDER);
+ if (ctx->progress_done < ctx->approx_nr_objects)
+ display_progress(ctx->progress, ctx->approx_nr_objects);
+ stop_progress(&ctx->progress);
+}
+
+static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx)
+{
+ uint32_t i, count_distinct = 1;
- if (report_progress)
- progress = start_delayed_progress(
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
_("Counting distinct commits in commit graph"),
- oids.nr);
- display_progress(progress, 0); /* TODO: Measure QSORT() progress */
- QSORT(oids.list, oids.nr, commit_compare);
- count_distinct = 1;
- for (i = 1; i < oids.nr; i++) {
- display_progress(progress, i + 1);
- if (!oideq(&oids.list[i - 1], &oids.list[i]))
+ ctx->oids.nr);
+ display_progress(ctx->progress, 0); /* TODO: Measure QSORT() progress */
+ QSORT(ctx->oids.list, ctx->oids.nr, oid_compare);
+
+ for (i = 1; i < ctx->oids.nr; i++) {
+ display_progress(ctx->progress, i + 1);
+ if (!oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i])) {
+ if (ctx->split) {
+ struct commit *c = lookup_commit(ctx->r, &ctx->oids.list[i]);
+
+ if (!c || c->graph_pos != COMMIT_NOT_FROM_GRAPH)
+ continue;
+ }
+
count_distinct++;
+ }
}
- stop_progress(&progress);
+ stop_progress(&ctx->progress);
- if (count_distinct >= GRAPH_EDGE_LAST_MASK)
- die(_("the commit graph format cannot write %d commits"), count_distinct);
+ return count_distinct;
+}
- commits.nr = 0;
- commits.alloc = count_distinct;
- ALLOC_ARRAY(commits.list, commits.alloc);
+static void copy_oids_to_commits(struct write_commit_graph_context *ctx)
+{
+ uint32_t i;
+ struct commit_list *parent;
- num_extra_edges = 0;
- if (report_progress)
- progress = start_delayed_progress(
+ ctx->num_extra_edges = 0;
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
_("Finding extra edges in commit graph"),
- oids.nr);
- for (i = 0; i < oids.nr; i++) {
+ ctx->oids.nr);
+ for (i = 0; i < ctx->oids.nr; i++) {
int num_parents = 0;
- display_progress(progress, i + 1);
- if (i > 0 && oideq(&oids.list[i - 1], &oids.list[i]))
+ display_progress(ctx->progress, i + 1);
+ if (i > 0 && oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i]))
continue;
- commits.list[commits.nr] = lookup_commit(the_repository, &oids.list[i]);
- parse_commit_no_graph(commits.list[commits.nr]);
+ ALLOC_GROW(ctx->commits.list, ctx->commits.nr + 1, ctx->commits.alloc);
+ ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]);
- for (parent = commits.list[commits.nr]->parents;
+ if (ctx->split &&
+ ctx->commits.list[ctx->commits.nr]->graph_pos != COMMIT_NOT_FROM_GRAPH)
+ continue;
+
+ parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]);
+
+ for (parent = ctx->commits.list[ctx->commits.nr]->parents;
parent; parent = parent->next)
num_parents++;
if (num_parents > 2)
- num_extra_edges += num_parents - 1;
+ ctx->num_extra_edges += num_parents - 1;
- commits.nr++;
+ ctx->commits.nr++;
}
- num_chunks = num_extra_edges ? 4 : 3;
- stop_progress(&progress);
+ stop_progress(&ctx->progress);
+}
- if (commits.nr >= GRAPH_EDGE_LAST_MASK)
- die(_("too many commits to write graph"));
+static int write_graph_chunk_base_1(struct hashfile *f,
+ struct commit_graph *g)
+{
+ int num = 0;
- compute_generation_numbers(&commits, report_progress);
+ if (!g)
+ return 0;
+
+ num = write_graph_chunk_base_1(f, g->base_graph);
+ hashwrite(f, g->oid.hash, the_hash_algo->rawsz);
+ return num + 1;
+}
- graph_name = get_commit_graph_filename(obj_dir);
- if (safe_create_leading_directories(graph_name)) {
- UNLEAK(graph_name);
- die_errno(_("unable to create leading directories of %s"),
- graph_name);
+static int write_graph_chunk_base(struct hashfile *f,
+ struct write_commit_graph_context *ctx)
+{
+ int num = write_graph_chunk_base_1(f, ctx->new_base_graph);
+
+ if (num != ctx->num_commit_graphs_after - 1) {
+ error(_("failed to write correct number of base graph ids"));
+ return -1;
}
- hold_lock_file_for_update(&lk, graph_name, LOCK_DIE_ON_ERROR);
- f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
+ return 0;
+}
- hashwrite_be32(f, GRAPH_SIGNATURE);
+static int write_commit_graph_file(struct write_commit_graph_context *ctx)
+{
+ uint32_t i;
+ int fd;
+ struct hashfile *f;
+ struct lock_file lk = LOCK_INIT;
+ uint32_t chunk_ids[6];
+ uint64_t chunk_offsets[6];
+ const unsigned hashsz = the_hash_algo->rawsz;
+ struct strbuf progress_title = STRBUF_INIT;
+ int num_chunks = 3;
+ struct object_id file_hash;
- hashwrite_u8(f, GRAPH_VERSION);
- hashwrite_u8(f, oid_version());
- hashwrite_u8(f, num_chunks);
- hashwrite_u8(f, 0); /* unused padding byte */
+ if (ctx->split) {
+ struct strbuf tmp_file = STRBUF_INIT;
+
+ strbuf_addf(&tmp_file,
+ "%s/info/commit-graphs/tmp_graph_XXXXXX",
+ ctx->obj_dir);
+ ctx->graph_name = strbuf_detach(&tmp_file, NULL);
+ } else {
+ ctx->graph_name = get_commit_graph_filename(ctx->obj_dir);
+ }
+
+ if (safe_create_leading_directories(ctx->graph_name)) {
+ UNLEAK(ctx->graph_name);
+ error(_("unable to create leading directories of %s"),
+ ctx->graph_name);
+ return -1;
+ }
+
+ if (ctx->split) {
+ char *lock_name = get_chain_filename(ctx->obj_dir);
+
+ hold_lock_file_for_update(&lk, lock_name, LOCK_DIE_ON_ERROR);
+
+ fd = git_mkstemp_mode(ctx->graph_name, 0444);
+ if (fd < 0) {
+ error(_("unable to create '%s'"), ctx->graph_name);
+ return -1;
+ }
+
+ f = hashfd(fd, ctx->graph_name);
+ } else {
+ hold_lock_file_for_update(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR);
+ fd = lk.tempfile->fd;
+ f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
+ }
chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT;
chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
chunk_ids[2] = GRAPH_CHUNKID_DATA;
- if (num_extra_edges)
- chunk_ids[3] = GRAPH_CHUNKID_EXTRAEDGES;
- else
- chunk_ids[3] = 0;
- chunk_ids[4] = 0;
+ if (ctx->num_extra_edges) {
+ chunk_ids[num_chunks] = GRAPH_CHUNKID_EXTRAEDGES;
+ num_chunks++;
+ }
+ if (ctx->num_commit_graphs_after > 1) {
+ chunk_ids[num_chunks] = GRAPH_CHUNKID_BASE;
+ num_chunks++;
+ }
+
+ chunk_ids[num_chunks] = 0;
chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE;
- chunk_offsets[2] = chunk_offsets[1] + hashsz * commits.nr;
- chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * commits.nr;
- chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges;
+ chunk_offsets[2] = chunk_offsets[1] + hashsz * ctx->commits.nr;
+ chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr;
+
+ num_chunks = 3;
+ if (ctx->num_extra_edges) {
+ chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
+ 4 * ctx->num_extra_edges;
+ num_chunks++;
+ }
+ if (ctx->num_commit_graphs_after > 1) {
+ chunk_offsets[num_chunks + 1] = chunk_offsets[num_chunks] +
+ hashsz * (ctx->num_commit_graphs_after - 1);
+ num_chunks++;
+ }
+
+ hashwrite_be32(f, GRAPH_SIGNATURE);
+
+ hashwrite_u8(f, GRAPH_VERSION);
+ hashwrite_u8(f, oid_version());
+ hashwrite_u8(f, num_chunks);
+ hashwrite_u8(f, ctx->num_commit_graphs_after - 1);
for (i = 0; i <= num_chunks; i++) {
uint32_t chunk_write[3];
hashwrite(f, chunk_write, 12);
}
- if (report_progress) {
+ if (ctx->report_progress) {
strbuf_addf(&progress_title,
Q_("Writing out commit graph in %d pass",
"Writing out commit graph in %d passes",
num_chunks),
num_chunks);
- progress = start_delayed_progress(
+ ctx->progress = start_delayed_progress(
progress_title.buf,
- num_chunks * commits.nr);
+ num_chunks * ctx->commits.nr);
}
- write_graph_chunk_fanout(f, commits.list, commits.nr, progress, &progress_cnt);
- write_graph_chunk_oids(f, hashsz, commits.list, commits.nr, progress, &progress_cnt);
- write_graph_chunk_data(f, hashsz, commits.list, commits.nr, progress, &progress_cnt);
- if (num_extra_edges)
- write_graph_chunk_extra_edges(f, commits.list, commits.nr, progress, &progress_cnt);
- stop_progress(&progress);
+ write_graph_chunk_fanout(f, ctx);
+ write_graph_chunk_oids(f, hashsz, ctx);
+ write_graph_chunk_data(f, hashsz, ctx);
+ if (ctx->num_extra_edges)
+ write_graph_chunk_extra_edges(f, ctx);
+ if (ctx->num_commit_graphs_after > 1 &&
+ write_graph_chunk_base(f, ctx)) {
+ return -1;
+ }
+ stop_progress(&ctx->progress);
strbuf_release(&progress_title);
- close_commit_graph(the_repository);
- finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
+ if (ctx->split && ctx->base_graph_name && ctx->num_commit_graphs_after > 1) {
+ char *new_base_hash = xstrdup(oid_to_hex(&ctx->new_base_graph->oid));
+ char *new_base_name = get_split_graph_filename(ctx->new_base_graph->obj_dir, new_base_hash);
+
+ free(ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 2]);
+ free(ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 2]);
+ ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 2] = new_base_name;
+ ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 2] = new_base_hash;
+ }
+
+ close_commit_graph(ctx->r->objects);
+ finalize_hashfile(f, file_hash.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
+
+ if (ctx->split) {
+ FILE *chainf = fdopen_lock_file(&lk, "w");
+ char *final_graph_name;
+ int result;
+
+ close(fd);
+
+ if (!chainf) {
+ error(_("unable to open commit-graph chain file"));
+ return -1;
+ }
+
+ if (ctx->base_graph_name) {
+ const char *dest = ctx->commit_graph_filenames_after[
+ ctx->num_commit_graphs_after - 2];
+
+ if (strcmp(ctx->base_graph_name, dest)) {
+ result = rename(ctx->base_graph_name, dest);
+
+ if (result) {
+ error(_("failed to rename base commit-graph file"));
+ return -1;
+ }
+ }
+ } else {
+ char *graph_name = get_commit_graph_filename(ctx->obj_dir);
+ unlink(graph_name);
+ }
+
+ ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 1] = xstrdup(oid_to_hex(&file_hash));
+ final_graph_name = get_split_graph_filename(ctx->obj_dir,
+ ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 1]);
+ ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 1] = final_graph_name;
+
+ result = rename(ctx->graph_name, final_graph_name);
+
+ for (i = 0; i < ctx->num_commit_graphs_after; i++)
+ fprintf(lk.tempfile->fp, "%s\n", ctx->commit_graph_hash_after[i]);
+
+ if (result) {
+ error(_("failed to rename temporary commit-graph file"));
+ return -1;
+ }
+ }
+
commit_lock_file(&lk);
- free(graph_name);
- free(commits.list);
- free(oids.list);
+ return 0;
+}
+
+static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
+{
+ struct commit_graph *g = ctx->r->objects->commit_graph;
+ uint32_t num_commits = ctx->commits.nr;
+ uint32_t i;
+
+ int max_commits = 0;
+ int size_mult = 2;
+
+ if (ctx->split_opts) {
+ max_commits = ctx->split_opts->max_commits;
+ size_mult = ctx->split_opts->size_multiple;
+ }
+
+ g = ctx->r->objects->commit_graph;
+ ctx->num_commit_graphs_after = ctx->num_commit_graphs_before + 1;
+
+ while (g && (g->num_commits <= size_mult * num_commits ||
+ (max_commits && num_commits > max_commits))) {
+ if (strcmp(g->obj_dir, ctx->obj_dir))
+ break;
+
+ num_commits += g->num_commits;
+ g = g->base_graph;
+
+ ctx->num_commit_graphs_after--;
+ }
+
+ ctx->new_base_graph = g;
+
+ if (ctx->num_commit_graphs_after == 2) {
+ char *old_graph_name = get_commit_graph_filename(g->obj_dir);
+
+ if (!strcmp(g->filename, old_graph_name) &&
+ strcmp(g->obj_dir, ctx->obj_dir)) {
+ ctx->num_commit_graphs_after = 1;
+ ctx->new_base_graph = NULL;
+ }
+
+ free(old_graph_name);
+ }
+
+ ALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after);
+ ALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after);
+
+ for (i = 0; i < ctx->num_commit_graphs_after &&
+ i < ctx->num_commit_graphs_before; i++)
+ ctx->commit_graph_filenames_after[i] = xstrdup(ctx->commit_graph_filenames_before[i]);
+
+ i = ctx->num_commit_graphs_before - 1;
+ g = ctx->r->objects->commit_graph;
+
+ while (g) {
+ if (i < ctx->num_commit_graphs_after)
+ ctx->commit_graph_hash_after[i] = xstrdup(oid_to_hex(&g->oid));
+
+ i--;
+ g = g->base_graph;
+ }
+}
+
+static void merge_commit_graph(struct write_commit_graph_context *ctx,
+ struct commit_graph *g)
+{
+ uint32_t i;
+ uint32_t offset = g->num_commits_in_base;
+
+ ALLOC_GROW(ctx->commits.list, ctx->commits.nr + g->num_commits, ctx->commits.alloc);
+
+ for (i = 0; i < g->num_commits; i++) {
+ struct object_id oid;
+ struct commit *result;
+
+ display_progress(ctx->progress, i + 1);
+
+ load_oid_from_graph(g, i + offset, &oid);
+
+ /* only add commits if they still exist in the repo */
+ result = lookup_commit_reference_gently(ctx->r, &oid, 1);
+
+ if (result) {
+ ctx->commits.list[ctx->commits.nr] = result;
+ ctx->commits.nr++;
+ }
+ }
+}
+
+static int commit_compare(const void *_a, const void *_b)
+{
+ const struct commit *a = *(const struct commit **)_a;
+ const struct commit *b = *(const struct commit **)_b;
+ return oidcmp(&a->object.oid, &b->object.oid);
+}
+
+static void sort_and_scan_merged_commits(struct write_commit_graph_context *ctx)
+{
+ uint32_t i, num_parents;
+ struct commit_list *parent;
+
+ if (ctx->report_progress)
+ ctx->progress = start_delayed_progress(
+ _("Scanning merged commits"),
+ ctx->commits.nr);
+
+ QSORT(ctx->commits.list, ctx->commits.nr, commit_compare);
+
+ ctx->num_extra_edges = 0;
+ for (i = 0; i < ctx->commits.nr; i++) {
+ display_progress(ctx->progress, i);
+
+ if (i && oideq(&ctx->commits.list[i - 1]->object.oid,
+ &ctx->commits.list[i]->object.oid)) {
+ die(_("unexpected duplicate commit id %s"),
+ oid_to_hex(&ctx->commits.list[i]->object.oid));
+ } else {
+ num_parents = 0;
+ for (parent = ctx->commits.list[i]->parents; parent; parent = parent->next)
+ num_parents++;
+
+ if (num_parents > 2)
+ ctx->num_extra_edges += num_parents - 1;
+ }
+ }
+
+ stop_progress(&ctx->progress);
+}
+
+static void merge_commit_graphs(struct write_commit_graph_context *ctx)
+{
+ struct commit_graph *g = ctx->r->objects->commit_graph;
+ uint32_t current_graph_number = ctx->num_commit_graphs_before;
+ struct strbuf progress_title = STRBUF_INIT;
+
+ while (g && current_graph_number >= ctx->num_commit_graphs_after) {
+ current_graph_number--;
+
+ if (ctx->report_progress) {
+ strbuf_addstr(&progress_title, _("Merging commit-graph"));
+ ctx->progress = start_delayed_progress(progress_title.buf, 0);
+ }
+
+ merge_commit_graph(ctx, g);
+ stop_progress(&ctx->progress);
+ strbuf_release(&progress_title);
+
+ g = g->base_graph;
+ }
+
+ if (g) {
+ ctx->new_base_graph = g;
+ ctx->new_num_commits_in_base = g->num_commits + g->num_commits_in_base;
+ }
+
+ if (ctx->new_base_graph)
+ ctx->base_graph_name = xstrdup(ctx->new_base_graph->filename);
+
+ sort_and_scan_merged_commits(ctx);
+}
+
+static void mark_commit_graphs(struct write_commit_graph_context *ctx)
+{
+ uint32_t i;
+ time_t now = time(NULL);
+
+ for (i = ctx->num_commit_graphs_after - 1; i < ctx->num_commit_graphs_before; i++) {
+ struct stat st;
+ struct utimbuf updated_time;
+
+ stat(ctx->commit_graph_filenames_before[i], &st);
+
+ updated_time.actime = st.st_atime;
+ updated_time.modtime = now;
+ utime(ctx->commit_graph_filenames_before[i], &updated_time);
+ }
+}
+
+static void expire_commit_graphs(struct write_commit_graph_context *ctx)
+{
+ struct strbuf path = STRBUF_INIT;
+ DIR *dir;
+ struct dirent *de;
+ size_t dirnamelen;
+ timestamp_t expire_time = time(NULL);
+
+ if (ctx->split_opts && ctx->split_opts->expire_time)
+ expire_time -= ctx->split_opts->expire_time;
+ if (!ctx->split) {
+ char *chain_file_name = get_chain_filename(ctx->obj_dir);
+ unlink(chain_file_name);
+ free(chain_file_name);
+ ctx->num_commit_graphs_after = 0;
+ }
+
+ strbuf_addstr(&path, ctx->obj_dir);
+ strbuf_addstr(&path, "/info/commit-graphs");
+ dir = opendir(path.buf);
+
+ if (!dir)
+ goto out;
+
+ strbuf_addch(&path, '/');
+ dirnamelen = path.len;
+ while ((de = readdir(dir)) != NULL) {
+ struct stat st;
+ uint32_t i, found = 0;
+
+ strbuf_setlen(&path, dirnamelen);
+ strbuf_addstr(&path, de->d_name);
+
+ stat(path.buf, &st);
+
+ if (st.st_mtime > expire_time)
+ continue;
+ if (path.len < 6 || strcmp(path.buf + path.len - 6, ".graph"))
+ continue;
+
+ for (i = 0; i < ctx->num_commit_graphs_after; i++) {
+ if (!strcmp(ctx->commit_graph_filenames_after[i],
+ path.buf)) {
+ found = 1;
+ break;
+ }
+ }
+
+ if (!found)
+ unlink(path.buf);
+ }
+
+out:
+ strbuf_release(&path);
+}
+
+int write_commit_graph(const char *obj_dir,
+ struct string_list *pack_indexes,
+ struct string_list *commit_hex,
+ unsigned int flags,
+ const struct split_commit_graph_opts *split_opts)
+{
+ struct write_commit_graph_context *ctx;
+ uint32_t i, count_distinct = 0;
+ size_t len;
+ int res = 0;
+
+ if (!commit_graph_compatible(the_repository))
+ return 0;
+
+ ctx = xcalloc(1, sizeof(struct write_commit_graph_context));
+ ctx->r = the_repository;
+
+ /* normalize object dir with no trailing slash */
+ ctx->obj_dir = xmallocz(strlen(obj_dir) + 1);
+ normalize_path_copy(ctx->obj_dir, obj_dir);
+ len = strlen(ctx->obj_dir);
+ if (len && ctx->obj_dir[len - 1] == '/')
+ ctx->obj_dir[len - 1] = 0;
+
+ ctx->append = flags & COMMIT_GRAPH_APPEND ? 1 : 0;
+ ctx->report_progress = flags & COMMIT_GRAPH_PROGRESS ? 1 : 0;
+ ctx->split = flags & COMMIT_GRAPH_SPLIT ? 1 : 0;
+ ctx->split_opts = split_opts;
+
+ if (ctx->split) {
+ struct commit_graph *g;
+ prepare_commit_graph(ctx->r);
+
+ g = ctx->r->objects->commit_graph;
+
+ while (g) {
+ ctx->num_commit_graphs_before++;
+ g = g->base_graph;
+ }
+
+ if (ctx->num_commit_graphs_before) {
+ ALLOC_ARRAY(ctx->commit_graph_filenames_before, ctx->num_commit_graphs_before);
+ i = ctx->num_commit_graphs_before;
+ g = ctx->r->objects->commit_graph;
+
+ while (g) {
+ ctx->commit_graph_filenames_before[--i] = xstrdup(g->filename);
+ g = g->base_graph;
+ }
+ }
+ }
+
+ ctx->approx_nr_objects = approximate_object_count();
+ ctx->oids.alloc = ctx->approx_nr_objects / 32;
+
+ if (ctx->split && split_opts && ctx->oids.alloc > split_opts->max_commits)
+ ctx->oids.alloc = split_opts->max_commits;
+
+ if (ctx->append) {
+ prepare_commit_graph_one(ctx->r, ctx->obj_dir);
+ if (ctx->r->objects->commit_graph)
+ ctx->oids.alloc += ctx->r->objects->commit_graph->num_commits;
+ }
+
+ if (ctx->oids.alloc < 1024)
+ ctx->oids.alloc = 1024;
+ ALLOC_ARRAY(ctx->oids.list, ctx->oids.alloc);
+
+ if (ctx->append && ctx->r->objects->commit_graph) {
+ struct commit_graph *g = ctx->r->objects->commit_graph;
+ for (i = 0; i < g->num_commits; i++) {
+ const unsigned char *hash = g->chunk_oid_lookup + g->hash_len * i;
+ hashcpy(ctx->oids.list[ctx->oids.nr++].hash, hash);
+ }
+ }
+
+ if (pack_indexes) {
+ if ((res = fill_oids_from_packs(ctx, pack_indexes)))
+ goto cleanup;
+ }
+
+ if (commit_hex)
+ fill_oids_from_commit_hex(ctx, commit_hex);
+
+ if (!pack_indexes && !commit_hex)
+ fill_oids_from_all_packs(ctx);
+
+ close_reachable(ctx);
+
+ count_distinct = count_distinct_commits(ctx);
+
+ if (count_distinct >= GRAPH_EDGE_LAST_MASK) {
+ error(_("the commit graph format cannot write %d commits"), count_distinct);
+ res = -1;
+ goto cleanup;
+ }
+
+ ctx->commits.alloc = count_distinct;
+ ALLOC_ARRAY(ctx->commits.list, ctx->commits.alloc);
+
+ copy_oids_to_commits(ctx);
+
+ if (ctx->commits.nr >= GRAPH_EDGE_LAST_MASK) {
+ error(_("too many commits to write graph"));
+ res = -1;
+ goto cleanup;
+ }
+
+ if (!ctx->commits.nr)
+ goto cleanup;
+
+ if (ctx->split) {
+ split_graph_merge_strategy(ctx);
+
+ merge_commit_graphs(ctx);
+ } else
+ ctx->num_commit_graphs_after = 1;
+
+ compute_generation_numbers(ctx);
+
+ res = write_commit_graph_file(ctx);
+
+ if (ctx->split)
+ mark_commit_graphs(ctx);
+
+ expire_commit_graphs(ctx);
+
+cleanup:
+ free(ctx->graph_name);
+ free(ctx->commits.list);
+ free(ctx->oids.list);
+ free(ctx->obj_dir);
+
+ if (ctx->commit_graph_filenames_after) {
+ for (i = 0; i < ctx->num_commit_graphs_after; i++) {
+ free(ctx->commit_graph_filenames_after[i]);
+ free(ctx->commit_graph_hash_after[i]);
+ }
+
+ for (i = 0; i < ctx->num_commit_graphs_before; i++)
+ free(ctx->commit_graph_filenames_before[i]);
+
+ free(ctx->commit_graph_filenames_after);
+ free(ctx->commit_graph_filenames_before);
+ free(ctx->commit_graph_hash_after);
+ }
+
+ free(ctx);
+
+ return res;
}
#define VERIFY_COMMIT_GRAPH_ERROR_HASH 2
#define GENERATION_ZERO_EXISTS 1
#define GENERATION_NUMBER_EXISTS 2
-int verify_commit_graph(struct repository *r, struct commit_graph *g)
+int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
{
uint32_t i, cur_fanout_pos = 0;
struct object_id prev_oid, cur_oid, checksum;
struct hashfile *f;
int devnull;
struct progress *progress = NULL;
+ int local_error = 0;
if (!g) {
graph_report("no commit-graph file loaded");
hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
graph_commit = lookup_commit(r, &cur_oid);
- odb_commit = (struct commit *)create_object(r, cur_oid.hash, alloc_commit_node(r));
+ odb_commit = (struct commit *)create_object(r, &cur_oid, alloc_commit_node(r));
if (parse_commit_internal(odb_commit, 0, 0)) {
graph_report(_("failed to parse commit %s from object database for commit-graph"),
oid_to_hex(&cur_oid));
break;
}
+ /* parse parent in case it is in a base graph */
+ parse_commit_in_graph_one(r, g, graph_parents->item);
+
if (!oideq(&graph_parents->item->object.oid, &odb_parents->item->object.oid))
graph_report(_("commit-graph parent for %s is %s != %s"),
oid_to_hex(&cur_oid),
}
stop_progress(&progress);
- return verify_commit_graph_error;
+ local_error = verify_commit_graph_error;
+
+ if (!(flags & COMMIT_GRAPH_VERIFY_SHALLOW) && g->base_graph)
+ local_error |= verify_commit_graph(r, g->base_graph, flags);
+
+ return local_error;
}
void free_commit_graph(struct commit_graph *g)
g->data = NULL;
close(g->graph_fd);
}
+ free(g->filename);
free(g);
}