#define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
#define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
#define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
-#define GRAPH_CHUNKID_LARGEEDGES 0x45444745 /* "EDGE" */
+#define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
-#define GRAPH_DATA_WIDTH 36
+#define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
#define GRAPH_VERSION_1 0x1
#define GRAPH_VERSION GRAPH_VERSION_1
-#define GRAPH_OID_VERSION_SHA1 1
-#define GRAPH_OID_LEN_SHA1 GIT_SHA1_RAWSZ
-#define GRAPH_OID_VERSION GRAPH_OID_VERSION_SHA1
-#define GRAPH_OID_LEN GRAPH_OID_LEN_SHA1
-
-#define GRAPH_OCTOPUS_EDGES_NEEDED 0x80000000
-#define GRAPH_PARENT_MISSING 0x7fffffff
+#define GRAPH_EXTRA_EDGES_NEEDED 0x80000000
#define GRAPH_EDGE_LAST_MASK 0x7fffffff
#define GRAPH_PARENT_NONE 0x70000000
#define GRAPH_FANOUT_SIZE (4 * 256)
#define GRAPH_CHUNKLOOKUP_WIDTH 12
#define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \
- + GRAPH_FANOUT_SIZE + GRAPH_OID_LEN)
+ + GRAPH_FANOUT_SIZE + the_hash_algo->rawsz)
char *get_commit_graph_filename(const char *obj_dir)
{
return xstrfmt("%s/info/commit-graph", obj_dir);
}
+static uint8_t oid_version(void)
+{
+ return 1;
+}
+
static struct commit_graph *alloc_commit_graph(void)
{
struct commit_graph *g = xcalloc(1, sizeof(*g));
struct commit_graph *load_commit_graph_one(const char *graph_file)
{
void *graph_map;
- const unsigned char *data, *chunk_lookup;
size_t graph_size;
struct stat st;
- uint32_t i;
- struct commit_graph *graph;
+ struct commit_graph *ret;
int fd = git_open(graph_file);
- uint64_t last_chunk_offset;
- uint32_t last_chunk_id;
- uint32_t graph_signature;
- unsigned char graph_version, hash_version;
if (fd < 0)
return NULL;
die(_("graph file %s is too small"), graph_file);
}
graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0);
+ ret = parse_commit_graph(graph_map, fd, graph_size);
+
+ if (!ret) {
+ munmap(graph_map, graph_size);
+ close(fd);
+ exit(1);
+ }
+
+ return ret;
+}
+
+struct commit_graph *parse_commit_graph(void *graph_map, int fd,
+ size_t graph_size)
+{
+ const unsigned char *data, *chunk_lookup;
+ uint32_t i;
+ struct commit_graph *graph;
+ uint64_t last_chunk_offset;
+ uint32_t last_chunk_id;
+ uint32_t graph_signature;
+ unsigned char graph_version, hash_version;
+
+ if (!graph_map)
+ return NULL;
+
+ if (graph_size < GRAPH_MIN_SIZE)
+ return NULL;
+
data = (const unsigned char *)graph_map;
graph_signature = get_be32(data);
if (graph_signature != GRAPH_SIGNATURE) {
error(_("graph signature %X does not match signature %X"),
graph_signature, GRAPH_SIGNATURE);
- goto cleanup_fail;
+ return NULL;
}
graph_version = *(unsigned char*)(data + 4);
if (graph_version != GRAPH_VERSION) {
error(_("graph version %X does not match version %X"),
graph_version, GRAPH_VERSION);
- goto cleanup_fail;
+ return NULL;
}
hash_version = *(unsigned char*)(data + 5);
- if (hash_version != GRAPH_OID_VERSION) {
+ if (hash_version != oid_version()) {
error(_("hash version %X does not match version %X"),
- hash_version, GRAPH_OID_VERSION);
- goto cleanup_fail;
+ hash_version, oid_version());
+ return NULL;
}
graph = alloc_commit_graph();
- graph->hash_len = GRAPH_OID_LEN;
+ graph->hash_len = the_hash_algo->rawsz;
graph->num_chunks = *(unsigned char*)(data + 6);
graph->graph_fd = fd;
graph->data = graph_map;
last_chunk_offset = 8;
chunk_lookup = data + 8;
for (i = 0; i < graph->num_chunks; i++) {
- uint32_t chunk_id = get_be32(chunk_lookup + 0);
- uint64_t chunk_offset = get_be64(chunk_lookup + 4);
+ uint32_t chunk_id;
+ uint64_t chunk_offset;
int chunk_repeated = 0;
+ if (data + graph_size - chunk_lookup <
+ GRAPH_CHUNKLOOKUP_WIDTH) {
+ error(_("chunk lookup table entry missing; graph file may be incomplete"));
+ free(graph);
+ return NULL;
+ }
+
+ chunk_id = get_be32(chunk_lookup + 0);
+ chunk_offset = get_be64(chunk_lookup + 4);
+
chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
- if (chunk_offset > graph_size - GIT_MAX_RAWSZ) {
+ if (chunk_offset > graph_size - the_hash_algo->rawsz) {
error(_("improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
(uint32_t)chunk_offset);
- goto cleanup_fail;
+ free(graph);
+ return NULL;
}
switch (chunk_id) {
graph->chunk_commit_data = data + chunk_offset;
break;
- case GRAPH_CHUNKID_LARGEEDGES:
- if (graph->chunk_large_edges)
+ case GRAPH_CHUNKID_EXTRAEDGES:
+ if (graph->chunk_extra_edges)
chunk_repeated = 1;
else
- graph->chunk_large_edges = data + chunk_offset;
+ graph->chunk_extra_edges = data + chunk_offset;
break;
}
if (chunk_repeated) {
error(_("chunk id %08x appears multiple times"), chunk_id);
- goto cleanup_fail;
+ free(graph);
+ return NULL;
}
if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP)
}
return graph;
-
-cleanup_fail:
- munmap(graph_map, graph_size);
- close(fd);
- exit(1);
}
static void prepare_commit_graph_one(struct repository *r, const char *obj_dir)
g->chunk_oid_lookup, g->hash_len, pos);
}
-static struct commit_list **insert_parent_or_die(struct commit_graph *g,
+static struct commit_list **insert_parent_or_die(struct repository *r,
+ struct commit_graph *g,
uint64_t pos,
struct commit_list **pptr)
{
die("invalid parent position %"PRIu64, pos);
hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * pos);
- c = lookup_commit(the_repository, &oid);
+ c = lookup_commit(r, &oid);
if (!c)
die(_("could not find commit %s"), oid_to_hex(&oid));
c->graph_pos = pos;
item->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
}
-static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t pos)
+static int fill_commit_in_graph(struct repository *r,
+ struct commit *item,
+ struct commit_graph *g, uint32_t pos)
{
uint32_t edge_value;
uint32_t *parent_data_ptr;
edge_value = get_be32(commit_data + g->hash_len);
if (edge_value == GRAPH_PARENT_NONE)
return 1;
- pptr = insert_parent_or_die(g, edge_value, pptr);
+ pptr = insert_parent_or_die(r, g, edge_value, pptr);
edge_value = get_be32(commit_data + g->hash_len + 4);
if (edge_value == GRAPH_PARENT_NONE)
return 1;
- if (!(edge_value & GRAPH_OCTOPUS_EDGES_NEEDED)) {
- pptr = insert_parent_or_die(g, edge_value, pptr);
+ if (!(edge_value & GRAPH_EXTRA_EDGES_NEEDED)) {
+ pptr = insert_parent_or_die(r, g, edge_value, pptr);
return 1;
}
- parent_data_ptr = (uint32_t*)(g->chunk_large_edges +
+ parent_data_ptr = (uint32_t*)(g->chunk_extra_edges +
4 * (uint64_t)(edge_value & GRAPH_EDGE_LAST_MASK));
do {
edge_value = get_be32(parent_data_ptr);
- pptr = insert_parent_or_die(g,
+ pptr = insert_parent_or_die(r, g,
edge_value & GRAPH_EDGE_LAST_MASK,
pptr);
parent_data_ptr++;
}
}
-static int parse_commit_in_graph_one(struct commit_graph *g, struct commit *item)
+static int parse_commit_in_graph_one(struct repository *r,
+ struct commit_graph *g,
+ struct commit *item)
{
uint32_t pos;
return 1;
if (find_commit_in_graph(item, g, &pos))
- return fill_commit_in_graph(item, g, pos);
+ return fill_commit_in_graph(r, item, g, pos);
return 0;
}
{
if (!prepare_commit_graph(r))
return 0;
- return parse_commit_in_graph_one(r->objects->commit_graph, item);
+ return parse_commit_in_graph_one(r, r->objects->commit_graph, item);
}
void load_commit_graph_info(struct repository *r, struct commit *item)
fill_commit_graph_info(item, r->objects->commit_graph, pos);
}
-static struct tree *load_tree_for_commit(struct commit_graph *g, struct commit *c)
+static struct tree *load_tree_for_commit(struct repository *r,
+ struct commit_graph *g,
+ struct commit *c)
{
struct object_id oid;
const unsigned char *commit_data = g->chunk_commit_data +
GRAPH_DATA_WIDTH * (c->graph_pos);
hashcpy(oid.hash, commit_data);
- c->maybe_tree = lookup_tree(the_repository, &oid);
+ c->maybe_tree = lookup_tree(r, &oid);
return c->maybe_tree;
}
-static struct tree *get_commit_tree_in_graph_one(struct commit_graph *g,
+static struct tree *get_commit_tree_in_graph_one(struct repository *r,
+ struct commit_graph *g,
const struct commit *c)
{
if (c->maybe_tree)
if (c->graph_pos == COMMIT_NOT_FROM_GRAPH)
BUG("get_commit_tree_in_graph_one called from non-commit-graph commit");
- return load_tree_for_commit(g, (struct commit *)c);
+ return load_tree_for_commit(r, g, (struct commit *)c);
}
struct tree *get_commit_tree_in_graph(struct repository *r, const struct commit *c)
{
- return get_commit_tree_in_graph_one(r->objects->commit_graph, c);
+ return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c);
}
static void write_graph_chunk_fanout(struct hashfile *f,
struct commit **commits,
- int nr_commits)
+ int nr_commits,
+ struct progress *progress,
+ uint64_t *progress_cnt)
{
int i, count = 0;
struct commit **list = commits;
while (count < nr_commits) {
if ((*list)->object.oid.hash[0] != i)
break;
+ display_progress(progress, ++*progress_cnt);
count++;
list++;
}
}
static void write_graph_chunk_oids(struct hashfile *f, int hash_len,
- struct commit **commits, int nr_commits)
+ struct commit **commits, int nr_commits,
+ struct progress *progress,
+ uint64_t *progress_cnt)
{
struct commit **list = commits;
int count;
- for (count = 0; count < nr_commits; count++, list++)
+ for (count = 0; count < nr_commits; count++, list++) {
+ display_progress(progress, ++*progress_cnt);
hashwrite(f, (*list)->object.oid.hash, (int)hash_len);
+ }
}
static const unsigned char *commit_to_sha1(size_t index, void *table)
}
static void write_graph_chunk_data(struct hashfile *f, int hash_len,
- struct commit **commits, int nr_commits)
+ struct commit **commits, int nr_commits,
+ struct progress *progress,
+ uint64_t *progress_cnt)
{
struct commit **list = commits;
struct commit **last = commits + nr_commits;
struct commit_list *parent;
int edge_value;
uint32_t packedDate[2];
+ display_progress(progress, ++*progress_cnt);
parse_commit(*list);
hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len);
commit_to_sha1);
if (edge_value < 0)
- edge_value = GRAPH_PARENT_MISSING;
+ BUG("missing parent %s for commit %s",
+ oid_to_hex(&parent->item->object.oid),
+ oid_to_hex(&(*list)->object.oid));
}
hashwrite_be32(f, edge_value);
if (!parent)
edge_value = GRAPH_PARENT_NONE;
else if (parent->next)
- edge_value = GRAPH_OCTOPUS_EDGES_NEEDED | num_extra_edges;
+ edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges;
else {
edge_value = sha1_pos(parent->item->object.oid.hash,
commits,
nr_commits,
commit_to_sha1);
if (edge_value < 0)
- edge_value = GRAPH_PARENT_MISSING;
+ BUG("missing parent %s for commit %s",
+ oid_to_hex(&parent->item->object.oid),
+ oid_to_hex(&(*list)->object.oid));
}
hashwrite_be32(f, edge_value);
- if (edge_value & GRAPH_OCTOPUS_EDGES_NEEDED) {
+ if (edge_value & GRAPH_EXTRA_EDGES_NEEDED) {
do {
num_extra_edges++;
parent = parent->next;
}
}
-static void write_graph_chunk_large_edges(struct hashfile *f,
+static void write_graph_chunk_extra_edges(struct hashfile *f,
struct commit **commits,
- int nr_commits)
+ int nr_commits,
+ struct progress *progress,
+ uint64_t *progress_cnt)
{
struct commit **list = commits;
struct commit **last = commits + nr_commits;
while (list < last) {
int num_parents = 0;
+
+ display_progress(progress, ++*progress_cnt);
+
for (parent = (*list)->parents; num_parents < 3 && parent;
parent = parent->next)
num_parents++;
commit_to_sha1);
if (edge_value < 0)
- edge_value = GRAPH_PARENT_MISSING;
+ BUG("missing parent %s for commit %s",
+ oid_to_hex(&parent->item->object.oid),
+ oid_to_hex(&(*list)->object.oid));
else if (!parent->next)
edge_value |= GRAPH_LAST_EDGE;
static void close_reachable(struct packed_oid_list *oids, int report_progress)
{
- int i, j;
+ int i;
struct commit *commit;
struct progress *progress = NULL;
if (report_progress)
progress = start_delayed_progress(
- _("Loading known commits in commit graph"), j = 0);
+ _("Loading known commits in commit graph"), oids->nr);
for (i = 0; i < oids->nr; i++) {
- display_progress(progress, ++j);
+ display_progress(progress, i + 1);
commit = lookup_commit(the_repository, &oids->list[i]);
if (commit)
commit->object.flags |= UNINTERESTING;
*/
if (report_progress)
progress = start_delayed_progress(
- _("Expanding reachable commits in commit graph"), j = 0);
+ _("Expanding reachable commits in commit graph"), oids->nr);
for (i = 0; i < oids->nr; i++) {
- display_progress(progress, ++j);
+ display_progress(progress, i + 1);
commit = lookup_commit(the_repository, &oids->list[i]);
if (commit && !parse_commit(commit))
if (report_progress)
progress = start_delayed_progress(
- _("Clearing commit marks in commit graph"), j = 0);
+ _("Clearing commit marks in commit graph"), oids->nr);
for (i = 0; i < oids->nr; i++) {
- display_progress(progress, ++j);
+ display_progress(progress, i + 1);
commit = lookup_commit(the_repository, &oids->list[i]);
if (commit)
int num_extra_edges;
struct commit_list *parent;
struct progress *progress = NULL;
+ const unsigned hashsz = the_hash_algo->rawsz;
+ uint64_t progress_cnt = 0;
+ struct strbuf progress_title = STRBUF_INIT;
+ unsigned long approx_nr_objects;
if (!commit_graph_compatible(the_repository))
return;
oids.nr = 0;
- oids.alloc = approximate_object_count() / 32;
+ approx_nr_objects = approximate_object_count();
+ oids.alloc = approx_nr_objects / 32;
oids.progress = NULL;
oids.progress_done = 0;
strbuf_addf(&packname, "%s/pack/", obj_dir);
dirlen = packname.len;
if (report_progress) {
- oids.progress = start_delayed_progress(
- _("Finding commits for commit graph"), 0);
+ 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++) {
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, 0);
+ for_each_object_in_pack(p, add_packed_commits, &oids,
+ FOR_EACH_OBJECT_PACK_ORDER);
close_pack(p);
free(p);
}
stop_progress(&oids.progress);
+ strbuf_reset(&progress_title);
strbuf_release(&packname);
}
if (commit_hex) {
- if (report_progress)
- progress = start_delayed_progress(
- _("Finding commits for commit graph"),
- commit_hex->nr);
+ 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;
}
}
stop_progress(&progress);
+ strbuf_reset(&progress_title);
}
if (!pack_indexes && !commit_hex) {
if (report_progress)
oids.progress = start_delayed_progress(
- _("Finding commits for commit graph"), 0);
- for_each_packed_object(add_packed_commits, &oids, 0);
+ _("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);
}
close_reachable(&oids, report_progress);
+ if (report_progress)
+ 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]))
count_distinct++;
}
+ stop_progress(&progress);
- if (count_distinct >= GRAPH_PARENT_MISSING)
+ if (count_distinct >= GRAPH_EDGE_LAST_MASK)
die(_("the commit graph format cannot write %d commits"), count_distinct);
commits.nr = 0;
ALLOC_ARRAY(commits.list, commits.alloc);
num_extra_edges = 0;
+ if (report_progress)
+ progress = start_delayed_progress(
+ _("Finding extra edges in commit graph"),
+ oids.nr);
for (i = 0; i < oids.nr; i++) {
int num_parents = 0;
+ display_progress(progress, i + 1);
if (i > 0 && oideq(&oids.list[i - 1], &oids.list[i]))
continue;
commits.nr++;
}
num_chunks = num_extra_edges ? 4 : 3;
+ stop_progress(&progress);
- if (commits.nr >= GRAPH_PARENT_MISSING)
+ if (commits.nr >= GRAPH_EDGE_LAST_MASK)
die(_("too many commits to write graph"));
compute_generation_numbers(&commits, report_progress);
hashwrite_be32(f, GRAPH_SIGNATURE);
hashwrite_u8(f, GRAPH_VERSION);
- hashwrite_u8(f, GRAPH_OID_VERSION);
+ hashwrite_u8(f, oid_version());
hashwrite_u8(f, num_chunks);
hashwrite_u8(f, 0); /* unused padding byte */
chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP;
chunk_ids[2] = GRAPH_CHUNKID_DATA;
if (num_extra_edges)
- chunk_ids[3] = GRAPH_CHUNKID_LARGEEDGES;
+ chunk_ids[3] = GRAPH_CHUNKID_EXTRAEDGES;
else
chunk_ids[3] = 0;
chunk_ids[4] = 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] + GRAPH_OID_LEN * commits.nr;
- chunk_offsets[3] = chunk_offsets[2] + (GRAPH_OID_LEN + 16) * commits.nr;
+ 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;
for (i = 0; i <= num_chunks; i++) {
hashwrite(f, chunk_write, 12);
}
- write_graph_chunk_fanout(f, commits.list, commits.nr);
- write_graph_chunk_oids(f, GRAPH_OID_LEN, commits.list, commits.nr);
- write_graph_chunk_data(f, GRAPH_OID_LEN, commits.list, commits.nr);
- write_graph_chunk_large_edges(f, commits.list, commits.nr);
+ if (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(
+ progress_title.buf,
+ num_chunks * 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);
+ strbuf_release(&progress_title);
close_commit_graph(the_repository);
finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
}
graph_commit = lookup_commit(r, &cur_oid);
- if (!parse_commit_in_graph_one(g, graph_commit))
+ if (!parse_commit_in_graph_one(r, g, graph_commit))
graph_report("failed to parse %s from commit-graph",
oid_to_hex(&cur_oid));
}
continue;
}
- if (!oideq(&get_commit_tree_in_graph_one(g, graph_commit)->object.oid,
+ if (!oideq(&get_commit_tree_in_graph_one(r, g, graph_commit)->object.oid,
get_commit_tree_oid(odb_commit)))
graph_report("root tree OID for commit %s in commit-graph is %s != %s",
oid_to_hex(&cur_oid),