* and return the paths that match the given pattern in list.
*/
static int list_paths(struct string_list *list, const char *with_tree,
- const char *prefix, const struct pathspec *pattern)
+ const struct pathspec *pattern)
{
int i, ret;
char *m;
item->util = item; /* better a valid pointer than a fake one */
}
- ret = report_path_error(m, pattern, prefix);
+ ret = report_path_error(m, pattern);
free(m);
return ret;
}
die(_("cannot do a partial commit during a cherry-pick."));
}
- if (list_paths(&partial, !current_head ? NULL : "HEAD", prefix, &pathspec))
+ if (list_paths(&partial, !current_head ? NULL : "HEAD", &pathspec))
exit(1);
discard_cache();
set_ident_var(&date, strbuf_detach(&date_buf, NULL));
}
- strbuf_addstr(author_ident, fmt_ident(name, email, date, IDENT_STRICT));
+ strbuf_addstr(author_ident, fmt_ident(name, email, WANT_AUTHOR_IDENT, date,
+ IDENT_STRICT));
assert_split_ident(&author, author_ident);
export_one("GIT_AUTHOR_NAME", author.name_begin, author.name_end, 0);
export_one("GIT_AUTHOR_EMAIL", author.mail_begin, author.mail_end, 0);
const char *hook_arg2 = NULL;
int clean_message_contents = (cleanup_mode != COMMIT_MSG_CLEANUP_NONE);
int old_display_comment_prefix;
+ int merge_contains_scissors = 0;
/* This checks and barfs if author is badly specified */
determine_author_info(author_ident);
strbuf_addbuf(&sb, &message);
hook_arg1 = "message";
} else if (!stat(git_path_merge_msg(the_repository), &statbuf)) {
+ size_t merge_msg_start;
+
/*
* prepend SQUASH_MSG here if it exists and a
* "merge --squash" was originally performed
hook_arg1 = "squash";
} else
hook_arg1 = "merge";
+
+ merge_msg_start = sb.len;
if (strbuf_read_file(&sb, git_path_merge_msg(the_repository), 0) < 0)
die_errno(_("could not read MERGE_MSG"));
+
+ if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS &&
+ wt_status_locate_end(sb.buf + merge_msg_start,
+ sb.len - merge_msg_start) <
+ sb.len - merge_msg_start)
+ merge_contains_scissors = 1;
} else if (!stat(git_path_squash_msg(the_repository), &statbuf)) {
if (strbuf_read_file(&sb, git_path_squash_msg(the_repository), 0) < 0)
die_errno(_("could not read SQUASH_MSG"));
struct ident_split ci, ai;
if (whence != FROM_COMMIT) {
- if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS)
+ if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS &&
+ !merge_contains_scissors)
wt_status_add_cut_line(s->fp);
status_printf_ln(s, GIT_COLOR_NORMAL,
whence == FROM_MERGE
_("Please enter the commit message for your changes."
" Lines starting\nwith '%c' will be ignored, and an empty"
" message aborts the commit.\n"), comment_line_char);
- else if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS &&
- whence == FROM_COMMIT)
- wt_status_add_cut_line(s->fp);
- else /* COMMIT_MSG_CLEANUP_SPACE, that is. */
+ else if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS) {
+ if (whence == FROM_COMMIT && !merge_contains_scissors)
+ wt_status_add_cut_line(s->fp);
+ } else /* COMMIT_MSG_CLEANUP_SPACE, that is. */
status_printf(s, GIT_COLOR_NORMAL,
_("Please enter the commit message for your changes."
" Lines starting\n"
s->show_untracked_files = SHOW_NORMAL_UNTRACKED_FILES;
else if (!strcmp(untracked_files_arg, "all"))
s->show_untracked_files = SHOW_ALL_UNTRACKED_FILES;
+ /*
+ * Please update $__git_untracked_file_modes in
+ * git-completion.bash when you add new options
+ */
else
die(_("Invalid untracked files mode '%s'"), untracked_files_arg);
}
static struct status_deferred_config {
enum wt_status_format status_format;
int show_branch;
+ enum ahead_behind_flags ahead_behind;
} status_deferred_config = {
STATUS_FORMAT_UNSPECIFIED,
- -1 /* unspecified */
+ -1, /* unspecified */
+ AHEAD_BEHIND_UNSPECIFIED,
};
static void finalize_deferred_config(struct wt_status *s)
if (s->show_branch < 0)
s->show_branch = 0;
+ /*
+ * If the user did not give a "--[no]-ahead-behind" command
+ * line argument *AND* we will print in a human-readable format
+ * (short, long etc.) then we inherit from the status.aheadbehind
+ * config setting. In all other cases (and porcelain V[12] formats
+ * in particular), we inherit _FULL for backwards compatibility.
+ */
+ if (use_deferred_config &&
+ s->ahead_behind_flags == AHEAD_BEHIND_UNSPECIFIED)
+ s->ahead_behind_flags = status_deferred_config.ahead_behind;
+
if (s->ahead_behind_flags == AHEAD_BEHIND_UNSPECIFIED)
s->ahead_behind_flags = AHEAD_BEHIND_FULL;
}
die(_("Only one of --include/--only/--all/--interactive/--patch can be used."));
if (argc == 0 && (also || (only && !amend && !allow_empty)))
die(_("No paths with --include/--only does not make sense."));
- if (!cleanup_arg || !strcmp(cleanup_arg, "default"))
- cleanup_mode = use_editor ? COMMIT_MSG_CLEANUP_ALL :
- COMMIT_MSG_CLEANUP_SPACE;
- else if (!strcmp(cleanup_arg, "verbatim"))
- cleanup_mode = COMMIT_MSG_CLEANUP_NONE;
- else if (!strcmp(cleanup_arg, "whitespace"))
- cleanup_mode = COMMIT_MSG_CLEANUP_SPACE;
- else if (!strcmp(cleanup_arg, "strip"))
- cleanup_mode = COMMIT_MSG_CLEANUP_ALL;
- else if (!strcmp(cleanup_arg, "scissors"))
- cleanup_mode = use_editor ? COMMIT_MSG_CLEANUP_SCISSORS :
- COMMIT_MSG_CLEANUP_SPACE;
- else
- die(_("Invalid cleanup mode %s"), cleanup_arg);
+ cleanup_mode = get_cleanup_mode(cleanup_arg, use_editor);
handle_untracked_files_arg(s);
if (all && argc > 0)
- die(_("Paths with -a does not make sense."));
+ die(_("paths '%s ...' with -a does not make sense"),
+ argv[0]);
if (status_format != STATUS_FORMAT_NONE)
dry_run = 1;
status_deferred_config.show_branch = git_config_bool(k, v);
return 0;
}
+ if (!strcmp(k, "status.aheadbehind")) {
+ status_deferred_config.ahead_behind = git_config_bool(k, v);
+ return 0;
+ }
if (!strcmp(k, "status.showstash")) {
s->show_stash = git_config_bool(k, v);
return 0;
OPT_BOOL('s', "signoff", &signoff, N_("add Signed-off-by:")),
OPT_FILENAME('t', "template", &template_file, N_("use specified template file")),
OPT_BOOL('e', "edit", &edit_flag, N_("force edit of commit")),
- OPT_STRING(0, "cleanup", &cleanup_arg, N_("default"), N_("how to strip spaces and #comments from message")),
+ OPT_CLEANUP(&cleanup_arg),
OPT_BOOL(0, "status", &include_status, N_("include status in commit message template")),
{ OPTION_STRING, 'S', "gpg-sign", &sign_commit, N_("key-id"),
N_("GPG sign commit"), PARSE_OPT_OPTARG, NULL, (intptr_t) "" },
die(_("could not read commit message: %s"), strerror(saved_errno));
}
- if (verbose || /* Truncate the message just before the diff, if any. */
- cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS)
- strbuf_setlen(&sb, wt_status_locate_end(sb.buf, sb.len));
- if (cleanup_mode != COMMIT_MSG_CLEANUP_NONE)
- strbuf_stripspace(&sb, cleanup_mode == COMMIT_MSG_CLEANUP_ALL);
+ cleanup_message(&sb, cleanup_mode, verbose);
if (message_is_empty(&sb, cleanup_mode) && !allow_empty_message) {
rollback_index_files();
die("%s", err.buf);
}
- unlink(git_path_cherry_pick_head(the_repository));
- unlink(git_path_revert_head(the_repository));
+ sequencer_post_commit_cleanup(the_repository, 0);
unlink(git_path_merge_head(the_repository));
unlink(git_path_merge_msg(the_repository));
unlink(git_path_merge_mode(the_repository));
if (commit_index_files())
die(_("repository has been updated, but unable to write\n"
"new_index file. Check that disk is not full and quota is\n"
- "not exceeded, and then \"git reset HEAD\" to recover."));
+ "not exceeded, and then \"git restore --staged :/\" to recover."));
if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) &&
- write_commit_graph_reachable(get_object_directory(), 0))
+ write_commit_graph_reachable(get_object_directory(), 0, NULL))
return 1;
repo_rerere(the_repository, 0);
#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;
}
- if (verify_commit_graph_lite(graph))
+ hashcpy(graph->oid.hash, graph->data + graph->data_len - graph->hash_len);
+
+ if (verify_commit_graph_lite(graph)) {
+ free(graph);
return NULL;
+ }
return graph;
}
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);
+
+ 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;
}
+ 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(o->commit_graph);
+ close_commit_graph_one(o->commit_graph);
o->commit_graph = NULL;
}
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;
}
+static inline void set_commit_tree(struct commit *c, struct tree *t)
+{
+ c->maybe_tree = t;
+}
+
static int fill_commit_in_graph(struct repository *r,
struct commit *item,
struct commit_graph *g, uint32_t pos)
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;
- item->maybe_tree = NULL;
+ set_commit_tree(item, NULL);
date_high = get_be32(commit_data + g->hash_len + 8) & 0x3;
date_low = get_be32(commit_data + g->hash_len + 12);
*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);
- c->maybe_tree = lookup_tree(r, &oid);
+ set_commit_tree(c, lookup_tree(r, &oid));
return c->maybe_tree;
}
struct write_commit_graph_context {
struct repository *r;
- const char *obj_dir;
+ char *obj_dir;
char *graph_name;
struct packed_oid_list oids;
struct packed_commit_list commits;
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;
+ report_progress:1,
+ split:1;
+
+ const struct split_commit_graph_opts *split_opts;
};
static void write_graph_chunk_fanout(struct hashfile *f,
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),
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),
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;
display_progress(ctx->progress, i + 1);
commit = lookup_commit(ctx->r, &ctx->oids.list[i]);
- if (commit && !parse_commit_no_graph(commit))
+ 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(&ctx->progress);
return 0;
}
- int write_commit_graph_reachable(const char *obj_dir, unsigned int flags)
+ 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);
result = write_commit_graph(obj_dir, NULL, &list,
- flags);
+ flags, split_opts);
string_list_clear(&list, 0);
return result;
_("Counting distinct commits in commit graph"),
ctx->oids.nr);
display_progress(ctx->progress, 0); /* TODO: Measure QSORT() progress */
- QSORT(ctx->oids.list, ctx->oids.nr, commit_compare);
+ 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 (!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(&ctx->progress);
if (i > 0 && oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i]))
continue;
+ 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]);
+
+ 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;
stop_progress(&ctx->progress);
}
+ static int write_graph_chunk_base_1(struct hashfile *f,
+ struct commit_graph *g)
+ {
+ int num = 0;
+
+ 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;
+ }
+
+ 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;
+ }
+
+ return 0;
+ }
+
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[5];
- uint64_t chunk_offsets[5];
+ 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 = ctx->num_extra_edges ? 4 : 3;
+ int num_chunks = 3;
+ struct object_id file_hash;
+
+ 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);
+ }
- 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"),
return -1;
}
- hold_lock_file_for_update(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR);
- f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
+ if (ctx->split) {
+ char *lock_name = get_chain_filename(ctx->obj_dir);
- hashwrite_be32(f, GRAPH_SIGNATURE);
+ hold_lock_file_for_update(&lk, lock_name, LOCK_DIE_ON_ERROR);
- hashwrite_u8(f, GRAPH_VERSION);
- hashwrite_u8(f, oid_version());
- hashwrite_u8(f, num_chunks);
- hashwrite_u8(f, 0); /* unused padding byte */
+ 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 (ctx->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 * ctx->commits.nr;
chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr;
- chunk_offsets[4] = chunk_offsets[3] + 4 * ctx->num_extra_edges;
+
+ 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];
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);
+ 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, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC);
+ 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);
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 - 2;
+ }
+ }
+
+ 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) {
+ strbuf_release(&path);
+ return;
+ }
+
+ 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);
+ }
+ }
+
int write_commit_graph(const char *obj_dir,
struct string_list *pack_indexes,
struct string_list *commit_hex,
- unsigned int flags)
+ 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))
ctx = xcalloc(1, sizeof(struct write_commit_graph_context));
ctx->r = the_repository;
- ctx->obj_dir = obj_dir;
+
+ /* 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)
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 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);
}