summaryrefslogtreecommitdiff
path: root/commit-graph.c
diff options
context:
space:
mode:
Diffstat (limited to 'commit-graph.c')
-rw-r--r--commit-graph.c225
1 files changed, 123 insertions, 102 deletions
diff --git a/commit-graph.c b/commit-graph.c
index 37bd10eca8..79b0e72cc4 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1,3 +1,5 @@
+#define USE_THE_REPOSITORY_VARIABLE
+
#include "git-compat-util.h"
#include "config.h"
#include "csum-file.h"
@@ -274,68 +276,37 @@ struct commit_graph *load_commit_graph_one_fd_st(struct repository *r,
return ret;
}
-static int verify_commit_graph_lite(struct commit_graph *g)
+static int graph_read_oid_fanout(const unsigned char *chunk_start,
+ size_t chunk_size, void *data)
{
+ struct commit_graph *g = data;
int i;
- /*
- * Basic validation shared between parse_commit_graph()
- * which'll be called every time the graph is used, and the
- * much more expensive verify_commit_graph() used by
- * "commit-graph verify".
- *
- * There should only be very basic checks here to ensure that
- * we don't e.g. segfault in fill_commit_in_graph(), but
- * because this is a very hot codepath nothing that e.g. loops
- * over g->num_commits, or runs a checksum on the commit-graph
- * itself.
- */
- if (!g->chunk_oid_fanout) {
- error("commit-graph is missing the OID Fanout chunk");
- return 1;
- }
- if (!g->chunk_oid_lookup) {
- error("commit-graph is missing the OID Lookup chunk");
- return 1;
- }
- if (!g->chunk_commit_data) {
- error("commit-graph is missing the Commit Data chunk");
- return 1;
- }
+ if (chunk_size != 256 * sizeof(uint32_t))
+ return error(_("commit-graph oid fanout chunk is wrong size"));
+ g->chunk_oid_fanout = (const uint32_t *)chunk_start;
+ g->num_commits = ntohl(g->chunk_oid_fanout[255]);
for (i = 0; i < 255; i++) {
uint32_t oid_fanout1 = ntohl(g->chunk_oid_fanout[i]);
uint32_t oid_fanout2 = ntohl(g->chunk_oid_fanout[i + 1]);
if (oid_fanout1 > oid_fanout2) {
- error("commit-graph fanout values out of order");
+ error(_("commit-graph fanout values out of order"));
return 1;
}
}
- if (ntohl(g->chunk_oid_fanout[255]) != g->num_commits) {
- error("commit-graph oid table and fanout disagree on size");
- return 1;
- }
return 0;
}
-static int graph_read_oid_fanout(const unsigned char *chunk_start,
- size_t chunk_size, void *data)
-{
- struct commit_graph *g = data;
- if (chunk_size != 256 * sizeof(uint32_t))
- return error("commit-graph oid fanout chunk is wrong size");
- g->chunk_oid_fanout = (const uint32_t *)chunk_start;
- return 0;
-}
-
static int graph_read_oid_lookup(const unsigned char *chunk_start,
size_t chunk_size, void *data)
{
struct commit_graph *g = data;
g->chunk_oid_lookup = chunk_start;
- g->num_commits = chunk_size / g->hash_len;
+ if (chunk_size / g->hash_len != g->num_commits)
+ return error(_("commit-graph OID lookup chunk is the wrong size"));
return 0;
}
@@ -343,8 +314,8 @@ static int graph_read_commit_data(const unsigned char *chunk_start,
size_t chunk_size, void *data)
{
struct commit_graph *g = data;
- if (chunk_size != g->num_commits * GRAPH_DATA_WIDTH)
- return error("commit-graph commit data chunk is wrong size");
+ if (chunk_size / GRAPH_DATA_WIDTH != g->num_commits)
+ return error(_("commit-graph commit data chunk is wrong size"));
g->chunk_commit_data = chunk_start;
return 0;
}
@@ -353,8 +324,8 @@ static int graph_read_generation_data(const unsigned char *chunk_start,
size_t chunk_size, void *data)
{
struct commit_graph *g = data;
- if (chunk_size != g->num_commits * sizeof(uint32_t))
- return error("commit-graph generations chunk is wrong size");
+ if (chunk_size / sizeof(uint32_t) != g->num_commits)
+ return error(_("commit-graph generations chunk is wrong size"));
g->chunk_generation_data = chunk_start;
return 0;
}
@@ -363,8 +334,8 @@ static int graph_read_bloom_index(const unsigned char *chunk_start,
size_t chunk_size, void *data)
{
struct commit_graph *g = data;
- if (chunk_size != g->num_commits * 4) {
- warning("commit-graph changed-path index chunk is too small");
+ if (chunk_size / 4 != g->num_commits) {
+ warning(_("commit-graph changed-path index chunk is too small"));
return -1;
}
g->chunk_bloom_indexes = chunk_start;
@@ -375,11 +346,10 @@ static int graph_read_bloom_data(const unsigned char *chunk_start,
size_t chunk_size, void *data)
{
struct commit_graph *g = data;
- uint32_t hash_version;
if (chunk_size < BLOOMDATA_CHUNK_HEADER_SIZE) {
- warning("ignoring too-small changed-path chunk"
- " (%"PRIuMAX" < %"PRIuMAX") in commit-graph file",
+ warning(_("ignoring too-small changed-path chunk"
+ " (%"PRIuMAX" < %"PRIuMAX") in commit-graph file"),
(uintmax_t)chunk_size,
(uintmax_t)BLOOMDATA_CHUNK_HEADER_SIZE);
return -1;
@@ -387,13 +357,9 @@ static int graph_read_bloom_data(const unsigned char *chunk_start,
g->chunk_bloom_data = chunk_start;
g->chunk_bloom_data_size = chunk_size;
- hash_version = get_be32(chunk_start);
-
- if (hash_version != 1)
- return 0;
g->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings));
- g->bloom_filter_settings->hash_version = hash_version;
+ g->bloom_filter_settings->hash_version = get_be32(chunk_start);
g->bloom_filter_settings->num_hashes = get_be32(chunk_start + 4);
g->bloom_filter_settings->bits_per_entry = get_be32(chunk_start + 8);
g->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES;
@@ -461,9 +427,19 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s,
GRAPH_HEADER_SIZE, graph->num_chunks, 1))
goto free_and_return;
- read_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, graph_read_oid_fanout, graph);
- read_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, graph_read_oid_lookup, graph);
- read_chunk(cf, GRAPH_CHUNKID_DATA, graph_read_commit_data, graph);
+ if (read_chunk(cf, GRAPH_CHUNKID_OIDFANOUT, graph_read_oid_fanout, graph)) {
+ error(_("commit-graph required OID fanout chunk missing or corrupted"));
+ goto free_and_return;
+ }
+ if (read_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, graph_read_oid_lookup, graph)) {
+ error(_("commit-graph required OID lookup chunk missing or corrupted"));
+ goto free_and_return;
+ }
+ if (read_chunk(cf, GRAPH_CHUNKID_DATA, graph_read_commit_data, graph)) {
+ error(_("commit-graph required commit data chunk missing or corrupted"));
+ goto free_and_return;
+ }
+
pair_chunk(cf, GRAPH_CHUNKID_EXTRAEDGES, &graph->chunk_extra_edges,
&graph->chunk_extra_edges_size);
pair_chunk(cf, GRAPH_CHUNKID_BASE, &graph->chunk_base_graphs,
@@ -480,7 +456,7 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s,
graph->read_generation_data = 1;
}
- if (s->commit_graph_read_changed_paths) {
+ if (s->commit_graph_changed_paths_version) {
read_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES,
graph_read_bloom_index, graph);
read_chunk(cf, GRAPH_CHUNKID_BLOOMDATA,
@@ -496,10 +472,8 @@ struct commit_graph *parse_commit_graph(struct repo_settings *s,
FREE_AND_NULL(graph->bloom_filter_settings);
}
- oidread(&graph->oid, graph->data + graph->data_len - graph->hash_len);
-
- if (verify_commit_graph_lite(graph))
- goto free_and_return;
+ oidread(&graph->oid, graph->data + graph->data_len - graph->hash_len,
+ the_repository->hash_algo);
free_chunkfile(cf);
return graph;
@@ -567,6 +541,31 @@ static int validate_mixed_generation_chain(struct commit_graph *g)
return 0;
}
+static void validate_mixed_bloom_settings(struct commit_graph *g)
+{
+ struct bloom_filter_settings *settings = NULL;
+ for (; g; g = g->base_graph) {
+ if (!g->bloom_filter_settings)
+ continue;
+ if (!settings) {
+ settings = g->bloom_filter_settings;
+ continue;
+ }
+
+ if (g->bloom_filter_settings->bits_per_entry != settings->bits_per_entry ||
+ g->bloom_filter_settings->num_hashes != settings->num_hashes ||
+ g->bloom_filter_settings->hash_version != settings->hash_version) {
+ g->chunk_bloom_indexes = NULL;
+ g->chunk_bloom_data = NULL;
+ FREE_AND_NULL(g->bloom_filter_settings);
+
+ warning(_("disabling Bloom filters for commit-graph "
+ "layer '%s' due to incompatible settings"),
+ oid_to_hex(&g->oid));
+ }
+ }
+}
+
static int add_graph_to_chain(struct commit_graph *g,
struct commit_graph *chain,
struct object_id *oids,
@@ -589,7 +588,8 @@ static int add_graph_to_chain(struct commit_graph *g,
if (!cur_g ||
!oideq(&oids[n], &cur_g->oid) ||
- !hasheq(oids[n].hash, g->chunk_base_graphs + st_mult(g->hash_len, n))) {
+ !hasheq(oids[n].hash, g->chunk_base_graphs + st_mult(g->hash_len, n),
+ the_repository->hash_algo)) {
warning(_("commit-graph chain does not match"));
return 0;
}
@@ -628,7 +628,7 @@ int open_commit_graph_chain(const char *chain_file,
/* treat empty files the same as missing */
errno = ENOENT;
} else {
- warning("commit-graph chain file too small");
+ warning(_("commit-graph chain file too small"));
errno = EINVAL;
}
return 0;
@@ -690,6 +690,7 @@ struct commit_graph *load_commit_graph_chain_fd_st(struct repository *r,
}
validate_mixed_generation_chain(graph_chain);
+ validate_mixed_bloom_settings(graph_chain);
free(oids);
fclose(fp);
@@ -834,6 +835,7 @@ void close_commit_graph(struct raw_object_store *o)
return;
clear_commit_graph_data_slab(&commit_graph_data_slab);
+ deinit_bloom_filters();
free_commit_graph(o->commit_graph);
o->commit_graph = NULL;
}
@@ -861,7 +863,8 @@ static void load_oid_from_graph(struct commit_graph *g,
lex_index = pos - g->num_commits_in_base;
- oidread(oid, g->chunk_oid_lookup + st_mult(g->hash_len, lex_index));
+ oidread(oid, g->chunk_oid_lookup + st_mult(g->hash_len, lex_index),
+ the_repository->hash_algo);
}
static struct commit_list **insert_parent_or_die(struct repository *r,
@@ -972,7 +975,7 @@ static int fill_commit_in_graph(struct repository *r,
parent_data_pos = edge_value & GRAPH_EDGE_LAST_MASK;
do {
if (g->chunk_extra_edges_size / sizeof(uint32_t) <= parent_data_pos) {
- error("commit-graph extra-edges pointer out of bounds");
+ error(_("commit-graph extra-edges pointer out of bounds"));
free_commit_list(item->parents);
item->parents = NULL;
item->object.parsed = 0;
@@ -1103,7 +1106,7 @@ static struct tree *load_tree_for_commit(struct repository *r,
commit_data = g->chunk_commit_data +
st_mult(GRAPH_DATA_WIDTH, graph_pos - g->num_commits_in_base);
- oidread(&oid, commit_data);
+ oidread(&oid, commit_data, the_repository->hash_algo);
set_commit_tree(c, lookup_tree(r, &oid));
return c->maybe_tree;
@@ -1171,6 +1174,7 @@ struct write_commit_graph_context {
int count_bloom_filter_not_computed;
int count_bloom_filter_trunc_empty;
int count_bloom_filter_trunc_large;
+ int count_bloom_filter_upgraded;
};
static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1621,7 +1625,7 @@ static void compute_reachable_generation_numbers(
timestamp_t gen;
repo_parse_commit(info->r, c);
gen = info->get_generation(c, info->data);
- display_progress(info->progress, info->progress_cnt + 1);
+ display_progress(info->progress, ++info->progress_cnt);
if (gen != GENERATION_NUMBER_ZERO && gen != GENERATION_NUMBER_INFINITY)
continue;
@@ -1778,6 +1782,8 @@ static void trace2_bloom_filter_write_statistics(struct write_commit_graph_conte
ctx->count_bloom_filter_trunc_empty);
trace2_data_intmax("commit-graph", ctx->r, "filter-trunc-large",
ctx->count_bloom_filter_trunc_large);
+ trace2_data_intmax("commit-graph", ctx->r, "filter-upgraded",
+ ctx->count_bloom_filter_upgraded);
}
static void compute_bloom_filters(struct write_commit_graph_context *ctx)
@@ -1819,6 +1825,8 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
ctx->count_bloom_filter_trunc_empty++;
if (computed & BLOOM_TRUNC_LARGE)
ctx->count_bloom_filter_trunc_large++;
+ } else if (computed & BLOOM_UPGRADED) {
+ ctx->count_bloom_filter_upgraded++;
} else if (computed & BLOOM_NOT_COMPUTED)
ctx->count_bloom_filter_not_computed++;
ctx->total_bloom_filter_data_size += filter
@@ -1845,7 +1853,7 @@ static int add_ref_to_set(const char *refname UNUSED,
struct object_id peeled;
struct refs_cb_data *data = (struct refs_cb_data *)cb_data;
- if (!peel_iterated_oid(oid, &peeled))
+ if (!peel_iterated_oid(the_repository, oid, &peeled))
oid = &peeled;
if (oid_object_info(the_repository, oid, NULL) == OBJ_COMMIT)
oidset_insert(data->commits, oid);
@@ -1869,7 +1877,8 @@ int write_commit_graph_reachable(struct object_directory *odb,
data.progress = start_delayed_progress(
_("Collecting referenced commits"), 0);
- for_each_ref(add_ref_to_set, &data);
+ refs_for_each_ref(get_main_ref_store(the_repository), add_ref_to_set,
+ &data);
stop_progress(&data.progress);
@@ -2025,8 +2034,8 @@ static int write_graph_chunk_base(struct hashfile *f,
static int write_commit_graph_file(struct write_commit_graph_context *ctx)
{
uint32_t i;
- int fd;
struct hashfile *f;
+ struct tempfile *graph_layer; /* when ctx->split is non-zero */
struct lock_file lk = LOCK_INIT;
const unsigned hashsz = the_hash_algo->rawsz;
struct strbuf progress_title = STRBUF_INIT;
@@ -2058,24 +2067,23 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
LOCK_DIE_ON_ERROR, 0444);
free(lock_name);
- fd = git_mkstemp_mode(ctx->graph_name, 0444);
- if (fd < 0) {
+ graph_layer = mks_tempfile_m(ctx->graph_name, 0444);
+ if (!graph_layer) {
error(_("unable to create temporary graph layer"));
return -1;
}
- if (adjust_shared_perm(ctx->graph_name)) {
+ if (adjust_shared_perm(get_tempfile_path(graph_layer))) {
error(_("unable to adjust shared permissions for '%s'"),
- ctx->graph_name);
+ get_tempfile_path(graph_layer));
return -1;
}
- f = hashfd(fd, ctx->graph_name);
+ f = hashfd(get_tempfile_fd(graph_layer), get_tempfile_path(graph_layer));
} else {
hold_lock_file_for_update_mode(&lk, ctx->graph_name,
LOCK_DIE_ON_ERROR, 0444);
- fd = get_lock_file_fd(&lk);
- f = hashfd(fd, get_lock_file_path(&lk));
+ f = hashfd(get_lock_file_fd(&lk), get_lock_file_path(&lk));
}
cf = init_chunkfile(f);
@@ -2156,8 +2164,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
char *final_graph_name;
int result;
- close(fd);
-
if (!chainf) {
error(_("unable to open commit-graph chain file"));
return -1;
@@ -2192,7 +2198,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
free(ctx->commit_graph_filenames_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);
+ result = rename_tempfile(&graph_layer, final_graph_name);
for (i = 0; i < ctx->num_commit_graphs_after; i++)
fprintf(get_lock_file_fp(&lk), "%s\n", ctx->commit_graph_hash_after[i]);
@@ -2502,6 +2508,13 @@ int write_commit_graph(struct object_directory *odb,
}
if (!commit_graph_compatible(r))
return 0;
+ if (r->settings.commit_graph_changed_paths_version < -1
+ || r->settings.commit_graph_changed_paths_version > 2) {
+ warning(_("attempting to write a commit-graph, but "
+ "'commitGraph.changedPathsVersion' (%d) is not supported"),
+ r->settings.commit_graph_changed_paths_version);
+ return 0;
+ }
CALLOC_ARRAY(ctx, 1);
ctx->r = r;
@@ -2514,6 +2527,7 @@ int write_commit_graph(struct object_directory *odb,
ctx->write_generation_data = (get_configured_generation_version(r) == 2);
ctx->num_generation_data_overflows = 0;
+ bloom_settings.hash_version = r->settings.commit_graph_changed_paths_version;
bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
bloom_settings.bits_per_entry);
bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
@@ -2543,12 +2557,20 @@ int write_commit_graph(struct object_directory *odb,
g = ctx->r->objects->commit_graph;
/* We have changed-paths already. Keep them in the next graph */
- if (g && g->chunk_bloom_data) {
+ if (g && g->bloom_filter_settings) {
ctx->changed_paths = 1;
- ctx->bloom_settings = g->bloom_filter_settings;
+
+ /* don't propagate the hash_version unless unspecified */
+ if (bloom_settings.hash_version == -1)
+ bloom_settings.hash_version = g->bloom_filter_settings->hash_version;
+ bloom_settings.bits_per_entry = g->bloom_filter_settings->bits_per_entry;
+ bloom_settings.num_hashes = g->bloom_filter_settings->num_hashes;
+ bloom_settings.max_changed_paths = g->bloom_filter_settings->max_changed_paths;
}
}
+ bloom_settings.hash_version = bloom_settings.hash_version == 2 ? 2 : 1;
+
if (ctx->split) {
struct commit_graph *g = ctx->r->objects->commit_graph;
@@ -2578,7 +2600,8 @@ int write_commit_graph(struct object_directory *odb,
struct commit_graph *g = ctx->r->objects->commit_graph;
for (i = 0; i < g->num_commits; i++) {
struct object_id oid;
- oidread(&oid, g->chunk_oid_lookup + st_mult(g->hash_len, i));
+ oidread(&oid, g->chunk_oid_lookup + st_mult(g->hash_len, i),
+ the_repository->hash_algo);
oid_array_append(&ctx->oids, &oid);
}
}
@@ -2631,6 +2654,9 @@ int write_commit_graph(struct object_directory *odb,
res = write_commit_graph_file(ctx);
+ if (ctx->changed_paths)
+ deinit_bloom_filters();
+
if (ctx->split)
mark_commit_graphs(ctx);
@@ -2643,19 +2669,16 @@ cleanup:
oid_array_clear(&ctx->oids);
clear_topo_level_slab(&topo_levels);
- 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_before);
- 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);
+ for (i = 0; i < ctx->num_commit_graphs_after; i++) {
+ free(ctx->commit_graph_filenames_after[i]);
+ free(ctx->commit_graph_hash_after[i]);
}
+ free(ctx->commit_graph_filenames_after);
+ free(ctx->commit_graph_hash_after);
free(ctx);
@@ -2692,10 +2715,6 @@ static int verify_one_commit_graph(struct repository *r,
struct commit *seen_gen_zero = NULL;
struct commit *seen_gen_non_zero = NULL;
- verify_commit_graph_error = verify_commit_graph_lite(g);
- if (verify_commit_graph_error)
- return verify_commit_graph_error;
-
if (!commit_graph_checksum_valid(g)) {
graph_report(_("the commit-graph file has incorrect checksum and is likely corrupt"));
verify_commit_graph_error = VERIFY_COMMIT_GRAPH_ERROR_HASH;
@@ -2704,7 +2723,8 @@ static int verify_one_commit_graph(struct repository *r,
for (i = 0; i < g->num_commits; i++) {
struct commit *graph_commit;
- oidread(&cur_oid, g->chunk_oid_lookup + st_mult(g->hash_len, i));
+ oidread(&cur_oid, g->chunk_oid_lookup + st_mult(g->hash_len, i),
+ the_repository->hash_algo);
if (i && oidcmp(&prev_oid, &cur_oid) >= 0)
graph_report(_("commit-graph has incorrect OID order: %s then %s"),
@@ -2748,7 +2768,8 @@ static int verify_one_commit_graph(struct repository *r,
timestamp_t generation;
display_progress(progress, ++(*seen));
- oidread(&cur_oid, g->chunk_oid_lookup + st_mult(g->hash_len, i));
+ oidread(&cur_oid, g->chunk_oid_lookup + st_mult(g->hash_len, i),
+ the_repository->hash_algo);
graph_commit = lookup_commit(r, &cur_oid);
odb_commit = (struct commit *)create_object(r, &cur_oid, alloc_commit_node(r));
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-10 11:14:57 +0000