#include "midx.h"
#include "progress.h"
#include "trace2.h"
+#include "run-command.h"
#define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */
#define MIDX_VERSION 1
#define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
#define MIDX_LARGE_OFFSET_NEEDED 0x80000000
+#define PACK_EXPIRED UINT_MAX
+
static char *get_midx_filename(const char *object_dir)
{
return xstrfmt("%s/pack/multi-pack-index", object_dir);
uint32_t orig_pack_int_id;
char *pack_name;
struct packed_git *p;
+ unsigned expired : 1;
};
static int pack_info_compare(const void *_a, const void *_b)
packs->info[packs->nr].pack_name = xstrdup(file_name);
packs->info[packs->nr].orig_pack_int_id = packs->nr;
+ packs->info[packs->nr].expired = 0;
packs->nr++;
}
}
size_t written = 0;
for (i = 0; i < num_packs; i++) {
- size_t writelen = strlen(info[i].pack_name) + 1;
+ size_t writelen;
+
+ if (info[i].expired)
+ continue;
if (i && strcmp(info[i].pack_name, info[i - 1].pack_name) <= 0)
BUG("incorrect pack-file order: %s before %s",
info[i - 1].pack_name,
info[i].pack_name);
+ writelen = strlen(info[i].pack_name) + 1;
hashwrite(f, info[i].pack_name, writelen);
written += writelen;
}
for (i = 0; i < nr_objects; i++) {
struct pack_midx_entry *obj = list++;
+ if (perm[obj->pack_int_id] == PACK_EXPIRED)
+ BUG("object %s is in an expired pack with int-id %d",
+ oid_to_hex(&obj->oid),
+ obj->pack_int_id);
+
hashwrite_be32(f, perm[obj->pack_int_id]);
if (large_offset_needed && obj->offset >> 31)
return written;
}
-int write_midx_file(const char *object_dir)
+static int write_midx_internal(const char *object_dir, struct multi_pack_index *m,
+ struct string_list *packs_to_drop)
{
unsigned char cur_chunk, num_chunks = 0;
char *midx_name;
struct pack_midx_entry *entries = NULL;
int large_offsets_needed = 0;
int pack_name_concat_len = 0;
+ int dropped_packs = 0;
+ int result = 0;
midx_name = get_midx_filename(object_dir);
if (safe_create_leading_directories(midx_name)) {
midx_name);
}
- packs.m = load_multi_pack_index(object_dir, 1);
+ if (m)
+ packs.m = m;
+ else
+ packs.m = load_multi_pack_index(object_dir, 1);
packs.nr = 0;
packs.alloc = packs.m ? packs.m->num_packs : 16;
packs.info[packs.nr].orig_pack_int_id = i;
packs.info[packs.nr].pack_name = xstrdup(packs.m->pack_names[i]);
packs.info[packs.nr].p = NULL;
+ packs.info[packs.nr].expired = 0;
packs.nr++;
}
}
for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
- if (packs.m && packs.nr == packs.m->num_packs)
+ if (packs.m && packs.nr == packs.m->num_packs && !packs_to_drop)
goto cleanup;
entries = get_sorted_entries(packs.m, packs.info, packs.nr, &nr_entries);
QSORT(packs.info, packs.nr, pack_info_compare);
+ if (packs_to_drop && packs_to_drop->nr) {
+ int drop_index = 0;
+ int missing_drops = 0;
+
+ for (i = 0; i < packs.nr && drop_index < packs_to_drop->nr; i++) {
+ int cmp = strcmp(packs.info[i].pack_name,
+ packs_to_drop->items[drop_index].string);
+
+ if (!cmp) {
+ drop_index++;
+ packs.info[i].expired = 1;
+ } else if (cmp > 0) {
+ error(_("did not see pack-file %s to drop"),
+ packs_to_drop->items[drop_index].string);
+ drop_index++;
+ missing_drops++;
+ i--;
+ } else {
+ packs.info[i].expired = 0;
+ }
+ }
+
+ if (missing_drops) {
+ result = 1;
+ goto cleanup;
+ }
+ }
+
/*
* pack_perm stores a permutation between pack-int-ids from the
* previous multi-pack-index to the new one we are writing:
*/
ALLOC_ARRAY(pack_perm, packs.nr);
for (i = 0; i < packs.nr; i++) {
- pack_perm[packs.info[i].orig_pack_int_id] = i;
+ if (packs.info[i].expired) {
+ dropped_packs++;
+ pack_perm[packs.info[i].orig_pack_int_id] = PACK_EXPIRED;
+ } else {
+ pack_perm[packs.info[i].orig_pack_int_id] = i - dropped_packs;
+ }
}
- for (i = 0; i < packs.nr; i++)
- pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
+ for (i = 0; i < packs.nr; i++) {
+ if (!packs.info[i].expired)
+ pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
+ }
if (pack_name_concat_len % MIDX_CHUNK_ALIGNMENT)
pack_name_concat_len += MIDX_CHUNK_ALIGNMENT -
cur_chunk = 0;
num_chunks = large_offsets_needed ? 5 : 4;
- written = write_midx_header(f, num_chunks, packs.nr);
+ written = write_midx_header(f, num_chunks, packs.nr - dropped_packs);
chunk_ids[cur_chunk] = MIDX_CHUNKID_PACKNAMES;
chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
free(entries);
free(pack_perm);
free(midx_name);
- return 0;
+ return result;
+}
+
+int write_midx_file(const char *object_dir)
+{
+ return write_midx_internal(object_dir, NULL, NULL);
}
void clear_midx_file(struct repository *r)
int expire_midx_packs(struct repository *r, const char *object_dir)
{
+ uint32_t i, *count, result = 0;
+ struct string_list packs_to_drop = STRING_LIST_INIT_DUP;
+ struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+
+ if (!m)
+ return 0;
+
+ count = xcalloc(m->num_packs, sizeof(uint32_t));
+ for (i = 0; i < m->num_objects; i++) {
+ int pack_int_id = nth_midxed_pack_int_id(m, i);
+ count[pack_int_id]++;
+ }
+
+ for (i = 0; i < m->num_packs; i++) {
+ char *pack_name;
+
+ if (count[i])
+ continue;
+
+ if (prepare_midx_pack(r, m, i))
+ continue;
+
+ if (m->packs[i]->pack_keep)
+ continue;
+
+ pack_name = xstrdup(m->packs[i]->pack_name);
+ close_pack(m->packs[i]);
+
+ string_list_insert(&packs_to_drop, m->pack_names[i]);
+ unlink_pack_path(pack_name, 0);
+ free(pack_name);
+ }
+
+ free(count);
+
+ if (packs_to_drop.nr)
+ result = write_midx_internal(object_dir, m, &packs_to_drop);
+
+ string_list_clear(&packs_to_drop, 0);
+ return result;
+}
+
+struct repack_info {
+ timestamp_t mtime;
+ uint32_t referenced_objects;
+ uint32_t pack_int_id;
+};
+
+static int compare_by_mtime(const void *a_, const void *b_)
+{
+ const struct repack_info *a, *b;
+
+ a = (const struct repack_info *)a_;
+ b = (const struct repack_info *)b_;
+
+ if (a->mtime < b->mtime)
+ return -1;
+ if (a->mtime > b->mtime)
+ return 1;
return 0;
}
+
+static int fill_included_packs_all(struct multi_pack_index *m,
+ unsigned char *include_pack)
+{
+ uint32_t i;
+
+ for (i = 0; i < m->num_packs; i++)
+ include_pack[i] = 1;
+
+ return m->num_packs < 2;
+}
+
+static int fill_included_packs_batch(struct repository *r,
+ struct multi_pack_index *m,
+ unsigned char *include_pack,
+ size_t batch_size)
+{
+ uint32_t i, packs_to_repack;
+ size_t total_size;
+ struct repack_info *pack_info = xcalloc(m->num_packs, sizeof(struct repack_info));
+
+ for (i = 0; i < m->num_packs; i++) {
+ pack_info[i].pack_int_id = i;
+
+ if (prepare_midx_pack(r, m, i))
+ continue;
+
+ pack_info[i].mtime = m->packs[i]->mtime;
+ }
+
+ for (i = 0; batch_size && i < m->num_objects; i++) {
+ uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
+ pack_info[pack_int_id].referenced_objects++;
+ }
+
+ QSORT(pack_info, m->num_packs, compare_by_mtime);
+
+ total_size = 0;
+ packs_to_repack = 0;
+ for (i = 0; total_size < batch_size && i < m->num_packs; i++) {
+ int pack_int_id = pack_info[i].pack_int_id;
+ struct packed_git *p = m->packs[pack_int_id];
+ size_t expected_size;
+
+ if (!p)
+ continue;
+ if (open_pack_index(p) || !p->num_objects)
+ continue;
+
+ expected_size = (size_t)(p->pack_size
+ * pack_info[i].referenced_objects);
+ expected_size /= p->num_objects;
+
+ if (expected_size >= batch_size)
+ continue;
+
+ packs_to_repack++;
+ total_size += expected_size;
+ include_pack[pack_int_id] = 1;
+ }
+
+ free(pack_info);
+
+ if (total_size < batch_size || packs_to_repack < 2)
+ return 1;
+
+ return 0;
+}
+
+int midx_repack(struct repository *r, const char *object_dir, size_t batch_size)
+{
+ int result = 0;
+ uint32_t i;
+ unsigned char *include_pack;
+ struct child_process cmd = CHILD_PROCESS_INIT;
+ struct strbuf base_name = STRBUF_INIT;
+ struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+
+ if (!m)
+ return 0;
+
+ include_pack = xcalloc(m->num_packs, sizeof(unsigned char));
+
+ if (batch_size) {
+ if (fill_included_packs_batch(r, m, include_pack, batch_size))
+ goto cleanup;
+ } else if (fill_included_packs_all(m, include_pack))
+ goto cleanup;
+
+ argv_array_push(&cmd.args, "pack-objects");
+
+ strbuf_addstr(&base_name, object_dir);
+ strbuf_addstr(&base_name, "/pack/pack");
+ argv_array_push(&cmd.args, base_name.buf);
+ strbuf_release(&base_name);
+
+ cmd.git_cmd = 1;
+ cmd.in = cmd.out = -1;
+
+ if (start_command(&cmd)) {
+ error(_("could not start pack-objects"));
+ result = 1;
+ goto cleanup;
+ }
+
+ for (i = 0; i < m->num_objects; i++) {
+ struct object_id oid;
+ uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
+
+ if (!include_pack[pack_int_id])
+ continue;
+
+ nth_midxed_object_oid(&oid, m, i);
+ xwrite(cmd.in, oid_to_hex(&oid), the_hash_algo->hexsz);
+ xwrite(cmd.in, "\n", 1);
+ }
+ close(cmd.in);
+
+ if (finish_command(&cmd)) {
+ error(_("could not finish pack-objects"));
+ result = 1;
+ goto cleanup;
+ }
+
+ result = write_midx_internal(object_dir, m, NULL);
+ m = NULL;
+
+cleanup:
+ if (m)
+ close_midx(m);
+ free(include_pack);
+ return result;
+}