mirrors/git
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

index-pack: repack local links into promisor packs

Browse Source 
Teach index-pack to, when processing the objects in a pack with
--promisor specified on the CLI, repack local objects (and the local
objects that they refer to, recursively) referenced by these objects
into promisor packs.

This prevents the situation in which, when fetching from a promisor
remote, we end up with promisor objects (newly fetched) referring
to non-promisor objects (locally created prior to the fetch). This
situation may arise if the client had previously pushed objects to the
remote, for example. One issue that arises in this situation is that,
if the non-promisor objects become inaccessible except through promisor
objects (for example, if the branch pointing to them has moved to
point to the promisor object that refers to them), then GC will garbage
collect them. There are other ways to solve this, but the simplest
seems to be to enforce the invariant that we don't have promisor objects
referring to non-promisor objects.

This repacking is done from index-pack to minimize the performance
impact. During a fetch, the only time most objects are fully inflated
in memory is when their object ID is computed, so we also scan the
objects (to see which objects they refer to) during this time.

Also to minimize the performance impact, an object is calculated to be
local if it's a loose object or present in a non-promisor pack. (If it's
also in a promisor pack or referred to by an object in a promisor pack,
it is technically already a promisor object. But a misidentification
of a promisor object as a non-promisor object is relatively benign
here - we will thus repack that promisor object into a promisor pack,
duplicating it in the object store, but there is no correctness issue,
just an issue of inefficiency.)

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Jonathan Tan
2024-11-01 13:11:48 -07:00
committed by Junio C Hamano
parent d9e24ce2ca
commit c08589efdc
4 changed files with 172 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

111
builtin/index-pack.c
View File

@ -9,6 +9,7 @@
#include "csum-file.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"
#include "progress.h"
#include "fsck.h"
@ -20,9 +21,14 @@
#include "object-file.h"
#include "object-store-ll.h"
#include "oid-array.h"
#include "oidset.h"
#include "path.h"
#include "replace-object.h"
#include "tree-walk.h"
#include "promisor-remote.h"
#include "run-command.h"
#include "setup.h"
#include "strvec.h"
static const char index_pack_usage[] =
"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict[=<msg-id>=<severity>...]] [--fsck-objects[=<msg-id>=<severity>...]] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
@ -148,6 +154,13 @@ static uint32_t input_crc32;
static int input_fd, output_fd;
static const char *curr_pack;
/*
* local_links is guarded by read_mutex, and record_local_links is read-only in
* a thread.
*/
static struct oidset local_links = OIDSET_INIT;
static int record_local_links;
static struct thread_local *thread_data;
static int nr_dispatched;
static int threads_active;
@ -799,6 +812,44 @@ static int check_collison(struct object_entry *entry)
return 0;
}
static void record_if_local_object(const struct object_id *oid)
{
struct object_info info = OBJECT_INFO_INIT;
if (oid_object_info_extended(the_repository, oid, &info, 0))
/* Missing; assume it is a promisor object */
return;
if (info.whence == OI_PACKED && info.u.packed.pack->pack_promisor)
return;
oidset_insert(&local_links, oid);
}
static void do_record_local_links(struct object *obj)
{
if (obj->type == OBJ_TREE) {
struct tree *tree = (struct tree *)obj;
struct tree_desc desc;
struct name_entry entry;
if (init_tree_desc_gently(&desc, &tree->object.oid,
tree->buffer, tree->size, 0))
/*
* Error messages are given when packs are
* verified, so do not print any here.
*/
return;
while (tree_entry_gently(&desc, &entry))
record_if_local_object(&entry.oid);
} else if (obj->type == OBJ_COMMIT) {
struct commit *commit = (struct commit *) obj;
struct commit_list *parents = commit->parents;
for (; parents; parents = parents->next)
record_if_local_object(&parents->item->object.oid);
} else if (obj->type == OBJ_TAG) {
struct tag *tag = (struct tag *) obj;
record_if_local_object(get_tagged_oid(tag));
}
}
static void sha1_object(const void *data, struct object_entry *obj_entry,
unsigned long size, enum object_type type,
const struct object_id *oid)
@ -845,7 +896,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
free(has_data);
}
if (strict || do_fsck_object) {
if (strict || do_fsck_object || record_local_links) {
read_lock();
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(the_repository, oid);
@ -877,6 +928,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
die(_("fsck error in packed object"));
if (strict && fsck_walk(obj, NULL, &fsck_options))
die(_("Not all child objects of %s are reachable"), oid_to_hex(&obj->oid));
if (record_local_links)
do_record_local_links(obj);
if (obj->type == OBJ_TREE) {
struct tree *item = (struct tree *) obj;
@ -1719,6 +1772,58 @@ static void show_pack_info(int stat_only)
free(chain_histogram);
}
static void repack_local_links(void)
{
struct child_process cmd = CHILD_PROCESS_INIT;
FILE *out;
struct strbuf line = STRBUF_INIT;
struct oidset_iter iter;
struct object_id *oid;
char *base_name;
if (!oidset_size(&local_links))
return;
base_name = mkpathdup("%s/pack/pack", repo_get_object_directory(the_repository));
strvec_push(&cmd.args, "pack-objects");
strvec_push(&cmd.args, "--exclude-promisor-objects-best-effort");
strvec_push(&cmd.args, base_name);
cmd.git_cmd = 1;
cmd.in = -1;
cmd.out = -1;
if (start_command(&cmd))
die(_("could not start pack-objects to repack local links"));
oidset_iter_init(&local_links, &iter);
while ((oid = oidset_iter_next(&iter))) {
if (write_in_full(cmd.in, oid_to_hex(oid), the_hash_algo->hexsz) < 0 ||
write_in_full(cmd.in, "\n", 1) < 0)
die(_("failed to feed local object to pack-objects"));
}
close(cmd.in);
out = xfdopen(cmd.out, "r");
while (strbuf_getline_lf(&line, out) != EOF) {
unsigned char binary[GIT_MAX_RAWSZ];
if (line.len != the_hash_algo->hexsz ||
!hex_to_bytes(binary, line.buf, line.len))
die(_("index-pack: Expecting full hex object ID lines only from pack-objects."));
/*
* pack-objects creates the .pack and .idx files, but not the
* .promisor file. Create the .promisor file, which is empty.
*/
write_special_file("promisor", "", NULL, binary, NULL);
}
fclose(out);
if (finish_command(&cmd))
die(_("could not finish pack-objects to repack local links"));
strbuf_release(&line);
free(base_name);
}
int cmd_index_pack(int argc,
const char **argv,
const char *prefix,
@ -1794,7 +1899,7 @@ int cmd_index_pack(int argc,
} else if (skip_to_optional_arg(arg, "--keep", &keep_msg)) {
; /* nothing to do */
} else if (skip_to_optional_arg(arg, "--promisor", &promisor_msg)) {
; /* already parsed */
record_local_links = 1;
} else if (starts_with(arg, "--threads=")) {
char *end;
nr_threads = strtoul(arg+10, &end, 0);
@ -1970,6 +2075,8 @@ int cmd_index_pack(int argc,
free((void *) curr_index);
free(curr_rev_index);
repack_local_links();
/*
* Let the caller know this pack is not self contained
*/