diff options
author | Junio C Hamano <gitster@pobox.com> | 2024-05-25 16:06:03 -0700 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2024-05-25 16:06:03 -0700 |
commit | 07af6da1b8c6ee8cbc7087ac6bb4c59a805fefb7 (patch) | |
tree | ef387fbb93b735cbbaa600a048f931476eeeb8e8 | |
parent | 2a476a5b9fdf0aa2271ad4b787dec3d9773f5138 (diff) | |
parent | f6fcfe0eb2a03850905e7808da5ffe75fddc1903 (diff) | |
download | git-seen.tar.gz |
Merge branch 'ps/ref-storage-migration' into seenseen
Allow migrating a repository that uses the files backend for its
ref storage to use the reftable backend, with limitations.
* ps/ref-storage-migration:
builtin/refs: new command to migrate ref storage formats
refs: implement logic to migrate between ref storage formats
refs: implement removal of ref storages
refs/files: extract function to iterate through root refs
refs/files: refactor `add_pseudoref_and_head_entries()`
refs: allow to skip creation of reflog entries
refs: pass storage format to `ref_store_init()` explicitly
refs: convert ref storage format to an enum
setup: unset ref storage when reinitializing repository version
-rw-r--r-- | .gitignore | 1 | ||||
-rw-r--r-- | Documentation/git-refs.txt | 62 | ||||
-rw-r--r-- | Makefile | 1 | ||||
-rw-r--r-- | builtin.h | 1 | ||||
-rw-r--r-- | builtin/clone.c | 2 | ||||
-rw-r--r-- | builtin/init-db.c | 2 | ||||
-rw-r--r-- | builtin/refs.c | 75 | ||||
-rw-r--r-- | git.c | 1 | ||||
-rw-r--r-- | refs.c | 319 | ||||
-rw-r--r-- | refs.h | 41 | ||||
-rw-r--r-- | refs/files-backend.c | 121 | ||||
-rw-r--r-- | refs/packed-backend.c | 15 | ||||
-rw-r--r-- | refs/refs-internal.h | 7 | ||||
-rw-r--r-- | refs/reftable-backend.c | 37 | ||||
-rw-r--r-- | repository.c | 3 | ||||
-rw-r--r-- | repository.h | 10 | ||||
-rw-r--r-- | setup.c | 10 | ||||
-rw-r--r-- | setup.h | 9 | ||||
-rw-r--r-- | t/helper/test-ref-store.c | 1 | ||||
-rwxr-xr-x | t/t1460-refs-migrate.sh | 243 |
20 files changed, 916 insertions, 45 deletions
diff --git a/.gitignore b/.gitignore index 612c0f6a0f..8caf3700c2 100644 --- a/.gitignore +++ b/.gitignore @@ -126,6 +126,7 @@ /git-rebase /git-receive-pack /git-reflog +/git-refs /git-remote /git-remote-http /git-remote-https diff --git a/Documentation/git-refs.txt b/Documentation/git-refs.txt new file mode 100644 index 0000000000..3f73ad6aa6 --- /dev/null +++ b/Documentation/git-refs.txt @@ -0,0 +1,62 @@ +git-refs(1) +=========== + +NAME +---- + +git-refs - Low-level access to refs + +SYNOPSIS +-------- + +[verse] +'git refs migrate' --ref-format=<format> [--dry-run] + +DESCRIPTION +----------- + +This command provides low-level access to refs. + +COMMANDS +-------- + +migrate:: + Migrate ref store between different formats. + +OPTIONS +------- + +The following options are specific to 'git refs migrate': + +--ref-format=<format>:: + The ref format to migrate the ref store to. Can be one of: ++ +include::ref-storage-format.txt[] + +--dry-run:: + Perform the migration, but do not modify the repository. The migrated + refs will be written into a separate directory that can be inspected + separately. The name of the directory will be reported on stdout. This + can be used to double check that the migration works as expected doing + performing the actual migration. + +KNOWN LIMITATIONS +----------------- + +The ref format migration has several known limitations in its current form: + +* It is not possible to migrate repositories that have reflogs. + +* It is not possible to migrate repositories that have worktrees. + +* There is no way to block concurrent writes to the repository during an + ongoing migration. Concurrent writes can lead to an inconsistent migrated + state. Users are expected to block writes on a higher level. If your + repository is registered for scheduled maintenance, it is recommended to + unregister it first with git-maintenance(1). + +These limitations may eventually be lifted. + +GIT +--- +Part of the linkgit:git[1] suite @@ -1285,6 +1285,7 @@ BUILTIN_OBJS += builtin/read-tree.o BUILTIN_OBJS += builtin/rebase.o BUILTIN_OBJS += builtin/receive-pack.o BUILTIN_OBJS += builtin/reflog.o +BUILTIN_OBJS += builtin/refs.o BUILTIN_OBJS += builtin/remote-ext.o BUILTIN_OBJS += builtin/remote-fd.o BUILTIN_OBJS += builtin/remote.o @@ -207,6 +207,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix); int cmd_rebase__interactive(int argc, const char **argv, const char *prefix); int cmd_receive_pack(int argc, const char **argv, const char *prefix); int cmd_reflog(int argc, const char **argv, const char *prefix); +int cmd_refs(int argc, const char **argv, const char *prefix); int cmd_remote(int argc, const char **argv, const char *prefix); int cmd_remote_ext(int argc, const char **argv, const char *prefix); int cmd_remote_fd(int argc, const char **argv, const char *prefix); diff --git a/builtin/clone.c b/builtin/clone.c index 068e848646..de2bce8e7d 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -970,7 +970,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix) int submodule_progress; int filter_submodules = 0; int hash_algo; - unsigned int ref_storage_format = REF_STORAGE_FORMAT_UNKNOWN; + enum ref_storage_format ref_storage_format = REF_STORAGE_FORMAT_UNKNOWN; const int do_not_override_repo_unix_permissions = -1; struct transport_ls_refs_options transport_ls_refs_options = diff --git a/builtin/init-db.c b/builtin/init-db.c index 0170469b84..582dcf20f8 100644 --- a/builtin/init-db.c +++ b/builtin/init-db.c @@ -81,7 +81,7 @@ int cmd_init_db(int argc, const char **argv, const char *prefix) const char *ref_format = NULL; const char *initial_branch = NULL; int hash_algo = GIT_HASH_UNKNOWN; - unsigned int ref_storage_format = REF_STORAGE_FORMAT_UNKNOWN; + enum ref_storage_format ref_storage_format = REF_STORAGE_FORMAT_UNKNOWN; int init_shared_repository = -1; const struct option init_db_options[] = { OPT_STRING(0, "template", &template_dir, N_("template-directory"), diff --git a/builtin/refs.c b/builtin/refs.c new file mode 100644 index 0000000000..02401afa4e --- /dev/null +++ b/builtin/refs.c @@ -0,0 +1,75 @@ +#include "builtin.h" +#include "parse-options.h" +#include "refs.h" +#include "repository.h" +#include "strbuf.h" + +#define REFS_MIGRATE_USAGE \ + N_("git refs migrate --ref-format=<format> [--dry-run]") + +static int cmd_refs_migrate(int argc, const char **argv, const char *prefix) +{ + const char * const migrate_usage[] = { + REFS_MIGRATE_USAGE, + NULL + }; + const char *format_str = NULL; + enum ref_storage_format format; + unsigned int flags = 0; + struct option options[] = { + OPT_STRING_F(0, "ref-format", &format_str, N_("format"), + N_("specify the reference format to convert to"), + PARSE_OPT_NONEG), + OPT_BIT(0, "dry-run", &flags, + N_("perform a non-destructive dry-run"), + REPO_MIGRATE_REF_STORAGE_FORMAT_DRYRUN), + OPT_END(), + }; + struct strbuf errbuf = STRBUF_INIT; + int err; + + argc = parse_options(argc, argv, prefix, options, migrate_usage, 0); + if (argc) + usage(_("too many arguments")); + if (!format_str) + usage(_("missing --ref-format=<format>")); + + format = ref_storage_format_by_name(format_str); + if (format == REF_STORAGE_FORMAT_UNKNOWN) { + err = error(_("unknown ref storage format '%s'"), format_str); + goto out; + } + + if (the_repository->ref_storage_format == format) { + err = error(_("repository already uses '%s' format"), + ref_storage_format_to_name(format)); + goto out; + } + + if (repo_migrate_ref_storage_format(the_repository, format, flags, &errbuf) < 0) { + err = error("%s", errbuf.buf); + goto out; + } + + err = 0; + +out: + strbuf_release(&errbuf); + return err; +} + +int cmd_refs(int argc, const char **argv, const char *prefix) +{ + const char * const refs_usage[] = { + REFS_MIGRATE_USAGE, + NULL, + }; + parse_opt_subcommand_fn *fn = NULL; + struct option opts[] = { + OPT_SUBCOMMAND("migrate", &fn, cmd_refs_migrate), + OPT_END(), + }; + + argc = parse_options(argc, argv, prefix, opts, refs_usage, 0); + return fn(argc, argv, prefix); +} @@ -594,6 +594,7 @@ static struct cmd_struct commands[] = { { "rebase", cmd_rebase, RUN_SETUP | NEED_WORK_TREE }, { "receive-pack", cmd_receive_pack }, { "reflog", cmd_reflog, RUN_SETUP }, + { "refs", cmd_refs, RUN_SETUP }, { "remote", cmd_remote, RUN_SETUP }, { "remote-ext", cmd_remote_ext, NO_PARSEOPT }, { "remote-fd", cmd_remote_fd, NO_PARSEOPT }, @@ -37,14 +37,15 @@ static const struct ref_storage_be *refs_backends[] = { [REF_STORAGE_FORMAT_REFTABLE] = &refs_be_reftable, }; -static const struct ref_storage_be *find_ref_storage_backend(unsigned int ref_storage_format) +static const struct ref_storage_be *find_ref_storage_backend( + enum ref_storage_format ref_storage_format) { if (ref_storage_format < ARRAY_SIZE(refs_backends)) return refs_backends[ref_storage_format]; return NULL; } -unsigned int ref_storage_format_by_name(const char *name) +enum ref_storage_format ref_storage_format_by_name(const char *name) { for (unsigned int i = 0; i < ARRAY_SIZE(refs_backends); i++) if (refs_backends[i] && !strcmp(refs_backends[i]->name, name)) @@ -52,7 +53,7 @@ unsigned int ref_storage_format_by_name(const char *name) return REF_STORAGE_FORMAT_UNKNOWN; } -const char *ref_storage_format_to_name(unsigned int ref_storage_format) +const char *ref_storage_format_to_name(enum ref_storage_format ref_storage_format) { const struct ref_storage_be *be = find_ref_storage_backend(ref_storage_format); if (!be) @@ -1193,6 +1194,12 @@ int ref_transaction_update(struct ref_transaction *transaction, { assert(err); + if ((flags & REF_FORCE_CREATE_REFLOG) && + (flags & REF_SKIP_CREATE_REFLOG)) { + strbuf_addstr(err, _("refusing to force and skip creation of reflog")); + return -1; + } + if (!(flags & REF_SKIP_REFNAME_VERIFICATION) && ((new_oid && !is_null_oid(new_oid)) ? check_refname_format(refname, REFNAME_ALLOW_ONELEVEL) : @@ -1862,6 +1869,11 @@ int ref_store_create_on_disk(struct ref_store *refs, int flags, struct strbuf *e return refs->be->create_on_disk(refs, flags, err); } +int ref_store_remove_on_disk(struct ref_store *refs, struct strbuf *err) +{ + return refs->be->remove_on_disk(refs, err); +} + int repo_resolve_gitlink_ref(struct repository *r, const char *submodule, const char *refname, struct object_id *oid) @@ -1901,13 +1913,14 @@ static struct ref_store *lookup_ref_store_map(struct strmap *map, * gitdir. */ static struct ref_store *ref_store_init(struct repository *repo, + enum ref_storage_format format, const char *gitdir, unsigned int flags) { const struct ref_storage_be *be; struct ref_store *refs; - be = find_ref_storage_backend(repo->ref_storage_format); + be = find_ref_storage_backend(format); if (!be) BUG("reference backend is unknown"); @@ -1929,7 +1942,8 @@ struct ref_store *get_main_ref_store(struct repository *r) if (!r->gitdir) BUG("attempting to get main_ref_store outside of repository"); - r->refs_private = ref_store_init(r, r->gitdir, REF_STORE_ALL_CAPS); + r->refs_private = ref_store_init(r, r->ref_storage_format, + r->gitdir, REF_STORE_ALL_CAPS); r->refs_private = maybe_debug_wrap_ref_store(r->gitdir, r->refs_private); return r->refs_private; } @@ -1989,7 +2003,8 @@ struct ref_store *repo_get_submodule_ref_store(struct repository *repo, free(subrepo); goto done; } - refs = ref_store_init(subrepo, submodule_sb.buf, + refs = ref_store_init(subrepo, the_repository->ref_storage_format, + submodule_sb.buf, REF_STORE_READ | REF_STORE_ODB); register_ref_store_map(&repo->submodule_ref_stores, "submodule", refs, submodule); @@ -2018,12 +2033,12 @@ struct ref_store *get_worktree_ref_store(const struct worktree *wt) struct strbuf common_path = STRBUF_INIT; strbuf_git_common_path(&common_path, wt->repo, "worktrees/%s", wt->id); - refs = ref_store_init(wt->repo, common_path.buf, - REF_STORE_ALL_CAPS); + refs = ref_store_init(wt->repo, wt->repo->ref_storage_format, + common_path.buf, REF_STORE_ALL_CAPS); strbuf_release(&common_path); } else { - refs = ref_store_init(wt->repo, wt->repo->commondir, - REF_STORE_ALL_CAPS); + refs = ref_store_init(wt->repo, the_repository->ref_storage_format, + wt->repo->commondir, REF_STORE_ALL_CAPS); } if (refs) @@ -2569,3 +2584,287 @@ int ref_update_ref_must_exist(struct ref_update *update) return (update->flags & REF_HAVE_OLD) && (!is_null_oid(&update->old_oid) || update->old_target); } + +struct migration_data { + struct ref_store *old_refs; + struct ref_store *new_refs; + struct ref_transaction *transaction; + struct strbuf *errbuf; + const char *refname; +}; + +static int migrate_one_ref(const char *refname, const struct object_id *oid, + int flags, void *cb_data) +{ + struct migration_data *data = cb_data; + struct strbuf symref_target = STRBUF_INIT; + int ret; + + if (flags & REF_ISSYMREF) { + ret = refs_read_symbolic_ref(data->old_refs, refname, &symref_target); + if (ret < 0) + goto done; + + ret = ref_transaction_update(data->transaction, refname, NULL, null_oid(), + symref_target.buf, NULL, + REF_SKIP_CREATE_REFLOG | REF_NO_DEREF, NULL, data->errbuf); + if (ret < 0) + goto done; + } else { + ret = ref_transaction_create(data->transaction, refname, oid, NULL, + REF_SKIP_CREATE_REFLOG | REF_SKIP_OID_VERIFICATION, + NULL, data->errbuf); + if (ret < 0) + goto done; + } + +done: + strbuf_release(&symref_target); + return ret; +} + +static int move_files(const char *from_path, const char *to_path, struct strbuf *errbuf) +{ + struct strbuf from_buf = STRBUF_INIT, to_buf = STRBUF_INIT; + size_t from_len, to_len; + DIR *from_dir; + int ret; + + from_dir = opendir(from_path); + if (!from_dir) { + strbuf_addf(errbuf, "could not open source directory: '%s'", from_path); + ret = -1; + goto done; + } + + strbuf_addstr(&from_buf, from_path); + strbuf_complete(&from_buf, '/'); + from_len = from_buf.len; + + strbuf_addstr(&to_buf, to_path); + strbuf_complete(&to_buf, '/'); + to_len = to_buf.len; + + while (1) { + struct dirent *ent; + + errno = 0; + ent = readdir(from_dir); + if (!ent) + break; + + if (!strcmp(ent->d_name, ".") || + !strcmp(ent->d_name, "..")) + continue; + + strbuf_setlen(&from_buf, from_len); + strbuf_addstr(&from_buf, ent->d_name); + + strbuf_setlen(&to_buf, to_len); + strbuf_addstr(&to_buf, ent->d_name); + + ret = rename(from_buf.buf, to_buf.buf); + if (ret < 0) { + strbuf_addf(errbuf, "could not link file '%s' to '%s': %s", + from_buf.buf, to_buf.buf, strerror(errno)); + goto done; + } + } + + if (errno) { + strbuf_addf(errbuf, "could not read entry from directory '%s': %s", + from_path, strerror(errno)); + ret = -1; + goto done; + } + + ret = 0; + +done: + strbuf_release(&from_buf); + strbuf_release(&to_buf); + closedir(from_dir); + return ret; +} + +static int count_reflogs(const char *reflog, void *payload) +{ + size_t *reflog_count = payload; + (*reflog_count)++; + return 0; +} + +static int has_worktrees(void) +{ + struct worktree **worktrees = get_worktrees(); + int ret = 0; + size_t i; + + for (i = 0; worktrees[i]; i++) { + if (is_main_worktree(worktrees[i])) + continue; + ret = 1; + } + + free_worktrees(worktrees); + return ret; +} + +int repo_migrate_ref_storage_format(struct repository *repo, + enum ref_storage_format format, + unsigned int flags, + struct strbuf *errbuf) +{ + struct ref_store *old_refs = NULL, *new_refs = NULL; + struct ref_transaction *transaction = NULL; + struct strbuf buf = STRBUF_INIT; + struct migration_data data; + size_t reflog_count = 0; + char *new_gitdir; + int ret; + + old_refs = get_main_ref_store(repo); + + /* + * The overall logic looks like this: + * + * 1. Set up a new temporary directory and initialize it with the new + * format. This is where all refs will be migrated into. + * + * 2. Enumerate all refs and write them into the new ref storage. + * This operation is safe as we do not yet modify the main + * repository. + * + * 3. If we're in dry-run mode then we are done and can hand over the + * directory to the caller for inspection. If not, we now start + * with the destructive part. + * + * 4. Delete the old ref storage from disk. As we have a copy of refs + * in the new ref storage it's okay(ish) if we now get interrupted + * as there is an equivalent copy of all refs available. + * + * 5. Move the new ref storage files into place. + * + * 6. Change the repository format to the new ref format. + */ + strbuf_addf(&buf, "%s/%s", old_refs->gitdir, "ref_migration.XXXXXX"); + new_gitdir = mkdtemp(buf.buf); + if (!new_gitdir) { + strbuf_addf(errbuf, "cannot create migration directory: %s", + strerror(errno)); + ret = -1; + goto done; + } + + if (refs_for_each_reflog(old_refs, count_reflogs, &reflog_count) < 0) { + strbuf_addstr(errbuf, "cannot count reflogs"); + ret = -1; + goto done; + } + if (reflog_count) { + strbuf_addstr(errbuf, "migrating reflogs is not supported yet"); + ret = -1; + goto done; + } + + /* + * TODO: we should really be passing the caller-provided repository to + * `has_worktrees()`, but our worktree subsystem doesn't yet support + * that. + */ + if (has_worktrees()) { + strbuf_addstr(errbuf, "migrating repositories with worktrees is not supported yet"); + ret = -1; + goto done; + } + + new_refs = ref_store_init(repo, format, new_gitdir, + REF_STORE_ALL_CAPS); + ret = ref_store_create_on_disk(new_refs, 0, errbuf); + if (ret < 0) + goto done; + + transaction = ref_store_transaction_begin(new_refs, errbuf); + if (!transaction) + goto done; + + data.old_refs = old_refs; + data.new_refs = new_refs; + data.transaction = transaction; + data.errbuf = errbuf; + + /* + * We need to use the internal `do_for_each_ref()` here so that we can + * also include broken refs and symrefs. These would otherwise be + * skipped silently. + * + * Ideally, we would do this call while locking the old ref storage + * such that there cannot be any concurrent modifications. We do not + * have the infra for that though, and the "files" backend does not + * allow for a central lock due to its design. It's thus on the user to + * ensure that there are no concurrent writes. + */ + ret = do_for_each_ref(old_refs, "", NULL, migrate_one_ref, 0, + DO_FOR_EACH_INCLUDE_ROOT_REFS | DO_FOR_EACH_INCLUDE_BROKEN, + &data); + if (ret < 0) + goto done; + + /* + * TODO: we might want to migrate to `initial_ref_transaction_commit()` + * here, which is more efficient for the files backend because it would + * write new refs into the packed-refs file directly. At this point, + * the files backend doesn't handle pseudo-refs and symrefs correctly + * though, so this requires some more work. + */ + ret = ref_transaction_commit(transaction, errbuf); + if (ret < 0) + goto done; + + if (flags & REPO_MIGRATE_REF_STORAGE_FORMAT_DRYRUN) { + printf(_("Finished dry-run migration of refs, " + "the result can be found at '%s'\n"), new_gitdir); + ret = 0; + goto done; + } + + /* + * Until now we were in the non-destructive phase, where we only + * populated the new ref store. From hereon though we are about + * to get hands by deleting the old ref store and then moving + * the new one into place. + * + * Assuming that there were no concurrent writes, the new ref + * store should have all information. So if we fail from hereon + * we may be in an in-between state, but it would still be able + * to recover by manually moving remaining files from the + * temporary migration directory into place. + */ + ret = ref_store_remove_on_disk(old_refs, errbuf); + if (ret < 0) + goto done; + + ret = move_files(new_gitdir, old_refs->gitdir, errbuf); + if (ret < 0) + goto done; + rmdir(new_gitdir); + + /* + * We have migrated the repository, so we now need to adjust the + * repository format so that clients will use the new ref store. + * We also need to swap out the repository's main ref store. + */ + initialize_repository_version(hash_algo_by_ptr(repo->hash_algo), format, 1); + + repo->refs_private = new_refs; + ref_store_release(old_refs); + + ret = 0; + +done: + if (ret && new_refs) + ref_store_release(new_refs); + ref_transaction_free(transaction); + strbuf_release(&buf); + return ret; +} @@ -11,8 +11,14 @@ struct string_list; struct string_list_item; struct worktree; -unsigned int ref_storage_format_by_name(const char *name); -const char *ref_storage_format_to_name(unsigned int ref_storage_format); +enum ref_storage_format { + REF_STORAGE_FORMAT_UNKNOWN, + REF_STORAGE_FORMAT_FILES, + REF_STORAGE_FORMAT_REFTABLE, +}; + +enum ref_storage_format ref_storage_format_by_name(const char *name); +const char *ref_storage_format_to_name(enum ref_storage_format ref_storage_format); /* * Resolve a reference, recursively following symbolic refererences. @@ -124,6 +130,11 @@ int ref_store_create_on_disk(struct ref_store *refs, int flags, struct strbuf *e void ref_store_release(struct ref_store *ref_store); /* + * Remove the ref store from disk. This deletes all associated data. + */ +int ref_store_remove_on_disk(struct ref_store *refs, struct strbuf *err); + +/* * Return the peeled value of the oid currently being iterated via * for_each_ref(), etc. This is equivalent to calling: * @@ -654,12 +665,18 @@ struct ref_transaction *ref_store_transaction_begin(struct ref_store *refs, #define REF_SKIP_REFNAME_VERIFICATION (1 << 11) /* + * Skip creation of a reflog entry, even if it would have otherwise been + * created. + */ +#define REF_SKIP_CREATE_REFLOG (1 << 12) + +/* * Bitmask of all of the flags that are allowed to be passed in to * ref_transaction_update() and friends: */ #define REF_TRANSACTION_UPDATE_ALLOWED_FLAGS \ (REF_NO_DEREF | REF_FORCE_CREATE_REFLOG | REF_SKIP_OID_VERIFICATION | \ - REF_SKIP_REFNAME_VERIFICATION) + REF_SKIP_REFNAME_VERIFICATION | REF_SKIP_CREATE_REFLOG) /* * Add a reference update to transaction. `new_oid` is the value that @@ -1058,6 +1075,24 @@ int is_root_ref(const char *refname); int is_pseudo_ref(const char *refname); /* + * The following flags can be passed to `repo_migrate_ref_storage_format()`: + * + * - REPO_MIGRATE_REF_STORAGE_FORMAT_DRYRUN: perform a dry-run migration + * without touching the main repository. The result will be written into a + * temporary ref storage directory. + */ +#define REPO_MIGRATE_REF_STORAGE_FORMAT_DRYRUN (1 << 0) + +/* + * Migrate the ref storage format used by the repository to the + * specified one. + */ +int repo_migrate_ref_storage_format(struct repository *repo, + enum ref_storage_format format, + unsigned int flags, + struct strbuf *err); + +/* * The following functions have been removed in Git v2.45 in favor of functions * that receive a `ref_store` as parameter. The intent of this section is * merely to help patch authors of in-flight series to have a reference what diff --git a/refs/files-backend.c b/refs/files-backend.c index 02af84fc03..dd9d034218 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -323,19 +323,15 @@ static void loose_fill_ref_dir(struct ref_store *ref_store, add_per_worktree_entries_to_dir(dir, dirname); } -/* - * Add pseudorefs to the ref dir by parsing the directory for any files - * which follow the pseudoref syntax. - */ -static void add_pseudoref_and_head_entries(struct ref_store *ref_store, - struct ref_dir *dir, - const char *dirname) +static int for_each_root_ref(struct files_ref_store *refs, + int (*cb)(const char *refname, void *cb_data), + void *cb_data) { - struct files_ref_store *refs = - files_downcast(ref_store, REF_STORE_READ, "fill_ref_dir"); struct strbuf path = STRBUF_INIT, refname = STRBUF_INIT; + const char *dirname = refs->loose->root->name; struct dirent *de; size_t dirnamelen; + int ret; DIR *d; files_ref_path(refs, &path, dirname); @@ -343,7 +339,7 @@ static void add_pseudoref_and_head_entries(struct ref_store *ref_store, d = opendir(path.buf); if (!d) { strbuf_release(&path); - return; + return -1; } strbuf_addstr(&refname, dirname); @@ -359,14 +355,47 @@ static void add_pseudoref_and_head_entries(struct ref_store *ref_store, strbuf_addstr(&refname, de->d_name); dtype = get_dtype(de, &path, 1); - if (dtype == DT_REG && is_root_ref(de->d_name)) - loose_fill_ref_dir_regular_file(refs, refname.buf, dir); + if (dtype == DT_REG && is_root_ref(de->d_name)) { + ret = cb(refname.buf, cb_data); + if (ret) + goto done; + } strbuf_setlen(&refname, dirnamelen); } + +done: strbuf_release(&refname); strbuf_release(&path); closedir(d); + return ret; +} + +struct fill_root_ref_data { + struct files_ref_store *refs; + struct ref_dir *dir; +}; + +static int fill_root_ref(const char *refname, void *cb_data) +{ + struct fill_root_ref_data *data = cb_data; + loose_fill_ref_dir_regular_file(data->refs, refname, data->dir); + return 0; +} + +/* + * Add root refs to the ref dir by parsing the directory for any files which + * follow the root ref syntax. + */ +static void add_root_refs(struct files_ref_store *refs, + struct ref_dir *dir) +{ + struct fill_root_ref_data data = { + .refs = refs, + .dir = dir, + }; + + for_each_root_ref(refs, fill_root_ref, &data); } static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs, @@ -388,8 +417,7 @@ static struct ref_cache *get_loose_ref_cache(struct files_ref_store *refs, dir = get_ref_dir(refs->loose->root); if (flags & DO_FOR_EACH_INCLUDE_ROOT_REFS) - add_pseudoref_and_head_entries(dir->cache->ref_store, dir, - refs->loose->root->name); + add_root_refs(refs, dir); /* * Add an incomplete entry for "refs/" (to be filled @@ -1752,6 +1780,9 @@ static int files_log_ref_write(struct files_ref_store *refs, { int logfd, result; + if (flags & REF_SKIP_CREATE_REFLOG) + return 0; + if (log_all_ref_updates == LOG_REFS_UNSET) log_all_ref_updates = is_bare_repository() ? LOG_REFS_NONE : LOG_REFS_NORMAL; @@ -2253,6 +2284,7 @@ static int split_head_update(struct ref_update *update, struct ref_update *new_update; if ((update->flags & REF_LOG_ONLY) || + (update->flags & REF_SKIP_CREATE_REFLOG) || (update->flags & REF_IS_PRUNING) || (update->flags & REF_UPDATE_VIA_HEAD)) return 0; @@ -3309,11 +3341,72 @@ static int files_ref_store_create_on_disk(struct ref_store *ref_store, return 0; } +struct remove_one_root_ref_data { + const char *gitdir; + struct strbuf *err; +}; + +static int remove_one_root_ref(const char *refname, + void *cb_data) +{ + struct remove_one_root_ref_data *data = cb_data; + struct strbuf buf = STRBUF_INIT; + int ret = 0; + + strbuf_addf(&buf, "%s/%s", data->gitdir, refname); + + ret = remove_path(buf.buf); + if (ret < 0) + strbuf_addf(data->err, "could not delete %s: %s\n", + refname, strerror(errno)); + + strbuf_release(&buf); + return ret; +} + +static int files_ref_store_remove_on_disk(struct ref_store *ref_store, + struct strbuf *err) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_WRITE, "remove"); + struct remove_one_root_ref_data data = { + .gitdir = refs->base.gitdir, + .err = err, + }; + struct strbuf sb = STRBUF_INIT; + int ret = 0; + + strbuf_addf(&sb, "%s/refs", refs->base.gitdir); + if (remove_dir_recursively(&sb, 0) < 0) { + strbuf_addstr(err, "could not delete refs"); + ret = -1; + } + strbuf_reset(&sb); + + strbuf_addf(&sb, "%s/logs", refs->base.gitdir); + if (remove_dir_recursively(&sb, 0) < 0) { + strbuf_addstr(err, "could not delete logs\n"); + ret = -1; + } + strbuf_reset(&sb); + + ret = for_each_root_ref(refs, remove_one_root_ref, &data); + if (ret < 0) + ret = -1; + + if (ref_store_remove_on_disk(refs->packed_ref_store, err) < 0) + ret = -1; + + strbuf_release(&sb); + return ret; +} + struct ref_storage_be refs_be_files = { .name = "files", .init = files_ref_store_init, .release = files_ref_store_release, .create_on_disk = files_ref_store_create_on_disk, + .remove_on_disk = files_ref_store_remove_on_disk, .transaction_prepare = files_transaction_prepare, .transaction_finish = files_transaction_finish, diff --git a/refs/packed-backend.c b/refs/packed-backend.c index 2789fd92f5..c4c1e36aa2 100644 --- a/refs/packed-backend.c +++ b/refs/packed-backend.c @@ -1,5 +1,6 @@ #include "../git-compat-util.h" #include "../config.h" +#include "../dir.h" #include "../gettext.h" #include "../hash.h" #include "../hex.h" @@ -1266,6 +1267,19 @@ static int packed_ref_store_create_on_disk(struct ref_store *ref_store UNUSED, return 0; } +static int packed_ref_store_remove_on_disk(struct ref_store *ref_store, + struct strbuf *err) +{ + struct packed_ref_store *refs = packed_downcast(ref_store, 0, "remove"); + + if (remove_path(refs->path) < 0) { + strbuf_addstr(err, "could not delete packed-refs"); + return -1; + } + + return 0; +} + /* * Write the packed refs from the current snapshot to the packed-refs * tempfile, incorporating any changes from `updates`. `updates` must @@ -1724,6 +1738,7 @@ struct ref_storage_be refs_be_packed = { .init = packed_ref_store_init, .release = packed_ref_store_release, .create_on_disk = packed_ref_store_create_on_disk, + .remove_on_disk = packed_ref_store_remove_on_disk, .transaction_prepare = packed_transaction_prepare, .transaction_finish = packed_transaction_finish, diff --git a/refs/refs-internal.h b/refs/refs-internal.h index 682f62e1b6..9375a3ee1a 100644 --- a/refs/refs-internal.h +++ b/refs/refs-internal.h @@ -517,6 +517,12 @@ typedef int ref_store_create_on_disk_fn(struct ref_store *refs, int flags, struct strbuf *err); +/* + * Remove the reference store from disk. + */ +typedef int ref_store_remove_on_disk_fn(struct ref_store *refs, + struct strbuf *err); + typedef int ref_transaction_prepare_fn(struct ref_store *refs, struct ref_transaction *transaction, struct strbuf *err); @@ -649,6 +655,7 @@ struct ref_storage_be { ref_store_init_fn *init; ref_store_release_fn *release; ref_store_create_on_disk_fn *create_on_disk; + ref_store_remove_on_disk_fn *remove_on_disk; ref_transaction_prepare_fn *transaction_prepare; ref_transaction_finish_fn *transaction_finish; diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c index 32410a41d5..3a18cc7d49 100644 --- a/refs/reftable-backend.c +++ b/refs/reftable-backend.c @@ -2,6 +2,7 @@ #include "../abspath.h" #include "../chdir-notify.h" #include "../config.h" +#include "../dir.h" #include "../environment.h" #include "../gettext.h" #include "../hash.h" @@ -383,6 +384,38 @@ static int reftable_be_create_on_disk(struct ref_store *ref_store, return 0; } +static int reftable_be_remove_on_disk(struct ref_store *ref_store, + struct strbuf *err) +{ + struct reftable_ref_store *refs = + reftable_be_downcast(ref_store, REF_STORE_WRITE, "remove"); + struct strbuf sb = STRBUF_INIT; + int ret = 0; + + strbuf_addf(&sb, "%s/reftable", refs->base.gitdir); + if (remove_dir_recursively(&sb, 0) < 0) { + strbuf_addstr(err, "could not delete reftables"); + ret = -1; + } + strbuf_reset(&sb); + + strbuf_addf(&sb, "%s/HEAD", refs->base.gitdir); + if (remove_path(sb.buf) < 0) { + strbuf_addstr(err, "could not delete stub HEAD"); + ret = -1; + } + strbuf_reset(&sb); + + strbuf_addf(&sb, "%s/refs/heads", refs->base.gitdir); + if (remove_path(sb.buf) < 0) { + strbuf_addstr(err, "could not delete stub heads"); + ret = -1; + } + + strbuf_release(&sb); + return ret; +} + struct reftable_ref_iterator { struct ref_iterator base; struct reftable_ref_store *refs; @@ -1142,7 +1175,8 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data if (ret) goto done; - } else if (u->flags & REF_HAVE_NEW && + } else if (!(u->flags & REF_SKIP_CREATE_REFLOG) && + (u->flags & REF_HAVE_NEW) && (u->flags & REF_FORCE_CREATE_REFLOG || should_write_log(&arg->refs->base, u->refname))) { struct reftable_log_record *log; @@ -2231,6 +2265,7 @@ struct ref_storage_be refs_be_reftable = { .init = reftable_be_init, .release = reftable_be_release, .create_on_disk = reftable_be_create_on_disk, + .remove_on_disk = reftable_be_remove_on_disk, .transaction_prepare = reftable_be_transaction_prepare, .transaction_finish = reftable_be_transaction_finish, diff --git a/repository.c b/repository.c index deb68625e0..95d10cc4a0 100644 --- a/repository.c +++ b/repository.c @@ -148,7 +148,8 @@ void repo_set_compat_hash_algo(struct repository *repo, int algo) repo_read_loose_object_map(repo); } -void repo_set_ref_storage_format(struct repository *repo, unsigned int format) +void repo_set_ref_storage_format(struct repository *repo, + enum ref_storage_format format) { repo->ref_storage_format = format; } diff --git a/repository.h b/repository.h index 4744a00d5c..bd7a408013 100644 --- a/repository.h +++ b/repository.h @@ -1,6 +1,7 @@ #ifndef REPOSITORY_H #define REPOSITORY_H +#include "refs.h" #include "strmap.h" struct config_set; @@ -26,10 +27,6 @@ enum fetch_negotiation_setting { FETCH_NEGOTIATION_NOOP, }; -#define REF_STORAGE_FORMAT_UNKNOWN 0 -#define REF_STORAGE_FORMAT_FILES 1 -#define REF_STORAGE_FORMAT_REFTABLE 2 - struct repo_settings { int initialized; @@ -181,7 +178,7 @@ struct repository { const struct git_hash_algo *compat_hash_algo; /* Repository's reference storage format, as serialized on disk. */ - unsigned int ref_storage_format; + enum ref_storage_format ref_storage_format; /* A unique-id for tracing purposes. */ int trace2_repo_id; @@ -220,7 +217,8 @@ void repo_set_gitdir(struct repository *repo, const char *root, void repo_set_worktree(struct repository *repo, const char *path); void repo_set_hash_algo(struct repository *repo, int algo); void repo_set_compat_hash_algo(struct repository *repo, int compat_algo); -void repo_set_ref_storage_format(struct repository *repo, unsigned int format); +void repo_set_ref_storage_format(struct repository *repo, + enum ref_storage_format format); void initialize_repository(struct repository *repo); RESULT_MUST_BE_USED int repo_init(struct repository *r, const char *gitdir, const char *worktree); @@ -2050,7 +2050,7 @@ static int needs_work_tree_config(const char *git_dir, const char *work_tree) } void initialize_repository_version(int hash_algo, - unsigned int ref_storage_format, + enum ref_storage_format ref_storage_format, int reinit) { char repo_version_string[10]; @@ -2081,6 +2081,8 @@ void initialize_repository_version(int hash_algo, if (ref_storage_format != REF_STORAGE_FORMAT_FILES) git_config_set("extensions.refstorage", ref_storage_format_to_name(ref_storage_format)); + else if (reinit) + git_config_set_gently("extensions.refstorage", NULL); } static int is_reinit(void) @@ -2095,7 +2097,7 @@ static int is_reinit(void) return ret; } -void create_reference_database(unsigned int ref_storage_format, +void create_reference_database(enum ref_storage_format ref_storage_format, const char *initial_branch, int quiet) { struct strbuf err = STRBUF_INIT; @@ -2294,7 +2296,7 @@ static void validate_hash_algorithm(struct repository_format *repo_fmt, int hash } static void validate_ref_storage_format(struct repository_format *repo_fmt, - unsigned int format) + enum ref_storage_format format) { const char *name = getenv("GIT_DEFAULT_REF_FORMAT"); @@ -2314,7 +2316,7 @@ static void validate_ref_storage_format(struct repository_format *repo_fmt, int init_db(const char *git_dir, const char *real_git_dir, const char *template_dir, int hash, - unsigned int ref_storage_format, + enum ref_storage_format ref_storage_format, const char *initial_branch, int init_shared_repository, unsigned int flags) { @@ -1,6 +1,7 @@ #ifndef SETUP_H #define SETUP_H +#include "refs.h" #include "string-list.h" int is_inside_git_dir(void); @@ -128,7 +129,7 @@ struct repository_format { int is_bare; int hash_algo; int compat_hash_algo; - unsigned int ref_storage_format; + enum ref_storage_format ref_storage_format; int sparse_index; char *work_tree; struct string_list unknown_extensions; @@ -192,13 +193,13 @@ const char *get_template_dir(const char *option_template); int init_db(const char *git_dir, const char *real_git_dir, const char *template_dir, int hash_algo, - unsigned int ref_storage_format, + enum ref_storage_format ref_storage_format, const char *initial_branch, int init_shared_repository, unsigned int flags); void initialize_repository_version(int hash_algo, - unsigned int ref_storage_format, + enum ref_storage_format ref_storage_format, int reinit); -void create_reference_database(unsigned int ref_storage_format, +void create_reference_database(enum ref_storage_format ref_storage_format, const char *initial_branch, int quiet); /* diff --git a/t/helper/test-ref-store.c b/t/helper/test-ref-store.c index c9efd74c2b..ad24300170 100644 --- a/t/helper/test-ref-store.c +++ b/t/helper/test-ref-store.c @@ -126,6 +126,7 @@ static struct flag_definition transaction_flags[] = { FLAG_DEF(REF_FORCE_CREATE_REFLOG), FLAG_DEF(REF_SKIP_OID_VERIFICATION), FLAG_DEF(REF_SKIP_REFNAME_VERIFICATION), + FLAG_DEF(REF_SKIP_CREATE_REFLOG), { NULL, 0 } }; diff --git a/t/t1460-refs-migrate.sh b/t/t1460-refs-migrate.sh new file mode 100755 index 0000000000..f7c0783d30 --- /dev/null +++ b/t/t1460-refs-migrate.sh @@ -0,0 +1,243 @@ +#!/bin/sh + +test_description='migration of ref storage backends' + +GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main +export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME + +TEST_PASSES_SANITIZE_LEAK=true +. ./test-lib.sh + +test_migration () { + git -C "$1" for-each-ref --include-root-refs \ + --format='%(refname) %(objectname) %(symref)' >expect && + git -C "$1" refs migrate --ref-format="$2" && + git -C "$1" for-each-ref --include-root-refs \ + --format='%(refname) %(objectname) %(symref)' >actual && + test_cmp expect actual && + + git -C "$1" rev-parse --show-ref-format >actual && + echo "$2" >expect && + test_cmp expect actual +} + +test_expect_success 'setup' ' + rm -rf .git && + # The migration does not yet support reflogs. + git config --global core.logAllRefUpdates false +' + +test_expect_success "superfluous arguments" ' + test_when_finished "rm -rf repo" && + git init repo && + test_must_fail git -C repo refs migrate foo 2>err && + cat >expect <<-EOF && + usage: too many arguments + EOF + test_cmp expect err +' + +test_expect_success "missing ref storage format" ' + test_when_finished "rm -rf repo" && + git init repo && + test_must_fail git -C repo refs migrate 2>err && + cat >expect <<-EOF && + usage: missing --ref-format=<format> + EOF + test_cmp expect err +' + +test_expect_success "unknown ref storage format" ' + test_when_finished "rm -rf repo" && + git init repo && + test_must_fail git -C repo refs migrate \ + --ref-format=unknown 2>err && + cat >expect <<-EOF && + error: unknown ref storage format ${SQ}unknown${SQ} + EOF + test_cmp expect err +' + +ref_formats="files reftable" +for from_format in $ref_formats +do + for to_format in $ref_formats + do + if test "$from_format" = "$to_format" + then + continue + fi + + test_expect_success "$from_format: migration to same format fails" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_must_fail git -C repo refs migrate \ + --ref-format=$from_format 2>err && + cat >expect <<-EOF && + error: repository already uses ${SQ}$from_format${SQ} format + EOF + test_cmp expect err + ' + + test_expect_success "$from_format -> $to_format: migration with reflog fails" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_config -C repo core.logAllRefUpdates true && + test_commit -C repo logged && + test_must_fail git -C repo refs migrate \ + --ref-format=$to_format 2>err && + cat >expect <<-EOF && + error: migrating reflogs is not supported yet + EOF + test_cmp expect err + ' + + test_expect_success "$from_format -> $to_format: migration with worktree fails" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + git -C repo worktree add wt && + test_must_fail git -C repo refs migrate \ + --ref-format=$to_format 2>err && + cat >expect <<-EOF && + error: migrating repositories with worktrees is not supported yet + EOF + test_cmp expect err + ' + + test_expect_success "$from_format -> $to_format: unborn HEAD" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_migration repo "$to_format" + ' + + test_expect_success "$from_format -> $to_format: single ref" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + test_migration repo "$to_format" + ' + + test_expect_success "$from_format -> $to_format: bare repository" ' + test_when_finished "rm -rf repo repo.git" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + git clone --ref-format=$from_format --mirror repo repo.git && + test_migration repo.git "$to_format" + ' + + test_expect_success "$from_format -> $to_format: dangling symref" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + git -C repo symbolic-ref BROKEN_HEAD refs/heads/nonexistent && + test_migration repo "$to_format" && + echo refs/heads/nonexistent >expect && + git -C repo symbolic-ref BROKEN_HEAD >actual && + test_cmp expect actual + ' + + test_expect_success "$from_format -> $to_format: broken ref" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + test-tool -C repo ref-store main update-ref "" refs/heads/broken \ + "$(test_oid 001)" "$ZERO_OID" REF_SKIP_CREATE_REFLOG,REF_SKIP_OID_VERIFICATION && + test_migration repo "$to_format" && + test_oid 001 >expect && + git -C repo rev-parse refs/heads/broken >actual && + test_cmp expect actual + ' + + test_expect_success "$from_format -> $to_format: pseudo-refs" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + git -C repo update-ref FOO_HEAD HEAD && + test_migration repo "$to_format" + ' + + test_expect_success "$from_format -> $to_format: special refs are left alone" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + git -C repo rev-parse HEAD >repo/.git/MERGE_HEAD && + git -C repo rev-parse MERGE_HEAD && + test_migration repo "$to_format" && + test_path_is_file repo/.git/MERGE_HEAD + ' + + test_expect_success "$from_format -> $to_format: a bunch of refs" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + + test_commit -C repo initial && + cat >input <<-EOF && + create FOO_HEAD HEAD + create refs/heads/branch-1 HEAD + create refs/heads/branch-2 HEAD + create refs/heads/branch-3 HEAD + create refs/heads/branch-4 HEAD + create refs/tags/tag-1 HEAD + create refs/tags/tag-2 HEAD + EOF + git -C repo update-ref --stdin <input && + test_migration repo "$to_format" + ' + + test_expect_success "$from_format -> $to_format: dry-run migration does not modify repository" ' + test_when_finished "rm -rf repo" && + git init --ref-format=$from_format repo && + test_commit -C repo initial && + git -C repo refs migrate --dry-run \ + --ref-format=$to_format >output && + grep "Finished dry-run migration of refs" output && + test_path_is_dir repo/.git/ref_migration.* && + echo $from_format >expect && + git -C repo rev-parse --show-ref-format >actual && + test_cmp expect actual + ' + done +done + +test_expect_success 'migrating from files format deletes backend files' ' + test_when_finished "rm -rf repo" && + git init --ref-format=files repo && + test_commit -C repo first && + git -C repo pack-refs --all && + test_commit -C repo second && + git -C repo update-ref ORIG_HEAD HEAD && + git -C repo rev-parse HEAD >repo/.git/FETCH_HEAD && + + test_path_is_file repo/.git/HEAD && + test_path_is_file repo/.git/ORIG_HEAD && + test_path_is_file repo/.git/refs/heads/main && + test_path_is_file repo/.git/packed-refs && + + test_migration repo reftable && + + echo "ref: refs/heads/.invalid" >expect && + test_cmp expect repo/.git/HEAD && + echo "this repository uses the reftable format" >expect && + test_cmp expect repo/.git/refs/heads && + test_path_is_file repo/.git/FETCH_HEAD && + test_path_is_missing repo/.git/ORIG_HEAD && + test_path_is_missing repo/.git/refs/heads/main && + test_path_is_missing repo/.git/logs && + test_path_is_missing repo/.git/packed-refs +' + +test_expect_success 'migrating from reftable format deletes backend files' ' + test_when_finished "rm -rf repo" && + git init --ref-format=reftable repo && + test_commit -C repo first && + + test_path_is_dir repo/.git/reftable && + test_migration repo files && + + test_path_is_missing repo/.git/reftable && + echo "ref: refs/heads/main" >expect && + test_cmp expect repo/.git/HEAD && + test_path_is_file repo/.git/refs/heads/main +' + +test_done |