diff options
| -rw-r--r-- | Documentation/config/remote.txt | 8 | ||||
| -rw-r--r-- | Documentation/technical/partial-clone.txt | 117 | ||||
| -rw-r--r-- | Makefile | 2 | ||||
| -rw-r--r-- | builtin/cat-file.c | 5 | ||||
| -rw-r--r-- | builtin/fetch.c | 29 | ||||
| -rw-r--r-- | builtin/gc.c | 3 | ||||
| -rw-r--r-- | builtin/index-pack.c | 8 | ||||
| -rw-r--r-- | builtin/repack.c | 3 | ||||
| -rw-r--r-- | cache-tree.c | 3 | ||||
| -rw-r--r-- | cache.h | 2 | ||||
| -rw-r--r-- | config.c | 5 | ||||
| -rw-r--r-- | connected.c | 3 | ||||
| -rw-r--r-- | diff.c | 9 | ||||
| -rw-r--r-- | environment.c | 2 | ||||
| -rw-r--r-- | fetch-object.c | 40 | ||||
| -rw-r--r-- | fetch-object.h | 9 | ||||
| -rw-r--r-- | list-objects-filter-options.c | 51 | ||||
| -rw-r--r-- | list-objects-filter-options.h | 3 | ||||
| -rw-r--r-- | packfile.c | 3 | ||||
| -rw-r--r-- | promisor-remote.c | 265 | ||||
| -rw-r--r-- | promisor-remote.h | 31 | ||||
| -rw-r--r-- | setup.c | 3 | ||||
| -rw-r--r-- | sha1-file.c | 15 | ||||
| -rwxr-xr-x | t/t0410-partial-clone.sh | 61 | ||||
| -rwxr-xr-x | t/t5601-clone.sh | 3 | ||||
| -rwxr-xr-x | t/t5616-partial-clone.sh | 4 | ||||
| -rw-r--r-- | unpack-trees.c | 8 |
27 files changed, 523 insertions, 172 deletions
diff --git a/Documentation/config/remote.txt b/Documentation/config/remote.txt index 6c4cad83a2..a8e6437a90 100644 --- a/Documentation/config/remote.txt +++ b/Documentation/config/remote.txt @@ -76,3 +76,11 @@ remote.<name>.pruneTags:: + See also `remote.<name>.prune` and the PRUNING section of linkgit:git-fetch[1]. + +remote.<name>.promisor:: + When set to true, this remote will be used to fetch promisor + objects. + +remote.<name>.partialclonefilter:: + The filter that will be applied when fetching from this + promisor remote. diff --git a/Documentation/technical/partial-clone.txt b/Documentation/technical/partial-clone.txt index 896c7b3878..210373e258 100644 --- a/Documentation/technical/partial-clone.txt +++ b/Documentation/technical/partial-clone.txt @@ -30,12 +30,20 @@ advance* during clone and fetch operations and thereby reduce download times and disk usage. Missing objects can later be "demand fetched" if/when needed. +A remote that can later provide the missing objects is called a +promisor remote, as it promises to send the objects when +requested. Initialy Git supported only one promisor remote, the origin +remote from which the user cloned and that was configured in the +"extensions.partialClone" config option. Later support for more than +one promisor remote has been implemented. + Use of partial clone requires that the user be online and the origin -remote be available for on-demand fetching of missing objects. This may -or may not be problematic for the user. For example, if the user can -stay within the pre-selected subset of the source tree, they may not -encounter any missing objects. Alternatively, the user could try to -pre-fetch various objects if they know that they are going offline. +remote or other promisor remotes be available for on-demand fetching +of missing objects. This may or may not be problematic for the user. +For example, if the user can stay within the pre-selected subset of +the source tree, they may not encounter any missing objects. +Alternatively, the user could try to pre-fetch various objects if they +know that they are going offline. Non-Goals @@ -100,18 +108,18 @@ or commits that reference missing trees. Handling Missing Objects ------------------------ -- An object may be missing due to a partial clone or fetch, or missing due - to repository corruption. To differentiate these cases, the local - repository specially indicates such filtered packfiles obtained from the - promisor remote as "promisor packfiles". +- An object may be missing due to a partial clone or fetch, or missing + due to repository corruption. To differentiate these cases, the + local repository specially indicates such filtered packfiles + obtained from promisor remotes as "promisor packfiles". + These promisor packfiles consist of a "<name>.promisor" file with arbitrary contents (like the "<name>.keep" files), in addition to their "<name>.pack" and "<name>.idx" files. - The local repository considers a "promisor object" to be an object that - it knows (to the best of its ability) that the promisor remote has promised - that it has, either because the local repository has that object in one of + it knows (to the best of its ability) that promisor remotes have promised + that they have, either because the local repository has that object in one of its promisor packfiles, or because another promisor object refers to it. + When Git encounters a missing object, Git can see if it is a promisor object @@ -123,12 +131,12 @@ expensive-to-modify list of missing objects.[a] - Since almost all Git code currently expects any referenced object to be present locally and because we do not want to force every command to do a dry-run first, a fallback mechanism is added to allow Git to attempt - to dynamically fetch missing objects from the promisor remote. + to dynamically fetch missing objects from promisor remotes. + When the normal object lookup fails to find an object, Git invokes -fetch-object to try to get the object from the server and then retry -the object lookup. This allows objects to be "faulted in" without -complicated prediction algorithms. +promisor_remote_get_direct() to try to get the object from a promisor +remote and then retry the object lookup. This allows objects to be +"faulted in" without complicated prediction algorithms. + For efficiency reasons, no check as to whether the missing object is actually a promisor object is performed. @@ -157,8 +165,7 @@ and prefetch those objects in bulk. + We are not happy with this global variable and would like to remove it, but that requires significant refactoring of the object code to pass an -additional flag. We hope that concurrent efforts to add an ODB API can -encompass this. +additional flag. Fetching Missing Objects @@ -182,21 +189,63 @@ has been updated to not use any object flags when the corresponding argument though they are not necessary. +Using many promisor remotes +--------------------------- + +Many promisor remotes can be configured and used. + +This allows for example a user to have multiple geographically-close +cache servers for fetching missing blobs while continuing to do +filtered `git-fetch` commands from the central server. + +When fetching objects, promisor remotes are tried one after the other +until all the objects have been fetched. + +Remotes that are considered "promisor" remotes are those specified by +the following configuration variables: + +- `extensions.partialClone = <name>` + +- `remote.<name>.promisor = true` + +- `remote.<name>.partialCloneFilter = ...` + +Only one promisor remote can be configured using the +`extensions.partialClone` config variable. This promisor remote will +be the last one tried when fetching objects. + +We decided to make it the last one we try, because it is likely that +someone using many promisor remotes is doing so because the other +promisor remotes are better for some reason (maybe they are closer or +faster for some kind of objects) than the origin, and the origin is +likely to be the remote specified by extensions.partialClone. + +This justification is not very strong, but one choice had to be made, +and anyway the long term plan should be to make the order somehow +fully configurable. + +For now though the other promisor remotes will be tried in the order +they appear in the config file. + Current Limitations ------------------- -- The remote used for a partial clone (or the first partial fetch - following a regular clone) is marked as the "promisor remote". +- It is not possible to specify the order in which the promisor + remotes are tried in other ways than the order in which they appear + in the config file. + -We are currently limited to a single promisor remote and only that -remote may be used for subsequent partial fetches. +It is also not possible to specify an order to be used when fetching +from one remote and a different order when fetching from another +remote. + +- It is not possible to push only specific objects to a promisor + remote. + -We accept this limitation because we believe initial users of this -feature will be using it on repositories with a strong single central -server. +It is not possible to push at the same time to multiple promisor +remote in a specific order. -- Dynamic object fetching will only ask the promisor remote for missing - objects. We assume that the promisor remote has a complete view of the +- Dynamic object fetching will only ask promisor remotes for missing + objects. We assume that promisor remotes have a complete view of the repository and can satisfy all such requests. - Repack essentially treats promisor and non-promisor packfiles as 2 @@ -218,15 +267,17 @@ server. Future Work ----------- -- Allow more than one promisor remote and define a strategy for fetching - missing objects from specific promisor remotes or of iterating over the - set of promisor remotes until a missing object is found. +- Improve the way to specify the order in which promisor remotes are + tried. + -A user might want to have multiple geographically-close cache servers -for fetching missing blobs while continuing to do filtered `git-fetch` -commands from the central server, for example. +For example this could allow to specify explicitly something like: +"When fetching from this remote, I want to use these promisor remotes +in this order, though, when pushing or fetching to that remote, I want +to use those promisor remotes in that order." + +- Allow pushing to promisor remotes. + -Or the user might want to work in a triangular work flow with multiple +The user might want to work in a triangular work flow with multiple promisor remotes that each have an incomplete view of the repository. - Allow repack to work on promisor packfiles (while keeping them distinct @@ -884,7 +884,6 @@ LIB_OBJS += ewah/ewah_io.o LIB_OBJS += ewah/ewah_rlw.o LIB_OBJS += exec-cmd.o LIB_OBJS += fetch-negotiator.o -LIB_OBJS += fetch-object.o LIB_OBJS += fetch-pack.o LIB_OBJS += fsck.o LIB_OBJS += fsmonitor.o @@ -948,6 +947,7 @@ LIB_OBJS += preload-index.o LIB_OBJS += pretty.o LIB_OBJS += prio-queue.o LIB_OBJS += progress.o +LIB_OBJS += promisor-remote.o LIB_OBJS += prompt.o LIB_OBJS += protocol.o LIB_OBJS += quote.o diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 995d47c85a..d6a1aa74cd 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -15,6 +15,7 @@ #include "sha1-array.h" #include "packfile.h" #include "object-store.h" +#include "promisor-remote.h" struct batch_options { int enabled; @@ -524,8 +525,8 @@ static int batch_objects(struct batch_options *opt) if (opt->all_objects) { struct object_cb_data cb; - if (repository_format_partial_clone) - warning("This repository has extensions.partialClone set. Some objects may not be loaded."); + if (has_promisor_remote()) + warning("This repository uses promisor remotes. Some objects may not be loaded."); cb.opt = opt; cb.expand = &data; diff --git a/builtin/fetch.c b/builtin/fetch.c index 54d6b01892..538f0e7207 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -24,6 +24,7 @@ #include "list-objects-filter-options.h" #include "commit-reach.h" #include "branch.h" +#include "promisor-remote.h" #define FORCED_UPDATES_DELAY_WARNING_IN_MS (10 * 1000) @@ -1559,37 +1560,27 @@ static inline void fetch_one_setup_partial(struct remote *remote) * If no prior partial clone/fetch and the current fetch DID NOT * request a partial-fetch, do a normal fetch. */ - if (!repository_format_partial_clone && !filter_options.choice) + if (!has_promisor_remote() && !filter_options.choice) return; /* - * If this is the FIRST partial-fetch request, we enable partial - * on this repo and remember the given filter-spec as the default - * for subsequent fetches to this remote. + * If this is a partial-fetch request, we enable partial on + * this repo if not already enabled and remember the given + * filter-spec as the default for subsequent fetches to this + * remote. */ - if (!repository_format_partial_clone && filter_options.choice) { + if (filter_options.choice) { partial_clone_register(remote->name, &filter_options); return; } /* - * We are currently limited to only ONE promisor remote and only - * allow partial-fetches from the promisor remote. - */ - if (strcmp(remote->name, repository_format_partial_clone)) { - if (filter_options.choice) - die(_("--filter can only be used with the remote " - "configured in extensions.partialClone")); - return; - } - - /* * Do a partial-fetch from the promisor remote using either the * explicitly given filter-spec or inherit the filter-spec from * the config. */ if (!filter_options.choice) - partial_clone_get_default_filter_spec(&filter_options); + partial_clone_get_default_filter_spec(&filter_options, remote->name); return; } @@ -1710,7 +1701,7 @@ int cmd_fetch(int argc, const char **argv, const char *prefix) if (depth || deepen_since || deepen_not.nr) deepen = 1; - if (filter_options.choice && !repository_format_partial_clone) + if (filter_options.choice && !has_promisor_remote()) die("--filter can only be used when extensions.partialClone is set"); if (all) { @@ -1744,7 +1735,7 @@ int cmd_fetch(int argc, const char **argv, const char *prefix) } if (remote) { - if (filter_options.choice || repository_format_partial_clone) + if (filter_options.choice || has_promisor_remote()) fetch_one_setup_partial(remote); result = fetch_one(remote, argc, argv, prune_tags_ok); } else { diff --git a/builtin/gc.c b/builtin/gc.c index a22b6ff683..fadb45489f 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -27,6 +27,7 @@ #include "pack-objects.h" #include "blob.h" #include "tree.h" +#include "promisor-remote.h" #define FAILED_RUN "failed to run %s" @@ -659,7 +660,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix) argv_array_push(&prune, prune_expire); if (quiet) argv_array_push(&prune, "--no-progress"); - if (repository_format_partial_clone) + if (has_promisor_remote()) argv_array_push(&prune, "--exclude-promisor-objects"); if (run_command_v_opt(prune.argv, RUN_GIT_CMD)) diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 0d55f73b0b..a23454da6e 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -14,7 +14,7 @@ #include "thread-utils.h" #include "packfile.h" #include "object-store.h" -#include "fetch-object.h" +#include "promisor-remote.h" static const char index_pack_usage[] = "git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])"; @@ -1352,7 +1352,7 @@ static void fix_unresolved_deltas(struct hashfile *f) sorted_by_pos[i] = &ref_deltas[i]; QSORT(sorted_by_pos, nr_ref_deltas, delta_pos_compare); - if (repository_format_partial_clone) { + if (has_promisor_remote()) { /* * Prefetch the delta bases. */ @@ -1366,8 +1366,8 @@ static void fix_unresolved_deltas(struct hashfile *f) oid_array_append(&to_fetch, &d->oid); } if (to_fetch.nr) - fetch_objects(repository_format_partial_clone, - to_fetch.oid, to_fetch.nr); + promisor_remote_get_direct(the_repository, + to_fetch.oid, to_fetch.nr); oid_array_clear(&to_fetch); } diff --git a/builtin/repack.c b/builtin/repack.c index 632c0c0a79..3b3dd14372 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -11,6 +11,7 @@ #include "midx.h" #include "packfile.h" #include "object-store.h" +#include "promisor-remote.h" static int delta_base_offset = 1; static int pack_kept_objects = -1; @@ -361,7 +362,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) argv_array_push(&cmd.args, "--all"); argv_array_push(&cmd.args, "--reflog"); argv_array_push(&cmd.args, "--indexed-objects"); - if (repository_format_partial_clone) + if (has_promisor_remote()) argv_array_push(&cmd.args, "--exclude-promisor-objects"); if (write_bitmaps > 0) argv_array_push(&cmd.args, "--write-bitmap-index"); diff --git a/cache-tree.c b/cache-tree.c index c22161f987..0e5724fad7 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -5,6 +5,7 @@ #include "cache-tree.h" #include "object-store.h" #include "replace-object.h" +#include "promisor-remote.h" #ifndef DEBUG_CACHE_TREE #define DEBUG_CACHE_TREE 0 @@ -357,7 +358,7 @@ static int update_one(struct cache_tree *it, } ce_missing_ok = mode == S_IFGITLINK || missing_ok || - (repository_format_partial_clone && + (has_promisor_remote() && ce_skip_worktree(ce)); if (is_null_oid(oid) || (!ce_missing_ok && !has_object_file(oid))) { @@ -937,8 +937,6 @@ extern int grafts_replace_parents; #define GIT_REPO_VERSION 0 #define GIT_REPO_VERSION_READ 1 extern int repository_format_precious_objects; -extern char *repository_format_partial_clone; -extern const char *core_partial_clone_filter_default; extern int repository_format_worktree_config; /* @@ -1379,11 +1379,6 @@ static int git_default_core_config(const char *var, const char *value, void *cb) return 0; } - if (!strcmp(var, "core.partialclonefilter")) { - return git_config_string(&core_partial_clone_filter_default, - var, value); - } - if (!strcmp(var, "core.usereplacerefs")) { read_replace_refs = git_config_bool(var, value); return 0; diff --git a/connected.c b/connected.c index cd9b324afa..971db009b3 100644 --- a/connected.c +++ b/connected.c @@ -5,6 +5,7 @@ #include "connected.h" #include "transport.h" #include "packfile.h" +#include "promisor-remote.h" /* * If we feed all the commits we want to verify to this command @@ -73,7 +74,7 @@ int check_connected(oid_iterate_fn fn, void *cb_data, argv_array_push(&rev_list.args,"rev-list"); argv_array_push(&rev_list.args, "--objects"); argv_array_push(&rev_list.args, "--stdin"); - if (repository_format_partial_clone) + if (has_promisor_remote()) argv_array_push(&rev_list.args, "--exclude-promisor-objects"); if (!opt->is_deepening_fetch) { argv_array_push(&rev_list.args, "--not"); @@ -25,7 +25,7 @@ #include "packfile.h" #include "parse-options.h" #include "help.h" -#include "fetch-object.h" +#include "promisor-remote.h" #ifdef NO_FAST_WORKING_DIRECTORY #define FAST_WORKING_DIRECTORY 0 @@ -6520,8 +6520,7 @@ static void add_if_missing(struct repository *r, void diffcore_std(struct diff_options *options) { - if (options->repo == the_repository && - repository_format_partial_clone) { + if (options->repo == the_repository && has_promisor_remote()) { /* * Prefetch the diff pairs that are about to be flushed. */ @@ -6538,8 +6537,8 @@ void diffcore_std(struct diff_options *options) /* * NEEDSWORK: Consider deduplicating the OIDs sent. */ - fetch_objects(repository_format_partial_clone, - to_fetch.oid, to_fetch.nr); + promisor_remote_get_direct(options->repo, + to_fetch.oid, to_fetch.nr); oid_array_clear(&to_fetch); } diff --git a/environment.c b/environment.c index 89af47cb85..efa072680a 100644 --- a/environment.c +++ b/environment.c @@ -31,8 +31,6 @@ int warn_ambiguous_refs = 1; int warn_on_object_refname_ambiguity = 1; int ref_paranoia = -1; int repository_format_precious_objects; -char *repository_format_partial_clone; -const char *core_partial_clone_filter_default; int repository_format_worktree_config; const char *git_commit_encoding; const char *git_log_output_encoding; diff --git a/fetch-object.c b/fetch-object.c deleted file mode 100644 index 4266548800..0000000000 --- a/fetch-object.c +++ /dev/null @@ -1,40 +0,0 @@ -#include "cache.h" -#include "packfile.h" -#include "pkt-line.h" -#include "strbuf.h" -#include "transport.h" -#include "fetch-object.h" - -static void fetch_refs(const char *remote_name, struct ref *ref) -{ - struct remote *remote; - struct transport *transport; - int original_fetch_if_missing = fetch_if_missing; - - fetch_if_missing = 0; - remote = remote_get(remote_name); - if (!remote->url[0]) - die(_("Remote with no URL")); - transport = transport_get(remote, remote->url[0]); - - transport_set_option(transport, TRANS_OPT_FROM_PROMISOR, "1"); - transport_set_option(transport, TRANS_OPT_NO_DEPENDENTS, "1"); - transport_fetch_refs(transport, ref); - fetch_if_missing = original_fetch_if_missing; -} - -void fetch_objects(const char *remote_name, const struct object_id *oids, - int oid_nr) -{ - struct ref *ref = NULL; - int i; - - for (i = 0; i < oid_nr; i++) { - struct ref *new_ref = alloc_ref(oid_to_hex(&oids[i])); - oidcpy(&new_ref->old_oid, &oids[i]); - new_ref->exact_oid = 1; - new_ref->next = ref; - ref = new_ref; - } - fetch_refs(remote_name, ref); -} diff --git a/fetch-object.h b/fetch-object.h deleted file mode 100644 index d6444caa5a..0000000000 --- a/fetch-object.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef FETCH_OBJECT_H -#define FETCH_OBJECT_H - -struct object_id; - -void fetch_objects(const char *remote_name, const struct object_id *oids, - int oid_nr); - -#endif diff --git a/list-objects-filter-options.c b/list-objects-filter-options.c index 1cb20c659c..28c571f922 100644 --- a/list-objects-filter-options.c +++ b/list-objects-filter-options.c @@ -6,6 +6,7 @@ #include "list-objects.h" #include "list-objects-filter.h" #include "list-objects-filter-options.h" +#include "promisor-remote.h" /* * Parse value of the argument to the "filter" keyword. @@ -29,6 +30,9 @@ static int gently_parse_list_objects_filter( { const char *v0; + if (!arg) + return 0; + if (filter_options->choice) { if (errbuf) { strbuf_addstr( @@ -146,41 +150,42 @@ void partial_clone_register( const char *remote, const struct list_objects_filter_options *filter_options) { - /* - * Record the name of the partial clone remote in the - * config and in the global variable -- the latter is - * used throughout to indicate that partial clone is - * enabled and to expect missing objects. - */ - if (repository_format_partial_clone && - *repository_format_partial_clone && - strcmp(remote, repository_format_partial_clone)) - die(_("cannot change partial clone promisor remote")); + char *cfg_name; + char *filter_name; - git_config_set("core.repositoryformatversion", "1"); - git_config_set("extensions.partialclone", remote); + /* Check if it is already registered */ + if (!promisor_remote_find(remote)) { + git_config_set("core.repositoryformatversion", "1"); - repository_format_partial_clone = xstrdup(remote); + /* Add promisor config for the remote */ + cfg_name = xstrfmt("remote.%s.promisor", remote); + git_config_set(cfg_name, "true"); + free(cfg_name); + } /* * Record the initial filter-spec in the config as * the default for subsequent fetches from this remote. */ - core_partial_clone_filter_default = - xstrdup(filter_options->filter_spec); - git_config_set("core.partialclonefilter", - core_partial_clone_filter_default); + filter_name = xstrfmt("remote.%s.partialclonefilter", remote); + git_config_set(filter_name, filter_options->filter_spec); + free(filter_name); + + /* Make sure the config info are reset */ + promisor_remote_reinit(); } void partial_clone_get_default_filter_spec( - struct list_objects_filter_options *filter_options) + struct list_objects_filter_options *filter_options, + const char *remote) { + struct promisor_remote *promisor = promisor_remote_find(remote); + /* * Parse default value, but silently ignore it if it is invalid. */ - if (!core_partial_clone_filter_default) - return; - gently_parse_list_objects_filter(filter_options, - core_partial_clone_filter_default, - NULL); + if (promisor) + gently_parse_list_objects_filter(filter_options, + promisor->partial_clone_filter, + NULL); } diff --git a/list-objects-filter-options.h b/list-objects-filter-options.h index c54f0000fb..8deaa287b5 100644 --- a/list-objects-filter-options.h +++ b/list-objects-filter-options.h @@ -87,6 +87,7 @@ void partial_clone_register( const char *remote, const struct list_objects_filter_options *filter_options); void partial_clone_get_default_filter_spec( - struct list_objects_filter_options *filter_options); + struct list_objects_filter_options *filter_options, + const char *remote); #endif /* LIST_OBJECTS_FILTER_OPTIONS_H */ diff --git a/packfile.c b/packfile.c index d98ac22876..1a7d69fe32 100644 --- a/packfile.c +++ b/packfile.c @@ -17,6 +17,7 @@ #include "object-store.h" #include "midx.h" #include "commit-graph.h" +#include "promisor-remote.h" char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, @@ -2132,7 +2133,7 @@ int is_promisor_object(const struct object_id *oid) static int promisor_objects_prepared; if (!promisor_objects_prepared) { - if (repository_format_partial_clone) { + if (has_promisor_remote()) { for_each_packed_object(add_promisor_object, &promisor_objects, FOR_EACH_OBJECT_PROMISOR_ONLY); diff --git a/promisor-remote.c b/promisor-remote.c new file mode 100644 index 0000000000..9bc296cdde --- /dev/null +++ b/promisor-remote.c @@ -0,0 +1,265 @@ +#include "cache.h" +#include "object-store.h" +#include "promisor-remote.h" +#include "config.h" +#include "transport.h" + +static char *repository_format_partial_clone; +static const char *core_partial_clone_filter_default; + +void set_repository_format_partial_clone(char *partial_clone) +{ + repository_format_partial_clone = xstrdup_or_null(partial_clone); +} + +static int fetch_refs(const char *remote_name, struct ref *ref) +{ + struct remote *remote; + struct transport *transport; + int original_fetch_if_missing = fetch_if_missing; + int res; + + fetch_if_missing = 0; + remote = remote_get(remote_name); + if (!remote->url[0]) + die(_("Remote with no URL")); + transport = transport_get(remote, remote->url[0]); + + transport_set_option(transport, TRANS_OPT_FROM_PROMISOR, "1"); + transport_set_option(transport, TRANS_OPT_NO_DEPENDENTS, "1"); + res = transport_fetch_refs(transport, ref); + fetch_if_missing = original_fetch_if_missing; + + return res; +} + +static int fetch_objects(const char *remote_name, + const struct object_id *oids, + int oid_nr) +{ + struct ref *ref = NULL; + int i; + + for (i = 0; i < oid_nr; i++) { + struct ref *new_ref = alloc_ref(oid_to_hex(&oids[i])); + oidcpy(&new_ref->old_oid, &oids[i]); + new_ref->exact_oid = 1; + new_ref->next = ref; + ref = new_ref; + } + return fetch_refs(remote_name, ref); +} + +static struct promisor_remote *promisors; +static struct promisor_remote **promisors_tail = &promisors; + +static struct promisor_remote *promisor_remote_new(const char *remote_name) +{ + struct promisor_remote *r; + + if (*remote_name == '/') { + warning(_("promisor remote name cannot begin with '/': %s"), + remote_name); + return NULL; + } + + FLEX_ALLOC_STR(r, name, remote_name); + + *promisors_tail = r; + promisors_tail = &r->next; + + return r; +} + +static struct promisor_remote *promisor_remote_lookup(const char *remote_name, + struct promisor_remote **previous) +{ + struct promisor_remote *r, *p; + + for (p = NULL, r = promisors; r; p = r, r = r->next) + if (!strcmp(r->name, remote_name)) { + if (previous) + *previous = p; + return r; + } + + return NULL; +} + +static void promisor_remote_move_to_tail(struct promisor_remote *r, + struct promisor_remote *previous) +{ + if (previous) + previous->next = r->next; + else + promisors = r->next ? r->next : r; + r->next = NULL; + *promisors_tail = r; + promisors_tail = &r->next; +} + +static int promisor_remote_config(const char *var, const char *value, void *data) +{ + const char *name; + int namelen; + const char *subkey; + + if (!strcmp(var, "core.partialclonefilter")) + return git_config_string(&core_partial_clone_filter_default, + var, value); + + if (parse_config_key(var, "remote", &name, &namelen, &subkey) < 0) + return 0; + + if (!strcmp(subkey, "promisor")) { + char *remote_name; + + if (!git_config_bool(var, value)) + return 0; + + remote_name = xmemdupz(name, namelen); + + if (!promisor_remote_lookup(remote_name, NULL)) + promisor_remote_new(remote_name); + + free(remote_name); + return 0; + } + if (!strcmp(subkey, "partialclonefilter")) { + struct promisor_remote *r; + char *remote_name = xmemdupz(name, namelen); + + r = promisor_remote_lookup(remote_name, NULL); + if (!r) + r = promisor_remote_new(remote_name); + + free(remote_name); + + if (!r) + return 0; + + return git_config_string(&r->partial_clone_filter, var, value); + } + + return 0; +} + +static int initialized; + +static void promisor_remote_init(void) +{ + if (initialized) + return; + initialized = 1; + + git_config(promisor_remote_config, NULL); + + if (repository_format_partial_clone) { + struct promisor_remote *o, *previous; + + o = promisor_remote_lookup(repository_format_partial_clone, + &previous); + if (o) + promisor_remote_move_to_tail(o, previous); + else + promisor_remote_new(repository_format_partial_clone); + } +} + +static void promisor_remote_clear(void) +{ + while (promisors) { + struct promisor_remote *r = promisors; + promisors = promisors->next; + free(r); + } + + promisors_tail = &promisors; +} + +void promisor_remote_reinit(void) +{ + initialized = 0; + promisor_remote_clear(); + promisor_remote_init(); +} + +struct promisor_remote *promisor_remote_find(const char *remote_name) +{ + promisor_remote_init(); + + if (!remote_name) + return promisors; + + return promisor_remote_lookup(remote_name, NULL); +} + +int has_promisor_remote(void) +{ + return !!promisor_remote_find(NULL); +} + +static int remove_fetched_oids(struct repository *repo, + struct object_id **oids, + int oid_nr, int to_free) +{ + int i, remaining_nr = 0; + int *remaining = xcalloc(oid_nr, sizeof(*remaining)); + struct object_id *old_oids = *oids; + struct object_id *new_oids; + + for (i = 0; i < oid_nr; i++) + if (oid_object_info_extended(repo, &old_oids[i], NULL, + OBJECT_INFO_SKIP_FETCH_OBJECT)) { + remaining[i] = 1; + remaining_nr++; + } + + if (remaining_nr) { + int j = 0; + new_oids = xcalloc(remaining_nr, sizeof(*new_oids)); + for (i = 0; i < oid_nr; i++) + if (remaining[i]) + oidcpy(&new_oids[j++], &old_oids[i]); + *oids = new_oids; + if (to_free) + free(old_oids); + } + + free(remaining); + + return remaining_nr; +} + +int promisor_remote_get_direct(struct repository *repo, + const struct object_id *oids, + int oid_nr) +{ + struct promisor_remote *r; + struct object_id *remaining_oids = (struct object_id *)oids; + int remaining_nr = oid_nr; + int to_free = 0; + int res = -1; + + promisor_remote_init(); + + for (r = promisors; r; r = r->next) { + if (fetch_objects(r->name, remaining_oids, remaining_nr) < 0) { + if (remaining_nr == 1) + continue; + remaining_nr = remove_fetched_oids(repo, &remaining_oids, + remaining_nr, to_free); + if (remaining_nr) { + to_free = 1; + continue; + } + } + res = 0; + break; + } + + if (to_free) + free(remaining_oids); + + return res; +} diff --git a/promisor-remote.h b/promisor-remote.h new file mode 100644 index 0000000000..8200dfc940 --- /dev/null +++ b/promisor-remote.h @@ -0,0 +1,31 @@ +#ifndef PROMISOR_REMOTE_H +#define PROMISOR_REMOTE_H + +struct object_id; + +/* + * Promisor remote linked list + * + * Information in its fields come from remote.XXX config entries or + * from extensions.partialclone or core.partialclonefilter. + */ +struct promisor_remote { + struct promisor_remote *next; + const char *partial_clone_filter; + const char name[FLEX_ARRAY]; +}; + +extern void promisor_remote_reinit(void); +extern struct promisor_remote *promisor_remote_find(const char *remote_name); +extern int has_promisor_remote(void); +extern int promisor_remote_get_direct(struct repository *repo, + const struct object_id *oids, + int oid_nr); + +/* + * This should be used only once from setup.c to set the value we got + * from the extensions.partialclone config option. + */ +extern void set_repository_format_partial_clone(char *partial_clone); + +#endif /* PROMISOR_REMOTE_H */ @@ -4,6 +4,7 @@ #include "dir.h" #include "string-list.h" #include "chdir-notify.h" +#include "promisor-remote.h" static int inside_git_dir = -1; static int inside_work_tree = -1; @@ -478,7 +479,7 @@ static int check_repository_format_gently(const char *gitdir, struct repository_ } repository_format_precious_objects = candidate->precious_objects; - repository_format_partial_clone = xstrdup_or_null(candidate->partial_clone); + set_repository_format_partial_clone(candidate->partial_clone); repository_format_worktree_config = candidate->worktree_config; string_list_clear(&candidate->unknown_extensions, 0); diff --git a/sha1-file.c b/sha1-file.c index 4895408e1e..e85f249a5d 100644 --- a/sha1-file.c +++ b/sha1-file.c @@ -30,8 +30,8 @@ #include "mergesort.h" #include "quote.h" #include "packfile.h" -#include "fetch-object.h" #include "object-store.h" +#include "promisor-remote.h" /* The maximum size for an object header. */ #define MAX_HEADER_LEN 32 @@ -1471,16 +1471,17 @@ int oid_object_info_extended(struct repository *r, const struct object_id *oid, } /* Check if it is a missing object */ - if (fetch_if_missing && repository_format_partial_clone && + if (fetch_if_missing && has_promisor_remote() && !already_retried && r == the_repository && !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) { /* - * TODO Investigate having fetch_object() return - * TODO error/success and stopping the music here. - * TODO Pass a repository struct through fetch_object, - * such that arbitrary repositories work. + * TODO Investigate checking promisor_remote_get_direct() + * TODO return value and stopping on error here. + * TODO Pass a repository struct through + * promisor_remote_get_direct(), such that arbitrary + * repositories work. */ - fetch_objects(repository_format_partial_clone, real, 1); + promisor_remote_get_direct(r, real, 1); already_retried = 1; continue; } diff --git a/t/t0410-partial-clone.sh b/t/t0410-partial-clone.sh index 33e0aa4a89..d4b7e535ea 100755 --- a/t/t0410-partial-clone.sh +++ b/t/t0410-partial-clone.sh @@ -26,7 +26,7 @@ promise_and_delete () { test_expect_success 'extensions.partialclone without filter' ' test_create_repo server && git clone --filter="blob:none" "file://$(pwd)/server" client && - git -C client config --unset core.partialclonefilter && + git -C client config --unset remote.origin.partialclonefilter && git -C client fetch origin ' @@ -166,8 +166,9 @@ test_expect_success 'fetching of missing objects' ' # associated packfile contains the object ls repo/.git/objects/pack/pack-*.promisor >promisorlist && test_line_count = 1 promisorlist && - IDX=$(cat promisorlist | sed "s/promisor$/idx/") && - git verify-pack --verbose "$IDX" | grep "$HASH" + IDX=$(sed "s/promisor$/idx/" promisorlist) && + git verify-pack --verbose "$IDX" >out && + grep "$HASH" out ' test_expect_success 'fetching of missing objects works with ref-in-want enabled' ' @@ -182,8 +183,55 @@ test_expect_success 'fetching of missing objects works with ref-in-want enabled' grep "git< fetch=.*ref-in-want" trace ' +test_expect_success 'fetching of missing objects from another promisor remote' ' + git clone "file://$(pwd)/server" server2 && + test_commit -C server2 bar && + git -C server2 repack -a -d --write-bitmap-index && + HASH2=$(git -C server2 rev-parse bar) && + + git -C repo remote add server2 "file://$(pwd)/server2" && + git -C repo config remote.server2.promisor true && + git -C repo cat-file -p "$HASH2" && + + git -C repo fetch server2 && + rm -rf repo/.git/objects/* && + git -C repo cat-file -p "$HASH2" && + + # Ensure that the .promisor file is written, and check that its + # associated packfile contains the object + ls repo/.git/objects/pack/pack-*.promisor >promisorlist && + test_line_count = 1 promisorlist && + IDX=$(sed "s/promisor$/idx/" promisorlist) && + git verify-pack --verbose "$IDX" >out && + grep "$HASH2" out +' + +test_expect_success 'fetching of missing objects configures a promisor remote' ' + git clone "file://$(pwd)/server" server3 && + test_commit -C server3 baz && + git -C server3 repack -a -d --write-bitmap-index && + HASH3=$(git -C server3 rev-parse baz) && + git -C server3 config uploadpack.allowfilter 1 && + + rm repo/.git/objects/pack/pack-*.promisor && + + git -C repo remote add server3 "file://$(pwd)/server3" && + git -C repo fetch --filter="blob:none" server3 $HASH3 && + + test_cmp_config -C repo true remote.server3.promisor && + + # Ensure that the .promisor file is written, and check that its + # associated packfile contains the object + ls repo/.git/objects/pack/pack-*.promisor >promisorlist && + test_line_count = 1 promisorlist && + IDX=$(sed "s/promisor$/idx/" promisorlist) && + git verify-pack --verbose "$IDX" >out && + grep "$HASH3" out +' + test_expect_success 'fetching of missing blobs works' ' - rm -rf server repo && + rm -rf server server2 repo && + rm -rf server server3 repo && test_create_repo server && test_commit -C server foo && git -C server repack -a -d --write-bitmap-index && @@ -514,8 +562,9 @@ test_expect_success 'fetching of missing objects from an HTTP server' ' # associated packfile contains the object ls repo/.git/objects/pack/pack-*.promisor >promisorlist && test_line_count = 1 promisorlist && - IDX=$(cat promisorlist | sed "s/promisor$/idx/") && - git verify-pack --verbose "$IDX" | grep "$HASH" + IDX=$(sed "s/promisor$/idx/" promisorlist) && + git verify-pack --verbose "$IDX" >out && + grep "$HASH" out ' # DO NOT add non-httpd-specific tests here, because the last part of this diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh index 4a3b901f06..2e94354e5b 100755 --- a/t/t5601-clone.sh +++ b/t/t5601-clone.sh @@ -654,7 +654,8 @@ partial_clone () { git -C client fsck && # Ensure that unneeded blobs are not inadvertently fetched. - test_config -C client extensions.partialclone "not a remote" && + test_config -C client remote.origin.promisor "false" && + git -C client config --unset remote.origin.partialclonefilter && test_must_fail git -C client cat-file -e "$HASH1" && # But this blob was fetched, because clone performs an initial checkout diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh index 565254558f..73cd95812f 100755 --- a/t/t5616-partial-clone.sh +++ b/t/t5616-partial-clone.sh @@ -42,8 +42,8 @@ test_expect_success 'do partial clone 1' ' test_cmp expect_1.oids observed.oids && test "$(git -C pc1 config --local core.repositoryformatversion)" = "1" && - test "$(git -C pc1 config --local extensions.partialclone)" = "origin" && - test "$(git -C pc1 config --local core.partialclonefilter)" = "blob:none" + test "$(git -C pc1 config --local remote.origin.promisor)" = "true" && + test "$(git -C pc1 config --local remote.origin.partialclonefilter)" = "blob:none" ' # checkout master to force dynamic object fetch of blobs at HEAD. diff --git a/unpack-trees.c b/unpack-trees.c index 50f257bd5c..9c25126aec 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -16,7 +16,7 @@ #include "submodule-config.h" #include "fsmonitor.h" #include "object-store.h" -#include "fetch-object.h" +#include "promisor-remote.h" /* * Error messages expected by scripts out of plumbing commands such as @@ -400,7 +400,7 @@ static int check_updates(struct unpack_trees_options *o) load_gitmodules_file(index, &state); enable_delayed_checkout(&state); - if (repository_format_partial_clone && o->update && !o->dry_run) { + if (has_promisor_remote() && o->update && !o->dry_run) { /* * Prefetch the objects that are to be checked out in the loop * below. @@ -419,8 +419,8 @@ static int check_updates(struct unpack_trees_options *o) oid_array_append(&to_fetch, &ce->oid); } if (to_fetch.nr) - fetch_objects(repository_format_partial_clone, - to_fetch.oid, to_fetch.nr); + promisor_remote_get_direct(the_repository, + to_fetch.oid, to_fetch.nr); oid_array_clear(&to_fetch); } for (i = 0; i < index->cache_nr; i++) { |