Currently when git-fetch is asked to recurse into submodules, it dispatches a plain "git-fetch -C <submodule-dir>" (and some submodule related options such as prefix and recusing strategy, but) without any information of the remote or the tip that should be fetched. This works surprisingly well in some workflows (such as using submodules as a third party library), while not so well in other scenarios, such as in a Gerrit topic-based workflow, that can tie together changes (potentially across repositories) on the server side. One of the parts of such a Gerrit workflow is to download a change when wanting to examine it, and you'd want to have its submodule changes that are in the same topic downloaded as well. However these submodule changes reside in their own repository in their own ref (refs/changes/<int>). Retry fetching a submodule if the object id that the superproject points to, cannot be found. Note: This is an RFC and doesn't support fetching to FETCH_HEAD yet, but only into a local branch. To make fetching into FETCH_HEAD work, we need some refactoring in builtin/fetch.c to adjust the calls to 'check_for_new_submodule_commits'. Signed-off-by: Stefan Beller <sbeller@xxxxxxxxxx> --- builtin/fetch.c | 9 ++-- submodule.c | 87 ++++++++++++++++++++++++++++++++++++- t/t5526-fetch-submodules.sh | 16 +++++++ 3 files changed, 104 insertions(+), 8 deletions(-) diff --git a/builtin/fetch.c b/builtin/fetch.c index 61bec5d213d..95c44bf6ffa 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -700,8 +700,7 @@ static int update_local_ref(struct ref *ref, what = _("[new ref]"); } - if ((recurse_submodules != RECURSE_SUBMODULES_OFF) && - (recurse_submodules != RECURSE_SUBMODULES_ON)) + if (recurse_submodules != RECURSE_SUBMODULES_OFF) check_for_new_submodule_commits(&ref->new_oid); r = s_update_ref(msg, ref, 0); format_display(display, r ? '!' : '*', what, @@ -716,8 +715,7 @@ static int update_local_ref(struct ref *ref, strbuf_add_unique_abbrev(&quickref, ¤t->object.oid, DEFAULT_ABBREV); strbuf_addstr(&quickref, ".."); strbuf_add_unique_abbrev(&quickref, &ref->new_oid, DEFAULT_ABBREV); - if ((recurse_submodules != RECURSE_SUBMODULES_OFF) && - (recurse_submodules != RECURSE_SUBMODULES_ON)) + if (recurse_submodules != RECURSE_SUBMODULES_OFF) check_for_new_submodule_commits(&ref->new_oid); r = s_update_ref("fast-forward", ref, 1); format_display(display, r ? '!' : ' ', quickref.buf, @@ -731,8 +729,7 @@ static int update_local_ref(struct ref *ref, strbuf_add_unique_abbrev(&quickref, ¤t->object.oid, DEFAULT_ABBREV); strbuf_addstr(&quickref, "..."); strbuf_add_unique_abbrev(&quickref, &ref->new_oid, DEFAULT_ABBREV); - if ((recurse_submodules != RECURSE_SUBMODULES_OFF) && - (recurse_submodules != RECURSE_SUBMODULES_ON)) + if (recurse_submodules != RECURSE_SUBMODULES_OFF) check_for_new_submodule_commits(&ref->new_oid); r = s_update_ref("forced-update", ref, 1); format_display(display, r ? '!' : '+', quickref.buf, diff --git a/submodule.c b/submodule.c index 8b67f086895..702cba138be 100644 --- a/submodule.c +++ b/submodule.c @@ -1127,8 +1127,11 @@ struct submodule_parallel_fetch { int result; struct string_list changed_submodule_names; + struct string_list retry; }; -#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0, 0, STRING_LIST_INIT_DUP } +#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0, 0, \ + STRING_LIST_INIT_DUP, \ + STRING_LIST_INIT_NODUP} static void calculate_changed_submodule_paths( struct submodule_parallel_fetch *spf) @@ -1259,8 +1262,10 @@ static int get_next_submodule(struct child_process *cp, { int ret = 0; struct submodule_parallel_fetch *spf = data; + struct string_list_item *it; for (; spf->count < spf->r->index->cache_nr; spf->count++) { + int recurse_config; struct strbuf submodule_prefix = STRBUF_INIT; const struct cache_entry *ce = spf->r->index->cache[spf->count]; const char *git_dir, *default_argv; @@ -1280,7 +1285,9 @@ static int get_next_submodule(struct child_process *cp, } } - switch (get_fetch_recurse_config(submodule, spf)) + recurse_config = get_fetch_recurse_config(submodule, spf); + + switch (recurse_config) { default: case RECURSE_SUBMODULES_DEFAULT: @@ -1318,9 +1325,50 @@ static int get_next_submodule(struct child_process *cp, strbuf_release(&submodule_prefix); if (ret) { spf->count++; + if (submodule != &default_submodule) + /* discard const-ness: */ + *task_cb = (void*)submodule; return 1; } } + +retry_next: + + if (spf->retry.nr) { + struct strbuf submodule_prefix = STRBUF_INIT; + const struct submodule *sub; + + it = string_list_last(&spf->retry); + sub = submodule_from_name(spf->r, &null_oid, + it->string); + + child_process_init(cp); + cp->dir = get_submodule_git_dir(spf->r, sub->path); + if (!cp->dir) { + string_list_pop(&spf->retry, 0); + goto retry_next; + } + prepare_submodule_repo_env_in_gitdir(&cp->env_array); + cp->git_cmd = 1; + + strbuf_addf(&submodule_prefix, "%s%s/", spf->prefix, sub->path); + argv_array_init(&cp->args); + argv_array_pushv(&cp->args, spf->args.argv); + argv_array_push(&cp->args, "on-demand"); + argv_array_push(&cp->args, "--submodule-prefix"); + argv_array_push(&cp->args, submodule_prefix.buf); + + /* NEEDSWORK: have get_default_remote from s--h */ + argv_array_push(&cp->args, "origin"); + oid_array_for_each_unique(it->util, + append_oid_to_argv, &cp->args); + + *task_cb = NULL; /* make sure we do not recurse forever */ + strbuf_release(&submodule_prefix); + string_list_pop(&spf->retry, 0); + return 1; + } + return 0; } @@ -1334,14 +1382,49 @@ static int fetch_start_failure(struct strbuf *err, return 0; } +static int commit_exists_in_sub(const struct object_id *oid, void *data) +{ + struct repository *subrepo = data; + + enum object_type type = oid_object_info(subrepo, oid, NULL); + + return type == OBJ_COMMIT; +} + static int fetch_finish(int retvalue, struct strbuf *err, void *cb, void *task_cb) { struct submodule_parallel_fetch *spf = cb; + struct submodule *sub = task_cb; + struct repository subrepo; if (retvalue) spf->result = 1; + if (!sub) + return 0; + + if (repo_submodule_init(&subrepo, spf->r, sub->path) < 0) + warning(_("Could not get submodule repository for submodule '%s' in repository '%s'"), + sub->path, spf->r->worktree); + else { + struct string_list_item *it; + struct oid_array *commits; + + it = string_list_lookup(&spf->changed_submodule_names, sub->name); + if (!it) + return 0; + + commits = it->util; + oid_array_filter(commits, + commit_exists_in_sub, + &subrepo); + + if (commits->nr) + string_list_append(&spf->retry, sub->name) + ->util = commits; + } + return 0; } diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh index 42692219a1a..af12c50e7dd 100755 --- a/t/t5526-fetch-submodules.sh +++ b/t/t5526-fetch-submodules.sh @@ -605,4 +605,20 @@ test_expect_success "fetch new commits when submodule got renamed" ' test_cmp expect actual ' +test_expect_success "fetch new commits on-demand when they are not reachable" ' + git checkout --detach && + C=$(git -C submodule commit-tree -m "new change outside refs/heads" HEAD^{tree}) && + git -C submodule update-ref refs/changes/1 $C && + git update-index --cacheinfo 160000 $C submodule && + git commit -m "updated submodule outside of refs/heads" && + D=$(git rev-parse HEAD) && + git update-ref refs/changes/2 $D && + ( + cd downstream && + git fetch --recurse-submodules --recurse-submodules-default on-demand origin refs/changes/2:refs/heads/my_branch && + git -C submodule cat-file -t $C && + git checkout --recurse-submodules FETCH_HEAD + ) +' + test_done -- 2.19.0.rc1.350.ge57e33dbd1-goog