From 4074d3c7e1a3b44c5c02235799d798f8b2613333 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 31 Jan 2023 13:29:15 +0000 Subject: [PATCH] clone: set fetch.bundleURI if appropriate Bundle providers may organize their bundle lists in a way that is intended to improve incremental fetches, not just initial clones. However, they do need to state that they have organized with that in mind, or else the client will not expect to save time by downloading bundles after the initial clone. This is done by specifying a bundle.heuristic value. There are two types of bundle lists: those at a static URI and those that are advertised from a Git remote over protocol v2. The new fetch.bundleURI config value applies for static bundle URIs that are not advertised over protocol v2. If the user specifies a static URI via 'git clone --bundle-uri', then Git can set this config as a reminder for future 'git fetch' operations to check the bundle list before connecting to the remote(s). For lists provided over protocol v2, we will want to take a different approach and create a property of the remote itself by creating a remote..* type config key. That is not implemented in this change. Later changes will update 'git fetch' to consume this option. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/config/fetch.txt | 8 +++++++ builtin/clone.c | 6 +++++- bundle-uri.c | 5 ++++- bundle-uri.h | 8 ++++++- t/t5558-clone-bundle-uri.sh | 39 ++++++++++++++++++++++++++++++++++ 5 files changed, 63 insertions(+), 3 deletions(-) diff --git a/Documentation/config/fetch.txt b/Documentation/config/fetch.txt index cd65d236b4..244f44d460 100644 --- a/Documentation/config/fetch.txt +++ b/Documentation/config/fetch.txt @@ -96,3 +96,11 @@ fetch.writeCommitGraph:: merge and the write may take longer. Having an updated commit-graph file helps performance of many Git commands, including `git merge-base`, `git push -f`, and `git log --graph`. Defaults to false. + +fetch.bundleURI:: + This value stores a URI for downloading Git object data from a bundle + URI before performing an incremental fetch from the origin Git server. + This is similar to how the `--bundle-uri` option behaves in + linkgit:git-clone[1]. `git clone --bundle-uri` will set the + `fetch.bundleURI` value if the supplied bundle URI contains a bundle + list that is organized for incremental fetches. diff --git a/builtin/clone.c b/builtin/clone.c index 430b2e981e..fa7f0ac42f 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -1248,12 +1248,16 @@ int cmd_clone(int argc, const char **argv, const char *prefix) * data from the --bundle-uri option. */ if (bundle_uri) { + int has_heuristic = 0; + /* At this point, we need the_repository to match the cloned repo. */ if (repo_init(the_repository, git_dir, work_tree)) warning(_("failed to initialize the repo, skipping bundle URI")); - else if (fetch_bundle_uri(the_repository, bundle_uri)) + else if (fetch_bundle_uri(the_repository, bundle_uri, &has_heuristic)) warning(_("failed to fetch objects from bundle URI '%s'"), bundle_uri); + else if (has_heuristic) + git_config_set_gently("fetch.bundleuri", bundle_uri); } strvec_push(&transport_ls_refs_options.ref_prefixes, "HEAD"); diff --git a/bundle-uri.c b/bundle-uri.c index af48938d24..7a1b6d94bf 100644 --- a/bundle-uri.c +++ b/bundle-uri.c @@ -736,7 +736,8 @@ static int unlink_bundle(struct remote_bundle_info *info, void *data) return 0; } -int fetch_bundle_uri(struct repository *r, const char *uri) +int fetch_bundle_uri(struct repository *r, const char *uri, + int *has_heuristic) { int result; struct bundle_list list; @@ -756,6 +757,8 @@ int fetch_bundle_uri(struct repository *r, const char *uri) result = unbundle_all_bundles(r, &list); cleanup: + if (has_heuristic) + *has_heuristic = (list.heuristic != BUNDLE_HEURISTIC_NONE); for_all_bundles_in_list(&list, unlink_bundle, NULL); clear_bundle_list(&list); clear_remote_bundle_info(&bundle, NULL); diff --git a/bundle-uri.h b/bundle-uri.h index ef32840bfa..6dbc780f66 100644 --- a/bundle-uri.h +++ b/bundle-uri.h @@ -124,8 +124,14 @@ int bundle_uri_parse_config_format(const char *uri, * based on that information. * * Returns non-zero if no bundle information is found at the given 'uri'. + * + * If the pointer 'has_heuristic' is non-NULL, then the value it points to + * will be set to be non-zero if and only if the fetched list has a + * heuristic value. Such a value indicates that the list was designed for + * incremental fetches. */ -int fetch_bundle_uri(struct repository *r, const char *uri); +int fetch_bundle_uri(struct repository *r, const char *uri, + int *has_heuristic); /** * Given a bundle list that was already advertised (likely by the diff --git a/t/t5558-clone-bundle-uri.sh b/t/t5558-clone-bundle-uri.sh index 6f9417a0af..b2d15e141c 100755 --- a/t/t5558-clone-bundle-uri.sh +++ b/t/t5558-clone-bundle-uri.sh @@ -432,6 +432,8 @@ test_expect_success 'clone incomplete bundle list (http, creationToken)' ' --single-branch --branch=base --no-tags \ "$HTTPD_URL/smart/fetch.git" clone-token-http && + test_cmp_config -C clone-token-http "$HTTPD_URL/bundle-list" fetch.bundleuri && + cat >expect <<-EOF && $HTTPD_URL/bundle-list $HTTPD_URL/bundle-1.bundle @@ -441,6 +443,43 @@ test_expect_success 'clone incomplete bundle list (http, creationToken)' ' test_cmp expect actual ' +test_expect_success 'http clone with bundle.heuristic creates fetch.bundleURI' ' + test_when_finished rm -rf fetch-http-4 trace*.txt && + + cat >"$HTTPD_DOCUMENT_ROOT_PATH/bundle-list" <<-EOF && + [bundle] + version = 1 + mode = all + heuristic = creationToken + + [bundle "bundle-1"] + uri = bundle-1.bundle + creationToken = 1 + EOF + + GIT_TRACE2_EVENT="$(pwd)/trace-clone.txt" \ + git clone --single-branch --branch=base \ + --bundle-uri="$HTTPD_URL/bundle-list" \ + "$HTTPD_URL/smart/fetch.git" fetch-http-4 && + + test_cmp_config -C fetch-http-4 "$HTTPD_URL/bundle-list" fetch.bundleuri && + + cat >expect <<-EOF && + $HTTPD_URL/bundle-list + $HTTPD_URL/bundle-1.bundle + EOF + + test_remote_https_urls actual && + test_cmp expect actual && + + # only received base ref from bundle-1 + git -C fetch-http-4 for-each-ref --format="%(refname)" "refs/bundles/*" >refs && + cat >expect <<-\EOF && + refs/bundles/base + EOF + test_cmp expect refs +' + # Do not add tests here unless they use the HTTP server, as they will # not run unless the HTTP dependencies exist.