| Message ID | d15f67c40ea10eff8d83df72a86b8677607f4ee3.1611596534.git.gitgitgadget@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Sparse Index | expand |
On Mon, Jan 25, 2021 at 9:42 AM Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com> wrote: > > From: Derrick Stolee <dstolee@microsoft.com> > > Previously, we enabled the sparse index format only using > GIT_TEST_SPARSE_INDEX=1. This is not a feasible direction for users to > actually select this mode. Further, sparse directory entries are not > understood by the index formats as advertised. > > We _could_ add a new index version that explicitly adds these > capabilities, but there are nuances to index formats 2, 3, and 4 that > are still valuable to select as options. For now, create a repo > extension, "extensions.sparseIndex", that specifies that the tool > reading this repository must understand sparse directory entries. > > This change only encodes the extension and enables it when > GIT_TEST_SPARSE_INDEX=1. Later, we will add a more user-friendly CLI > mechanism. One other interesting thing to note is that last I checked, jgit doesn't support index format v4, which makes us unable to use it. Making a v5 would force jgit to support all previous index formats in order to support your new feature. However, the jgit thing is going to make it hard for me to find other users willing to test out this feature at $DAYJOB. But I don't think there's anyway around that; you need to change the index format. And you at least have jrnieder cc'ed. :-) > > Signed-off-by: Derrick Stolee <dstolee@microsoft.com> > --- > Documentation/config/extensions.txt | 7 ++++++ > cache.h | 1 + > repo-settings.c | 7 ++++++ > repository.h | 3 ++- > setup.c | 3 +++ > sparse-index.c | 38 +++++++++++++++++++++++++---- > 6 files changed, 53 insertions(+), 6 deletions(-) > > diff --git a/Documentation/config/extensions.txt b/Documentation/config/extensions.txt > index 4e23d73cdca..5c86b364873 100644 > --- a/Documentation/config/extensions.txt > +++ b/Documentation/config/extensions.txt > @@ -6,3 +6,10 @@ extensions.objectFormat:: > Note that this setting should only be set by linkgit:git-init[1] or > linkgit:git-clone[1]. Trying to change it after initialization will not > work and will produce hard-to-diagnose issues. > + > +extensions.sparseIndex:: > + When combined with `core.sparseCheckout=true` and > + `core.sparseCheckoutCone=true`, the index may contain entries > + corresponding to directories outside of the sparse-checkout > + definition. Versions of Git that do not understand this extension > + do not expect directory entries in the index. Perhaps to make this slightly more explicit ("corresponding to" can be fuzzy and be read to assume you are talking about file entries underneath a directory rather than directory entries, so add an extra phrase to rule that out): ...the index may contain entries corresponding to directories outside of the sparse-checkout definition in lieu of containing each path under such directories... > diff --git a/cache.h b/cache.h > index b05341cc687..dcf089b7006 100644 > --- a/cache.h > +++ b/cache.h > @@ -1054,6 +1054,7 @@ struct repository_format { > int worktree_config; > int is_bare; > int hash_algo; > + int sparse_index; > char *work_tree; > struct string_list unknown_extensions; > struct string_list v1_only_extensions; > diff --git a/repo-settings.c b/repo-settings.c > index d63569e4041..9677d50f923 100644 > --- a/repo-settings.c > +++ b/repo-settings.c > @@ -85,4 +85,11 @@ void prepare_repo_settings(struct repository *r) > * removed. > */ > r->settings.command_requires_full_index = 1; > + > + /* > + * Initialize this as off. > + */ > + r->settings.sparse_index = 0; > + if (!repo_config_get_bool(r, "extensions.sparseindex", &value) && value) > + r->settings.sparse_index = 1; > } > diff --git a/repository.h b/repository.h > index e06a2301569..a45f7520fd9 100644 > --- a/repository.h > +++ b/repository.h > @@ -42,7 +42,8 @@ struct repo_settings { > > int core_multi_pack_index; > > - unsigned command_requires_full_index:1; > + unsigned command_requires_full_index:1, > + sparse_index:1; > }; > > struct repository { > diff --git a/setup.c b/setup.c > index c04cd25a30d..cd839456461 100644 > --- a/setup.c > +++ b/setup.c > @@ -500,6 +500,9 @@ static enum extension_result handle_extension(const char *var, > return error("invalid value for 'extensions.objectformat'"); > data->hash_algo = format; > return EXTENSION_OK; > + } else if (!strcmp(ext, "sparseindex")) { > + data->sparse_index = 1; > + return EXTENSION_OK; > } > return EXTENSION_UNKNOWN; > } > diff --git a/sparse-index.c b/sparse-index.c > index 5dd0b835b9d..71544095267 100644 > --- a/sparse-index.c > +++ b/sparse-index.c > @@ -102,19 +102,47 @@ static int convert_to_sparse_rec(struct index_state *istate, > return num_converted - start_converted; > } > > +static int enable_sparse_index(struct repository *repo) > +{ > + const char *config_path = repo_git_path(repo, "config.worktree"); > + > + if (upgrade_repository_format(1) < 0) { > + warning(_("unable to upgrade repository format to enable sparse-index")); > + return -1; > + } > + git_config_set_in_file_gently(config_path, > + "extensions.sparseIndex", > + "true"); > + > + prepare_repo_settings(repo); > + repo->settings.sparse_index = 1; > + return 0; > +} > + > int convert_to_sparse(struct index_state *istate) > { > if (istate->split_index || istate->sparse_index || > !core_apply_sparse_checkout || !core_sparse_checkout_cone) > return 0; > > + if (!istate->repo) > + istate->repo = the_repository; > + > + /* > + * The GIT_TEST_SPARSE_INDEX environment variable triggers the > + * extensions.sparseIndex config variable to be on. > + */ > + if (git_env_bool("GIT_TEST_SPARSE_INDEX", 0)) { > + int err = enable_sparse_index(istate->repo); > + if (err < 0) > + return err; > + } > + > /* > - * For now, only create a sparse index with the > - * GIT_TEST_SPARSE_INDEX environment variable. We will relax > - * this once we have a proper way to opt-in (and later still, > - * opt-out). > + * Only convert to sparse if extensions.sparseIndex is set. > */ > - if (!git_env_bool("GIT_TEST_SPARSE_INDEX", 0)) > + prepare_repo_settings(istate->repo); > + if (!istate->repo->settings.sparse_index) > return 0; > > if (!istate->sparse_checkout_patterns) { > -- > gitgitgadget
diff --git a/Documentation/config/extensions.txt b/Documentation/config/extensions.txt index 4e23d73cdca..5c86b364873 100644 --- a/Documentation/config/extensions.txt +++ b/Documentation/config/extensions.txt @@ -6,3 +6,10 @@ extensions.objectFormat:: Note that this setting should only be set by linkgit:git-init[1] or linkgit:git-clone[1]. Trying to change it after initialization will not work and will produce hard-to-diagnose issues. + +extensions.sparseIndex:: + When combined with `core.sparseCheckout=true` and + `core.sparseCheckoutCone=true`, the index may contain entries + corresponding to directories outside of the sparse-checkout + definition. Versions of Git that do not understand this extension + do not expect directory entries in the index. diff --git a/cache.h b/cache.h index b05341cc687..dcf089b7006 100644 --- a/cache.h +++ b/cache.h @@ -1054,6 +1054,7 @@ struct repository_format { int worktree_config; int is_bare; int hash_algo; + int sparse_index; char *work_tree; struct string_list unknown_extensions; struct string_list v1_only_extensions; diff --git a/repo-settings.c b/repo-settings.c index d63569e4041..9677d50f923 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -85,4 +85,11 @@ void prepare_repo_settings(struct repository *r) * removed. */ r->settings.command_requires_full_index = 1; + + /* + * Initialize this as off. + */ + r->settings.sparse_index = 0; + if (!repo_config_get_bool(r, "extensions.sparseindex", &value) && value) + r->settings.sparse_index = 1; } diff --git a/repository.h b/repository.h index e06a2301569..a45f7520fd9 100644 --- a/repository.h +++ b/repository.h @@ -42,7 +42,8 @@ struct repo_settings { int core_multi_pack_index; - unsigned command_requires_full_index:1; + unsigned command_requires_full_index:1, + sparse_index:1; }; struct repository { diff --git a/setup.c b/setup.c index c04cd25a30d..cd839456461 100644 --- a/setup.c +++ b/setup.c @@ -500,6 +500,9 @@ static enum extension_result handle_extension(const char *var, return error("invalid value for 'extensions.objectformat'"); data->hash_algo = format; return EXTENSION_OK; + } else if (!strcmp(ext, "sparseindex")) { + data->sparse_index = 1; + return EXTENSION_OK; } return EXTENSION_UNKNOWN; } diff --git a/sparse-index.c b/sparse-index.c index 5dd0b835b9d..71544095267 100644 --- a/sparse-index.c +++ b/sparse-index.c @@ -102,19 +102,47 @@ static int convert_to_sparse_rec(struct index_state *istate, return num_converted - start_converted; } +static int enable_sparse_index(struct repository *repo) +{ + const char *config_path = repo_git_path(repo, "config.worktree"); + + if (upgrade_repository_format(1) < 0) { + warning(_("unable to upgrade repository format to enable sparse-index")); + return -1; + } + git_config_set_in_file_gently(config_path, + "extensions.sparseIndex", + "true"); + + prepare_repo_settings(repo); + repo->settings.sparse_index = 1; + return 0; +} + int convert_to_sparse(struct index_state *istate) { if (istate->split_index || istate->sparse_index || !core_apply_sparse_checkout || !core_sparse_checkout_cone) return 0; + if (!istate->repo) + istate->repo = the_repository; + + /* + * The GIT_TEST_SPARSE_INDEX environment variable triggers the + * extensions.sparseIndex config variable to be on. + */ + if (git_env_bool("GIT_TEST_SPARSE_INDEX", 0)) { + int err = enable_sparse_index(istate->repo); + if (err < 0) + return err; + } + /* - * For now, only create a sparse index with the - * GIT_TEST_SPARSE_INDEX environment variable. We will relax - * this once we have a proper way to opt-in (and later still, - * opt-out). + * Only convert to sparse if extensions.sparseIndex is set. */ - if (!git_env_bool("GIT_TEST_SPARSE_INDEX", 0)) + prepare_repo_settings(istate->repo); + if (!istate->repo->settings.sparse_index) return 0; if (!istate->sparse_checkout_patterns) {