diff --git a/Documentation/config/index.txt b/Documentation/config/index.txt index 7cb50b37e9..75f3a2d105 100644 --- a/Documentation/config/index.txt +++ b/Documentation/config/index.txt @@ -14,6 +14,11 @@ index.recordOffsetTable:: Defaults to 'true' if index.threads has been explicitly enabled, 'false' otherwise. +index.sparse:: + When enabled, write the index using sparse-directory entries. This + has no effect unless `core.sparseCheckout` and + `core.sparseCheckoutCone` are both enabled. Defaults to 'false'. + index.threads:: Specifies the number of threads to spawn when loading the index. This is meant to reduce index load time on multiprocessor machines. diff --git a/Documentation/git-sparse-checkout.txt b/Documentation/git-sparse-checkout.txt index a0eeaeb02e..fdcf43f87c 100644 --- a/Documentation/git-sparse-checkout.txt +++ b/Documentation/git-sparse-checkout.txt @@ -45,6 +45,20 @@ To avoid interfering with other worktrees, it first enables the When `--cone` is provided, the `core.sparseCheckoutCone` setting is also set, allowing for better performance with a limited set of patterns (see 'CONE PATTERN SET' below). ++ +Use the `--[no-]sparse-index` option to toggle the use of the sparse +index format. This reduces the size of the index to be more closely +aligned with your sparse-checkout definition. This can have significant +performance advantages for commands such as `git status` or `git add`. +This feature is still experimental. Some commands might be slower with +a sparse index until they are properly integrated with the feature. ++ +**WARNING:** Using a sparse index requires modifying the index in a way +that is not completely understood by external tools. If you have trouble +with this compatibility, then run `git sparse-checkout init --no-sparse-index` +to rewrite your index to not be sparse. Older versions of Git will not +understand the sparse directory entries index extension and may fail to +interact with your repository until it is disabled. 'set':: Write a set of patterns to the sparse-checkout file, as given as diff --git a/Documentation/technical/index-format.txt b/Documentation/technical/index-format.txt index d363a71c37..65da0daaa5 100644 --- a/Documentation/technical/index-format.txt +++ b/Documentation/technical/index-format.txt @@ -44,6 +44,13 @@ Git index format localization, no special casing of directory separator '/'). Entries with the same name are sorted by their stage field. + An index entry typically represents a file. However, if sparse-checkout + is enabled in cone mode (`core.sparseCheckoutCone` is enabled) and the + `extensions.sparseIndex` extension is enabled, then the index may + contain entries for directories outside of the sparse-checkout definition. + These entries have mode `040000`, include the `SKIP_WORKTREE` bit, and + the path ends in a directory separator. + 32-bit ctime seconds, the last time a file's metadata changed this is stat(2) data @@ -385,3 +392,15 @@ The remaining data of each directory block is grouped by type: in this block of entries. - 32-bit count of cache entries in this block + +== Sparse Directory Entries + + When using sparse-checkout in cone mode, some entire directories within + the index can be summarized by pointing to a tree object instead of the + entire expanded list of paths within that tree. An index containing such + entries is a "sparse index". Index format versions 4 and less were not + implemented with such entries in mind. Thus, for these versions, an + index containing sparse directory entries will include this extension + with signature { 's', 'd', 'i', 'r' }. Like the split-index extension, + tools should avoid interacting with a sparse index unless they understand + this extension. diff --git a/Documentation/technical/sparse-index.txt b/Documentation/technical/sparse-index.txt new file mode 100644 index 0000000000..3b24c1a219 --- /dev/null +++ b/Documentation/technical/sparse-index.txt @@ -0,0 +1,208 @@ +Git Sparse-Index Design Document +================================ + +The sparse-checkout feature allows users to focus a working directory on +a subset of the files at HEAD. The cone mode patterns, enabled by +`core.sparseCheckoutCone`, allow for very fast pattern matching to +discover which files at HEAD belong in the sparse-checkout cone. + +Three important scale dimensions for a Git working directory are: + +* `HEAD`: How many files are present at `HEAD`? + +* Populated: How many files are within the sparse-checkout cone. + +* Modified: How many files has the user modified in the working directory? + +We will use big-O notation -- O(X) -- to denote how expensive certain +operations are in terms of these dimensions. + +These dimensions are ordered by their magnitude: users (typically) modify +fewer files than are populated, and we can only populate files at `HEAD`. + +Problems occur if there is an extreme imbalance in these dimensions. For +example, if `HEAD` contains millions of paths but the populated set has +only tens of thousands, then commands like `git status` and `git add` can +be dominated by operations that require O(`HEAD`) operations instead of +O(Populated). Primarily, the cost is in parsing and rewriting the index, +which is filled primarily with files at `HEAD` that are marked with the +`SKIP_WORKTREE` bit. + +The sparse-index intends to take these commands that read and modify the +index from O(`HEAD`) to O(Populated). To do this, we need to modify the +index format in a significant way: add "sparse directory" entries. + +With cone mode patterns, it is possible to detect when an entire +directory will have its contents outside of the sparse-checkout definition. +Instead of listing all of the files it contains as individual entries, a +sparse-index contains an entry with the directory name, referencing the +object ID of the tree at `HEAD` and marked with the `SKIP_WORKTREE` bit. +If we need to discover the details for paths within that directory, we +can parse trees to find that list. + +At time of writing, sparse-directory entries violate expectations about the +index format and its in-memory data structure. There are many consumers in +the codebase that expect to iterate through all of the index entries and +see only files. In fact, these loops expect to see a reference to every +staged file. One way to handle this is to parse trees to replace a +sparse-directory entry with all of the files within that tree as the index +is loaded. However, parsing trees is slower than parsing the index format, +so that is a slower operation than if we left the index alone. The plan is +to make all of these integrations "sparse aware" so this expansion through +tree parsing is unnecessary and they use fewer resources than when using a +full index. + +The implementation plan below follows four phases to slowly integrate with +the sparse-index. The intention is to incrementally update Git commands to +interact safely with the sparse-index without significant slowdowns. This +may not always be possible, but the hope is that the primary commands that +users need in their daily work are dramatically improved. + +Phase I: Format and initial speedups +------------------------------------ + +During this phase, Git learns to enable the sparse-index and safely parse +one. Protections are put in place so that every consumer of the in-memory +data structure can operate with its current assumption of every file at +`HEAD`. + +At first, every index parse will call a helper method, +`ensure_full_index()`, which scans the index for sparse-directory entries +(pointing to trees) and replaces them with the full list of paths (with +blob contents) by parsing tree objects. This will be slower in all cases. +The only noticeable change in behavior will be that the serialized index +file contains sparse-directory entries. + +To start, we use a new required index extension, `sdir`, to allow +inserting sparse-directory entries into indexes with file format +versions 2, 3, and 4. This prevents Git versions that do not understand +the sparse-index from operating on one, while allowing tools that do not +understand the sparse-index to operate on repositories as long as they do +not interact with the index. A new format, index v5, will be introduced +that includes sparse-directory entries by default. It might also +introduce other features that have been considered for improving the +index, as well. + +Next, consumers of the index will be guarded against operating on a +sparse-index by inserting calls to `ensure_full_index()` or +`expand_index_to_path()`. If a specific path is requested, then those will +be protected from within the `index_file_exists()` and `index_name_pos()` +API calls: they will call `ensure_full_index()` if necessary. The +intention here is to preserve existing behavior when interacting with a +sparse-checkout. We don't want a change to happen by accident, without +tests. Many of these locations may not need any change before removing the +guards, but we should not do so without tests to ensure the expected +behavior happens. + +It may be desirable to _change_ the behavior of some commands in the +presence of a sparse index or more generally in any sparse-checkout +scenario. In such cases, these should be carefully communicated and +tested. No such behavior changes are intended during this phase. + +During a scan of the codebase, not every iteration of the cache entries +needs an `ensure_full_index()` check. The basic reasons include: + +1. The loop is scanning for entries with non-zero stage. These entries + are not collapsed into a sparse-directory entry. + +2. The loop is scanning for submodules. These entries are not collapsed + into a sparse-directory entry. + +3. The loop is part of the index API, especially around reading or + writing the format. + +4. The loop is checking for correct order of cache entries and that is + correct if and only if the sparse-directory entries are in the correct + location. + +5. The loop ignores entries with the `SKIP_WORKTREE` bit set, or is + otherwise already aware of sparse directory entries. + +6. The sparse-index is disabled at this point when using the split-index + feature, so no effort is made to protect the split-index API. + +Even after inserting these guards, we will keep expanding sparse-indexes +for most Git commands using the `command_requires_full_index` repository +setting. This setting will be on by default and disabled one builtin at a +time until we have sufficient confidence that all of the index operations +are properly guarded. + +To complete this phase, the commands `git status` and `git add` will be +integrated with the sparse-index so that they operate with O(Populated) +performance. They will be carefully tested for operations within and +outside the sparse-checkout definition. + +Phase II: Careful integrations +------------------------------ + +This phase focuses on ensuring that all index extensions and APIs work +well with a sparse-index. This requires significant increases to our test +coverage, especially for operations that interact with the working +directory outside of the sparse-checkout definition. Some of these +behaviors may not be the desirable ones, such as some tests already +marked for failure in `t1092-sparse-checkout-compatibility.sh`. + +The index extensions that may require special integrations are: + +* FS Monitor +* Untracked cache + +While integrating with these features, we should look for patterns that +might lead to better APIs for interacting with the index. Coalescing +common usage patterns into an API call can reduce the number of places +where sparse-directories need to be handled carefully. + +Phase III: Important command speedups +------------------------------------- + +At this point, the patterns for testing and implementing sparse-directory +logic should be relatively stable. This phase focuses on updating some of +the most common builtins that use the index to operate as O(Populated). +Here is a potential list of commands that could be valuable to integrate +at this point: + +* `git commit` +* `git checkout` +* `git merge` +* `git rebase` + +Hopefully, commands such as `git merge` and `git rebase` can benefit +instead from merge algorithms that do not use the index as a data +structure, such as the merge-ORT strategy. As these topics mature, we +may enable the ORT strategy by default for repositories using the +sparse-index feature. + +Along with `git status` and `git add`, these commands cover the majority +of users' interactions with the working directory. In addition, we can +integrate with these commands: + +* `git grep` +* `git rm` + +These have been proposed as some whose behavior could change when in a +repo with a sparse-checkout definition. It would be good to include this +behavior automatically when using a sparse-index. Some clarity is needed +to make the behavior switch clear to the user. + +This phase is the first where parallel work might be possible without too +much conflicts between topics. + +Phase IV: The long tail +----------------------- + +This last phase is less a "phase" and more "the new normal" after all of +the previous work. + +To start, the `command_requires_full_index` option could be removed in +favor of expanding only when hitting an API guard. + +There are many Git commands that could use special attention to operate as +O(Populated), while some might be so rare that it is acceptable to leave +them with additional overhead when a sparse-index is present. + +Here are some commands that might be useful to update: + +* `git sparse-checkout set` +* `git am` +* `git clean` +* `git stash` diff --git a/Makefile b/Makefile index 0447d12b63..bebc734046 100644 --- a/Makefile +++ b/Makefile @@ -995,6 +995,7 @@ LIB_OBJS += setup.o LIB_OBJS += shallow.o LIB_OBJS += sideband.o LIB_OBJS += sigchain.o +LIB_OBJS += sparse-index.o LIB_OBJS += split-index.o LIB_OBJS += stable-qsort.o LIB_OBJS += strbuf.o diff --git a/attr.c b/attr.c index ac8ec7ce51..9e897e43f5 100644 --- a/attr.c +++ b/attr.c @@ -733,7 +733,7 @@ static struct attr_stack *read_attr_from_file(const char *path, unsigned flags) return res; } -static struct attr_stack *read_attr_from_index(const struct index_state *istate, +static struct attr_stack *read_attr_from_index(struct index_state *istate, const char *path, unsigned flags) { @@ -763,7 +763,7 @@ static struct attr_stack *read_attr_from_index(const struct index_state *istate, return res; } -static struct attr_stack *read_attr(const struct index_state *istate, +static struct attr_stack *read_attr(struct index_state *istate, const char *path, unsigned flags) { struct attr_stack *res = NULL; @@ -855,7 +855,7 @@ static void push_stack(struct attr_stack **attr_stack_p, } } -static void bootstrap_attr_stack(const struct index_state *istate, +static void bootstrap_attr_stack(struct index_state *istate, struct attr_stack **stack) { struct attr_stack *e; @@ -894,7 +894,7 @@ static void bootstrap_attr_stack(const struct index_state *istate, push_stack(stack, e, NULL, 0); } -static void prepare_attr_stack(const struct index_state *istate, +static void prepare_attr_stack(struct index_state *istate, const char *path, int dirlen, struct attr_stack **stack) { @@ -1094,7 +1094,7 @@ static void determine_macros(struct all_attrs_item *all_attrs, * If check->check_nr is non-zero, only attributes in check[] are collected. * Otherwise all attributes are collected. */ -static void collect_some_attrs(const struct index_state *istate, +static void collect_some_attrs(struct index_state *istate, const char *path, struct attr_check *check) { @@ -1123,7 +1123,7 @@ static void collect_some_attrs(const struct index_state *istate, fill(path, pathlen, basename_offset, check->stack, check->all_attrs, rem); } -void git_check_attr(const struct index_state *istate, +void git_check_attr(struct index_state *istate, const char *path, struct attr_check *check) { @@ -1140,7 +1140,7 @@ void git_check_attr(const struct index_state *istate, } } -void git_all_attrs(const struct index_state *istate, +void git_all_attrs(struct index_state *istate, const char *path, struct attr_check *check) { int i; diff --git a/attr.h b/attr.h index 404548f028..3732505eda 100644 --- a/attr.h +++ b/attr.h @@ -190,14 +190,14 @@ void attr_check_free(struct attr_check *check); */ const char *git_attr_name(const struct git_attr *); -void git_check_attr(const struct index_state *istate, +void git_check_attr(struct index_state *istate, const char *path, struct attr_check *check); /* * Retrieve all attributes that apply to the specified path. * check holds the attributes and their values. */ -void git_all_attrs(const struct index_state *istate, +void git_all_attrs(struct index_state *istate, const char *path, struct attr_check *check); enum git_attr_direction { diff --git a/builtin/add.c b/builtin/add.c index ea762a41e3..afccf2fd55 100644 --- a/builtin/add.c +++ b/builtin/add.c @@ -141,6 +141,8 @@ static int renormalize_tracked_files(const struct pathspec *pathspec, int flags) { int i, retval = 0; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) { struct cache_entry *ce = active_cache[i]; diff --git a/builtin/checkout-index.c b/builtin/checkout-index.c index c0bf4ac1b2..c9a3c71914 100644 --- a/builtin/checkout-index.c +++ b/builtin/checkout-index.c @@ -120,6 +120,8 @@ static void checkout_all(const char *prefix, int prefix_length) int i, errs = 0; struct cache_entry *last_ce = NULL; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr ; i++) { struct cache_entry *ce = active_cache[i]; if (ce_stage(ce) != checkout_stage diff --git a/builtin/checkout.c b/builtin/checkout.c index 4c696ef480..5bd9128d1a 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -369,6 +369,9 @@ static int checkout_worktree(const struct checkout_opts *opts, NULL); enable_delayed_checkout(&state); + + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (pos = 0; pos < active_nr; pos++) { struct cache_entry *ce = active_cache[pos]; if (ce->ce_flags & CE_MATCHED) { @@ -513,6 +516,8 @@ static int checkout_paths(const struct checkout_opts *opts, * Make sure all pathspecs participated in locating the paths * to be checked out. */ + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (pos = 0; pos < active_nr; pos++) if (opts->overlay_mode) mark_ce_for_checkout_overlay(active_cache[pos], diff --git a/builtin/commit.c b/builtin/commit.c index 55d50a8891..190d215d43 100644 --- a/builtin/commit.c +++ b/builtin/commit.c @@ -261,6 +261,8 @@ static int list_paths(struct string_list *list, const char *with_tree, free(max_prefix); } + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) { const struct cache_entry *ce = active_cache[i]; struct string_list_item *item; @@ -976,6 +978,8 @@ static int prepare_to_commit(const char *index_file, const char *prefix, if (get_oid(parent, &oid)) { int i, ita_nr = 0; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) if (ce_intent_to_add(active_cache[i])) ita_nr++; diff --git a/builtin/difftool.c b/builtin/difftool.c index ef25729d49..0202a43052 100644 --- a/builtin/difftool.c +++ b/builtin/difftool.c @@ -585,6 +585,9 @@ static int run_dir_diff(const char *extcmd, int symlinks, const char *prefix, setenv("GIT_DIFFTOOL_DIRDIFF", "true", 1); rc = run_command_v_opt(helper_argv, flags); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&wtindex); + /* * If the diff includes working copy files and those * files were modified during the diff, then the changes diff --git a/builtin/fsck.c b/builtin/fsck.c index e6a80e5404..87a99b0108 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -881,6 +881,8 @@ int cmd_fsck(int argc, const char **argv, const char *prefix) verify_index_checksum = 1; verify_ce_order = 1; read_cache(); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) { unsigned int mode; struct blob *blob; diff --git a/builtin/grep.c b/builtin/grep.c index 5de725f904..b71b4a2de6 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -504,6 +504,8 @@ static int grep_cache(struct grep_opt *opt, if (repo_read_index(repo) < 0) die(_("index file corrupt")); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(repo->index); for (nr = 0; nr < repo->index->cache_nr; nr++) { const struct cache_entry *ce = repo->index->cache[nr]; diff --git a/builtin/ls-files.c b/builtin/ls-files.c index 60a2913a01..a0b4e54d11 100644 --- a/builtin/ls-files.c +++ b/builtin/ls-files.c @@ -57,7 +57,7 @@ static const char *tag_modified = ""; static const char *tag_skip_worktree = ""; static const char *tag_resolve_undo = ""; -static void write_eolinfo(const struct index_state *istate, +static void write_eolinfo(struct index_state *istate, const struct cache_entry *ce, const char *path) { if (show_eol) { @@ -122,7 +122,7 @@ static void print_debug(const struct cache_entry *ce) } } -static void show_dir_entry(const struct index_state *istate, +static void show_dir_entry(struct index_state *istate, const char *tag, struct dir_entry *ent) { int len = max_prefix_len; @@ -139,7 +139,7 @@ static void show_dir_entry(const struct index_state *istate, write_name(ent->name); } -static void show_other_files(const struct index_state *istate, +static void show_other_files(struct index_state *istate, const struct dir_struct *dir) { int i; @@ -152,7 +152,7 @@ static void show_other_files(const struct index_state *istate, } } -static void show_killed_files(const struct index_state *istate, +static void show_killed_files(struct index_state *istate, const struct dir_struct *dir) { int i; @@ -254,7 +254,7 @@ static void show_ce(struct repository *repo, struct dir_struct *dir, } } -static void show_ru_info(const struct index_state *istate) +static void show_ru_info(struct index_state *istate) { struct string_list_item *item; @@ -317,6 +317,8 @@ static void show_files(struct repository *repo, struct dir_struct *dir) if (!(show_cached || show_stage || show_deleted || show_modified)) return; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(repo->index); for (i = 0; i < repo->index->cache_nr; i++) { const struct cache_entry *ce = repo->index->cache[i]; struct stat st; @@ -494,6 +496,8 @@ void overlay_tree_on_index(struct index_state *istate, die("bad tree-ish %s", tree_name); /* Hoist the unmerged entries up to stage #3 to make room */ + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { struct cache_entry *ce = istate->cache[i]; if (!ce_stage(ce)) diff --git a/builtin/merge-index.c b/builtin/merge-index.c index 38ea6ad6ca..c0383fe9df 100644 --- a/builtin/merge-index.c +++ b/builtin/merge-index.c @@ -58,6 +58,8 @@ static void merge_one_path(const char *path) static void merge_all(void) { int i; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) { const struct cache_entry *ce = active_cache[i]; if (!ce_stage(ce)) @@ -80,6 +82,9 @@ int cmd_merge_index(int argc, const char **argv, const char *prefix) read_cache(); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); + i = 1; if (!strcmp(argv[i], "-o")) { one_shot = 1; diff --git a/builtin/rm.c b/builtin/rm.c index 4858631e0f..5559a0b453 100644 --- a/builtin/rm.c +++ b/builtin/rm.c @@ -293,6 +293,8 @@ int cmd_rm(int argc, const char **argv, const char *prefix) seen = xcalloc(pathspec.nr, 1); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) { const struct cache_entry *ce = active_cache[i]; if (!ce_path_match(&the_index, ce, &pathspec, seen)) diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c index d7da50ada5..a4bdd7c494 100644 --- a/builtin/sparse-checkout.c +++ b/builtin/sparse-checkout.c @@ -14,6 +14,7 @@ #include "unpack-trees.h" #include "wt-status.h" #include "quote.h" +#include "sparse-index.h" static const char *empty_base = ""; @@ -110,6 +111,8 @@ static int update_working_directory(struct pattern_list *pl) if (is_index_unborn(r->index)) return UPDATE_SPARSITY_SUCCESS; + r->index->sparse_checkout_patterns = pl; + memset(&o, 0, sizeof(o)); o.verbose_update = isatty(2); o.update = 1; @@ -138,6 +141,7 @@ static int update_working_directory(struct pattern_list *pl) else rollback_lock_file(&lock_file); + r->index->sparse_checkout_patterns = NULL; return result; } @@ -276,16 +280,20 @@ static int set_config(enum sparse_checkout_mode mode) "core.sparseCheckoutCone", mode == MODE_CONE_PATTERNS ? "true" : NULL); + if (mode == MODE_NO_PATTERNS) + set_sparse_index_config(the_repository, 0); + return 0; } static char const * const builtin_sparse_checkout_init_usage[] = { - N_("git sparse-checkout init [--cone]"), + N_("git sparse-checkout init [--cone] [--[no-]sparse-index]"), NULL }; static struct sparse_checkout_init_opts { int cone_mode; + int sparse_index; } init_opts; static int sparse_checkout_init(int argc, const char **argv) @@ -300,11 +308,15 @@ static int sparse_checkout_init(int argc, const char **argv) static struct option builtin_sparse_checkout_init_options[] = { OPT_BOOL(0, "cone", &init_opts.cone_mode, N_("initialize the sparse-checkout in cone mode")), + OPT_BOOL(0, "sparse-index", &init_opts.sparse_index, + N_("toggle the use of a sparse index")), OPT_END(), }; repo_read_index(the_repository); + init_opts.sparse_index = -1; + argc = parse_options(argc, argv, NULL, builtin_sparse_checkout_init_options, builtin_sparse_checkout_init_usage, 0); @@ -323,10 +335,20 @@ static int sparse_checkout_init(int argc, const char **argv) sparse_filename = get_sparse_checkout_filename(); res = add_patterns_from_file_to_list(sparse_filename, "", 0, &pl, NULL, 0); + if (init_opts.sparse_index >= 0) { + if (set_sparse_index_config(the_repository, init_opts.sparse_index) < 0) + die(_("failed to modify sparse-index config")); + + /* force an index rewrite */ + repo_read_index(the_repository); + the_repository->index->updated_workdir = 1; + } + + core_apply_sparse_checkout = 1; + /* If we already have a sparse-checkout file, use it. */ if (res >= 0) { free(sparse_filename); - core_apply_sparse_checkout = 1; return update_working_directory(NULL); } @@ -348,6 +370,7 @@ static int sparse_checkout_init(int argc, const char **argv) add_pattern(strbuf_detach(&pattern, NULL), empty_base, 0, &pl, 0); strbuf_addstr(&pattern, "!/*/"); add_pattern(strbuf_detach(&pattern, NULL), empty_base, 0, &pl, 0); + pl.use_cone_patterns = init_opts.cone_mode; return write_patterns_and_update(&pl); } @@ -517,19 +540,18 @@ static int modify_pattern_list(int argc, const char **argv, enum modify_type m) { int result; int changed_config = 0; - struct pattern_list pl; - memset(&pl, 0, sizeof(pl)); + struct pattern_list *pl = xcalloc(1, sizeof(*pl)); switch (m) { case ADD: if (core_sparse_checkout_cone) - add_patterns_cone_mode(argc, argv, &pl); + add_patterns_cone_mode(argc, argv, pl); else - add_patterns_literal(argc, argv, &pl); + add_patterns_literal(argc, argv, pl); break; case REPLACE: - add_patterns_from_input(&pl, argc, argv); + add_patterns_from_input(pl, argc, argv); break; } @@ -539,12 +561,13 @@ static int modify_pattern_list(int argc, const char **argv, enum modify_type m) changed_config = 1; } - result = write_patterns_and_update(&pl); + result = write_patterns_and_update(pl); if (result && changed_config) set_config(MODE_NO_PATTERNS); - clear_pattern_list(&pl); + clear_pattern_list(pl); + free(pl); return result; } @@ -614,6 +637,9 @@ static int sparse_checkout_disable(int argc, const char **argv) strbuf_addstr(&match_all, "/*"); add_pattern(strbuf_detach(&match_all, NULL), empty_base, 0, &pl, 0); + prepare_repo_settings(the_repository); + the_repository->settings.sparse_index = 0; + if (update_working_directory(&pl)) die(_("error while refreshing working directory")); diff --git a/builtin/stash.c b/builtin/stash.c index c56fed3354..d68ed784d2 100644 --- a/builtin/stash.c +++ b/builtin/stash.c @@ -1412,6 +1412,8 @@ static int do_push_stash(const struct pathspec *ps, const char *stash_msg, int q int i; char *ps_matched = xcalloc(ps->nr, 1); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (i = 0; i < active_nr; i++) ce_path_match(&the_index, active_cache[i], ps, ps_matched); diff --git a/builtin/update-index.c b/builtin/update-index.c index 79087bccea..f1f16f2de5 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -745,6 +745,8 @@ static int do_reupdate(int ac, const char **av, */ has_head = 0; redo: + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(&the_index); for (pos = 0; pos < active_nr; pos++) { const struct cache_entry *ce = active_cache[pos]; struct cache_entry *old = NULL; diff --git a/cache-tree.c b/cache-tree.c index add1f07713..45e58666af 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -6,6 +6,7 @@ #include "object-store.h" #include "replace-object.h" #include "promisor-remote.h" +#include "sparse-index.h" #ifndef DEBUG_CACHE_TREE #define DEBUG_CACHE_TREE 0 @@ -255,6 +256,24 @@ static int update_one(struct cache_tree *it, *skip_count = 0; + /* + * If the first entry of this region is a sparse directory + * entry corresponding exactly to 'base', then this cache_tree + * struct is a "leaf" in the data structure, pointing to the + * tree OID specified in the entry. + */ + if (entries > 0) { + const struct cache_entry *ce = cache[0]; + + if (S_ISSPARSEDIR(ce->ce_mode) && + ce->ce_namelen == baselen && + !strncmp(ce->name, base, baselen)) { + it->entry_count = 1; + oidcpy(&it->oid, &ce->oid); + return 1; + } + } + if (0 <= it->entry_count && has_object_file(&it->oid)) return it->entry_count; @@ -442,6 +461,8 @@ int cache_tree_update(struct index_state *istate, int flags) if (i) return i; + ensure_full_index(istate); + if (!istate->cache_tree) istate->cache_tree = cache_tree(); @@ -787,6 +808,19 @@ int cache_tree_matches_traversal(struct cache_tree *root, return 0; } +static void verify_one_sparse(struct repository *r, + struct index_state *istate, + struct cache_tree *it, + struct strbuf *path, + int pos) +{ + struct cache_entry *ce = istate->cache[pos]; + + if (!S_ISSPARSEDIR(ce->ce_mode)) + BUG("directory '%s' is present in index, but not sparse", + path->buf); +} + static void verify_one(struct repository *r, struct index_state *istate, struct cache_tree *it, @@ -809,6 +843,12 @@ static void verify_one(struct repository *r, if (path->len) { pos = index_name_pos(istate, path->buf, path->len); + + if (pos >= 0) { + verify_one_sparse(r, istate, it, path, pos); + return; + } + pos = -pos - 1; } else { pos = 0; diff --git a/cache.h b/cache.h index 148d9ab5f1..b785ffb383 100644 --- a/cache.h +++ b/cache.h @@ -204,6 +204,8 @@ struct cache_entry { #error "CE_EXTENDED_FLAGS out of range" #endif +#define S_ISSPARSEDIR(m) ((m) == S_IFDIR) + /* Forward structure decls */ struct pathspec; struct child_process; @@ -249,6 +251,8 @@ static inline unsigned int create_ce_mode(unsigned int mode) { if (S_ISLNK(mode)) return S_IFLNK; + if (S_ISSPARSEDIR(mode)) + return S_IFDIR; if (S_ISDIR(mode) || S_ISGITLINK(mode)) return S_IFGITLINK; return S_IFREG | ce_permissions(mode); @@ -305,6 +309,7 @@ static inline unsigned int canon_mode(unsigned int mode) struct split_index; struct untracked_cache; struct progress; +struct pattern_list; struct index_state { struct cache_entry **cache; @@ -319,7 +324,14 @@ struct index_state { drop_cache_tree : 1, updated_workdir : 1, updated_skipworktree : 1, - fsmonitor_has_run_once : 1; + fsmonitor_has_run_once : 1, + + /* + * sparse_index == 1 when sparse-directory + * entries exist. Requires sparse-checkout + * in cone mode. + */ + sparse_index : 1; struct hashmap name_hash; struct hashmap dir_hash; struct object_id oid; @@ -329,6 +341,7 @@ struct index_state { struct mem_pool *ce_mem_pool; struct progress *progress; struct repository *repo; + struct pattern_list *sparse_checkout_patterns; }; /* Name hashing */ @@ -337,6 +350,7 @@ void add_name_hash(struct index_state *istate, struct cache_entry *ce); void remove_name_hash(struct index_state *istate, struct cache_entry *ce); void free_name_hash(struct index_state *istate); +void ensure_full_index(struct index_state *istate); /* Cache entry creation and cleanup */ @@ -722,6 +736,8 @@ int read_index_from(struct index_state *, const char *path, const char *gitdir); int is_index_unborn(struct index_state *); +void ensure_full_index(struct index_state *istate); + /* For use with `write_locked_index()`. */ #define COMMIT_LOCK (1 << 0) #define SKIP_IF_UNCHANGED (1 << 1) @@ -785,7 +801,7 @@ struct cache_entry *index_file_exists(struct index_state *istate, const char *na * index_name_pos(&index, "f", 1) -> -3 * index_name_pos(&index, "g", 1) -> -5 */ -int index_name_pos(const struct index_state *, const char *name, int namelen); +int index_name_pos(struct index_state *, const char *name, int namelen); /* * Some functions return the negative complement of an insert position when a @@ -835,8 +851,8 @@ int add_file_to_index(struct index_state *, const char *path, int flags); int chmod_index_entry(struct index_state *, struct cache_entry *ce, char flip); int ce_same_name(const struct cache_entry *a, const struct cache_entry *b); void set_object_name_for_intent_to_add_entry(struct cache_entry *ce); -int index_name_is_other(const struct index_state *, const char *, int); -void *read_blob_data_from_index(const struct index_state *, const char *, unsigned long *); +int index_name_is_other(struct index_state *, const char *, int); +void *read_blob_data_from_index(struct index_state *, const char *, unsigned long *); /* do stat comparison even if CE_VALID is true */ #define CE_MATCH_IGNORE_VALID 01 @@ -1044,6 +1060,7 @@ 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/convert.c b/convert.c index 45ac75f80c..fd9c84b025 100644 --- a/convert.c +++ b/convert.c @@ -127,7 +127,7 @@ static const char *gather_convert_stats_ascii(const char *data, unsigned long si } } -const char *get_cached_convert_stats_ascii(const struct index_state *istate, +const char *get_cached_convert_stats_ascii(struct index_state *istate, const char *path) { const char *ret; @@ -211,7 +211,7 @@ static void check_global_conv_flags_eol(const char *path, } } -static int has_crlf_in_index(const struct index_state *istate, const char *path) +static int has_crlf_in_index(struct index_state *istate, const char *path) { unsigned long sz; void *data; @@ -485,7 +485,7 @@ static int encode_to_worktree(const char *path, const char *src, size_t src_len, return 1; } -static int crlf_to_git(const struct index_state *istate, +static int crlf_to_git(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *buf, enum convert_crlf_action crlf_action, int conv_flags) @@ -1293,7 +1293,7 @@ static int git_path_check_ident(struct attr_check_item *check) static struct attr_check *check; -void convert_attrs(const struct index_state *istate, +void convert_attrs(struct index_state *istate, struct conv_attrs *ca, const char *path) { struct attr_check_item *ccheck = NULL; @@ -1355,7 +1355,7 @@ void reset_parsed_attributes(void) user_convert_tail = NULL; } -int would_convert_to_git_filter_fd(const struct index_state *istate, const char *path) +int would_convert_to_git_filter_fd(struct index_state *istate, const char *path) { struct conv_attrs ca; @@ -1374,7 +1374,7 @@ int would_convert_to_git_filter_fd(const struct index_state *istate, const char return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN, NULL, NULL); } -const char *get_convert_attr_ascii(const struct index_state *istate, const char *path) +const char *get_convert_attr_ascii(struct index_state *istate, const char *path) { struct conv_attrs ca; @@ -1400,7 +1400,7 @@ const char *get_convert_attr_ascii(const struct index_state *istate, const char return ""; } -int convert_to_git(const struct index_state *istate, +int convert_to_git(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst, int conv_flags) { @@ -1434,7 +1434,7 @@ int convert_to_git(const struct index_state *istate, return ret | ident_to_git(src, len, dst, ca.ident); } -void convert_to_git_filter_fd(const struct index_state *istate, +void convert_to_git_filter_fd(struct index_state *istate, const char *path, int fd, struct strbuf *dst, int conv_flags) { @@ -1511,7 +1511,7 @@ int convert_to_working_tree_ca(const struct conv_attrs *ca, meta, NULL); } -int renormalize_buffer(const struct index_state *istate, const char *path, +int renormalize_buffer(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst) { struct conv_attrs ca; @@ -1972,7 +1972,7 @@ struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca, return filter; } -struct stream_filter *get_stream_filter(const struct index_state *istate, +struct stream_filter *get_stream_filter(struct index_state *istate, const char *path, const struct object_id *oid) { diff --git a/convert.h b/convert.h index 43e567a59b..5ee1c32205 100644 --- a/convert.h +++ b/convert.h @@ -84,19 +84,19 @@ struct conv_attrs { const char *working_tree_encoding; /* Supported encoding or default encoding if NULL */ }; -void convert_attrs(const struct index_state *istate, +void convert_attrs(struct index_state *istate, struct conv_attrs *ca, const char *path); extern enum eol core_eol; extern char *check_roundtrip_encoding; -const char *get_cached_convert_stats_ascii(const struct index_state *istate, +const char *get_cached_convert_stats_ascii(struct index_state *istate, const char *path); const char *get_wt_convert_stats_ascii(const char *path); -const char *get_convert_attr_ascii(const struct index_state *istate, +const char *get_convert_attr_ascii(struct index_state *istate, const char *path); /* returns 1 if *dst was used */ -int convert_to_git(const struct index_state *istate, +int convert_to_git(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst, int conv_flags); int convert_to_working_tree_ca(const struct conv_attrs *ca, @@ -108,7 +108,7 @@ int async_convert_to_working_tree_ca(const struct conv_attrs *ca, size_t len, struct strbuf *dst, const struct checkout_metadata *meta, void *dco); -static inline int convert_to_working_tree(const struct index_state *istate, +static inline int convert_to_working_tree(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst, const struct checkout_metadata *meta) @@ -117,7 +117,7 @@ static inline int convert_to_working_tree(const struct index_state *istate, convert_attrs(istate, &ca, path); return convert_to_working_tree_ca(&ca, path, src, len, dst, meta); } -static inline int async_convert_to_working_tree(const struct index_state *istate, +static inline int async_convert_to_working_tree(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst, const struct checkout_metadata *meta, @@ -129,20 +129,20 @@ static inline int async_convert_to_working_tree(const struct index_state *istate } int async_query_available_blobs(const char *cmd, struct string_list *available_paths); -int renormalize_buffer(const struct index_state *istate, +int renormalize_buffer(struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *dst); -static inline int would_convert_to_git(const struct index_state *istate, +static inline int would_convert_to_git(struct index_state *istate, const char *path) { return convert_to_git(istate, path, NULL, 0, NULL, 0); } /* Precondition: would_convert_to_git_filter_fd(path) == true */ -void convert_to_git_filter_fd(const struct index_state *istate, +void convert_to_git_filter_fd(struct index_state *istate, const char *path, int fd, struct strbuf *dst, int conv_flags); -int would_convert_to_git_filter_fd(const struct index_state *istate, +int would_convert_to_git_filter_fd(struct index_state *istate, const char *path); /* @@ -176,7 +176,7 @@ void reset_parsed_attributes(void); struct stream_filter; /* opaque */ -struct stream_filter *get_stream_filter(const struct index_state *istate, +struct stream_filter *get_stream_filter(struct index_state *istate, const char *path, const struct object_id *); struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca, diff --git a/dir.c b/dir.c index 3474e67e8f..d81b5df803 100644 --- a/dir.c +++ b/dir.c @@ -306,7 +306,7 @@ static int do_read_blob(const struct object_id *oid, struct oid_stat *oid_stat, * [1] Only if DO_MATCH_DIRECTORY is passed; otherwise, this is NOT a match. * [2] Only if DO_MATCH_LEADING_PATHSPEC is passed; otherwise, not a match. */ -static int match_pathspec_item(const struct index_state *istate, +static int match_pathspec_item(struct index_state *istate, const struct pathspec_item *item, int prefix, const char *name, int namelen, unsigned flags) { @@ -429,7 +429,7 @@ static int match_pathspec_item(const struct index_state *istate, * pathspec did not match any names, which could indicate that the * user mistyped the nth pathspec. */ -static int do_match_pathspec(const struct index_state *istate, +static int do_match_pathspec(struct index_state *istate, const struct pathspec *ps, const char *name, int namelen, int prefix, char *seen, @@ -500,7 +500,7 @@ static int do_match_pathspec(const struct index_state *istate, return retval; } -static int match_pathspec_with_flags(const struct index_state *istate, +static int match_pathspec_with_flags(struct index_state *istate, const struct pathspec *ps, const char *name, int namelen, int prefix, char *seen, unsigned flags) @@ -516,7 +516,7 @@ static int match_pathspec_with_flags(const struct index_state *istate, return negative ? 0 : positive; } -int match_pathspec(const struct index_state *istate, +int match_pathspec(struct index_state *istate, const struct pathspec *ps, const char *name, int namelen, int prefix, char *seen, int is_dir) @@ -529,7 +529,7 @@ int match_pathspec(const struct index_state *istate, /** * Check if a submodule is a superset of the pathspec */ -int submodule_path_match(const struct index_state *istate, +int submodule_path_match(struct index_state *istate, const struct pathspec *ps, const char *submodule_name, char *seen) @@ -892,7 +892,7 @@ void add_pattern(const char *string, const char *base, add_pattern_to_hashsets(pl, pattern); } -static int read_skip_worktree_file_from_index(const struct index_state *istate, +static int read_skip_worktree_file_from_index(struct index_state *istate, const char *path, size_t *size_out, char **data_out, struct oid_stat *oid_stat) @@ -3542,6 +3542,8 @@ static void connect_wt_gitdir_in_nested(const char *sub_worktree, if (repo_read_index(&subrepo) < 0) die(_("index file corrupt in repo %s"), subrepo.gitdir); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(subrepo.index); for (i = 0; i < subrepo.index->cache_nr; i++) { const struct cache_entry *ce = subrepo.index->cache[i]; diff --git a/dir.h b/dir.h index 04d886cfce..35963f9e2c 100644 --- a/dir.h +++ b/dir.h @@ -354,7 +354,7 @@ int count_slashes(const char *s); int simple_length(const char *match); int no_wildcard(const char *string); char *common_prefix(const struct pathspec *pathspec); -int match_pathspec(const struct index_state *istate, +int match_pathspec(struct index_state *istate, const struct pathspec *pathspec, const char *name, int namelen, int prefix, char *seen, int is_dir); @@ -493,12 +493,12 @@ int git_fnmatch(const struct pathspec_item *item, const char *pattern, const char *string, int prefix); -int submodule_path_match(const struct index_state *istate, +int submodule_path_match(struct index_state *istate, const struct pathspec *ps, const char *submodule_name, char *seen); -static inline int ce_path_match(const struct index_state *istate, +static inline int ce_path_match(struct index_state *istate, const struct cache_entry *ce, const struct pathspec *pathspec, char *seen) @@ -507,7 +507,7 @@ static inline int ce_path_match(const struct index_state *istate, S_ISDIR(ce->ce_mode) || S_ISGITLINK(ce->ce_mode)); } -static inline int dir_path_match(const struct index_state *istate, +static inline int dir_path_match(struct index_state *istate, const struct dir_entry *ent, const struct pathspec *pathspec, int prefix, char *seen) diff --git a/entry.c b/entry.c index 2dc94ba5cc..9fdc843135 100644 --- a/entry.c +++ b/entry.c @@ -423,6 +423,8 @@ static void mark_colliding_entries(const struct checkout *state, ce->ce_flags |= CE_MATCHED; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(state->istate); for (i = 0; i < state->istate->cache_nr; i++) { struct cache_entry *dup = state->istate->cache[i]; diff --git a/merge-ort.c b/merge-ort.c index b1795d838e..6c2792b10e 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -2564,7 +2564,7 @@ static int blob_unchanged(struct merge_options *opt, struct strbuf basebuf = STRBUF_INIT; struct strbuf sidebuf = STRBUF_INIT; int ret = 0; /* assume changed for safety */ - const struct index_state *idx = &opt->priv->attr_index; + struct index_state *idx = &opt->priv->attr_index; if (!idx->initialized) initialize_attr_index(opt); diff --git a/merge-recursive.c b/merge-recursive.c index 7618303f7b..27b222ae49 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -522,6 +522,8 @@ static struct string_list *get_unmerged(struct index_state *istate) unmerged->strdup_strings = 1; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { struct string_list_item *item; struct stage_data *e; @@ -3014,7 +3016,7 @@ static int blob_unchanged(struct merge_options *opt, struct strbuf obuf = STRBUF_INIT; struct strbuf abuf = STRBUF_INIT; int ret = 0; /* assume changed for safety */ - const struct index_state *idx = opt->repo->index; + struct index_state *idx = opt->repo->index; if (a->mode != o->mode) return 0; diff --git a/name-hash.c b/name-hash.c index ce28f3f070..7487d33124 100644 --- a/name-hash.c +++ b/name-hash.c @@ -8,6 +8,7 @@ #include "cache.h" #include "thread-utils.h" #include "trace2.h" +#include "sparse-index.h" struct dir_entry { struct hashmap_entry ent; @@ -109,8 +110,11 @@ static void hash_index_entry(struct index_state *istate, struct cache_entry *ce) if (ce->ce_flags & CE_HASHED) return; ce->ce_flags |= CE_HASHED; - hashmap_entry_init(&ce->ent, memihash(ce->name, ce_namelen(ce))); - hashmap_add(&istate->name_hash, &ce->ent); + + if (!S_ISSPARSEDIR(ce->ce_mode)) { + hashmap_entry_init(&ce->ent, memihash(ce->name, ce_namelen(ce))); + hashmap_add(&istate->name_hash, &ce->ent); + } if (ignore_case) add_dir_entry(istate, ce); @@ -680,6 +684,7 @@ int index_dir_exists(struct index_state *istate, const char *name, int namelen) struct dir_entry *dir; lazy_init_name_hash(istate); + expand_to_path(istate, name, namelen, 0); dir = find_dir_entry(istate, name, namelen); return dir && dir->nr; } @@ -690,6 +695,7 @@ void adjust_dirname_case(struct index_state *istate, char *name) const char *ptr = startPtr; lazy_init_name_hash(istate); + expand_to_path(istate, name, strlen(name), 0); while (*ptr) { while (*ptr && *ptr != '/') ptr++; @@ -713,6 +719,7 @@ struct cache_entry *index_file_exists(struct index_state *istate, const char *na unsigned int hash = memihash(name, namelen); lazy_init_name_hash(istate); + expand_to_path(istate, name, namelen, icase); ce = hashmap_get_entry_from_hash(&istate->name_hash, hash, NULL, struct cache_entry, ent); diff --git a/pathspec.c b/pathspec.c index 18b3be362a..14c7e9fbe3 100644 --- a/pathspec.c +++ b/pathspec.c @@ -20,7 +20,7 @@ * to use find_pathspecs_matching_against_index() instead. */ void add_pathspec_matches_against_index(const struct pathspec *pathspec, - const struct index_state *istate, + struct index_state *istate, char *seen) { int num_unmatched = 0, i; @@ -36,6 +36,8 @@ void add_pathspec_matches_against_index(const struct pathspec *pathspec, num_unmatched++; if (!num_unmatched) return; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { const struct cache_entry *ce = istate->cache[i]; ce_path_match(istate, ce, pathspec, seen); @@ -51,7 +53,7 @@ void add_pathspec_matches_against_index(const struct pathspec *pathspec, * given pathspecs achieves against all items in the index. */ char *find_pathspecs_matching_against_index(const struct pathspec *pathspec, - const struct index_state *istate) + struct index_state *istate) { char *seen = xcalloc(pathspec->nr, 1); add_pathspec_matches_against_index(pathspec, istate, seen); @@ -702,7 +704,7 @@ void clear_pathspec(struct pathspec *pathspec) pathspec->nr = 0; } -int match_pathspec_attrs(const struct index_state *istate, +int match_pathspec_attrs(struct index_state *istate, const char *name, int namelen, const struct pathspec_item *item) { diff --git a/pathspec.h b/pathspec.h index 454ce364fa..2ccc8080b6 100644 --- a/pathspec.h +++ b/pathspec.h @@ -150,11 +150,11 @@ static inline int ps_strcmp(const struct pathspec_item *item, } void add_pathspec_matches_against_index(const struct pathspec *pathspec, - const struct index_state *istate, + struct index_state *istate, char *seen); char *find_pathspecs_matching_against_index(const struct pathspec *pathspec, - const struct index_state *istate); -int match_pathspec_attrs(const struct index_state *istate, + struct index_state *istate); +int match_pathspec_attrs(struct index_state *istate, const char *name, int namelen, const struct pathspec_item *item); diff --git a/read-cache.c b/read-cache.c index 5a907af2fb..72a1d339c9 100644 --- a/read-cache.c +++ b/read-cache.c @@ -25,6 +25,7 @@ #include "fsmonitor.h" #include "thread-utils.h" #include "progress.h" +#include "sparse-index.h" /* Mask for the name length in ce_flags in the on-disk index */ @@ -47,6 +48,7 @@ #define CACHE_EXT_FSMONITOR 0x46534D4E /* "FSMN" */ #define CACHE_EXT_ENDOFINDEXENTRIES 0x454F4945 /* "EOIE" */ #define CACHE_EXT_INDEXENTRYOFFSETTABLE 0x49454F54 /* "IEOT" */ +#define CACHE_EXT_SPARSE_DIRECTORIES 0x73646972 /* "sdir" */ /* changes that can be kept in $GIT_DIR/index (basically all extensions) */ #define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \ @@ -101,6 +103,9 @@ static const char *alternate_index_output; static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce) { + if (S_ISSPARSEDIR(ce->ce_mode)) + istate->sparse_index = 1; + istate->cache[nr] = ce; add_name_hash(istate, ce); } @@ -544,7 +549,7 @@ int cache_name_stage_compare(const char *name1, int len1, int stage1, const char return 0; } -static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage) +static int index_name_stage_pos(struct index_state *istate, const char *name, int namelen, int stage) { int first, last; @@ -562,10 +567,31 @@ static int index_name_stage_pos(const struct index_state *istate, const char *na } first = next+1; } + + if (istate->sparse_index && + first > 0) { + /* Note: first <= istate->cache_nr */ + struct cache_entry *ce = istate->cache[first - 1]; + + /* + * If we are in a sparse-index _and_ the entry before the + * insertion position is a sparse-directory entry that is + * an ancestor of 'name', then we need to expand the index + * and search again. This will only trigger once, because + * thereafter the index is fully expanded. + */ + if (S_ISSPARSEDIR(ce->ce_mode) && + ce_namelen(ce) < namelen && + !strncmp(name, ce->name, ce_namelen(ce))) { + ensure_full_index(istate); + return index_name_stage_pos(istate, name, namelen, stage); + } + } + return -first-1; } -int index_name_pos(const struct index_state *istate, const char *name, int namelen) +int index_name_pos(struct index_state *istate, const char *name, int namelen) { return index_name_stage_pos(istate, name, namelen, 0); } @@ -999,8 +1025,14 @@ int verify_path(const char *path, unsigned mode) c = *path++; if ((c == '.' && !verify_dotfile(path, mode)) || - is_dir_sep(c) || c == '\0') + is_dir_sep(c)) return 0; + /* + * allow terminating directory separators for + * sparse directory entries. + */ + if (c == '\0') + return S_ISDIR(mode); } else if (c == '\\' && protect_ntfs) { if (is_ntfs_dotgit(path)) return 0; @@ -1545,6 +1577,8 @@ int refresh_index(struct index_state *istate, unsigned int flags, */ preload_index(istate, pathspec, 0); trace2_region_enter("index", "refresh", NULL); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { struct cache_entry *ce, *new_entry; int cache_errno = 0; @@ -1760,6 +1794,10 @@ static int read_index_extension(struct index_state *istate, case CACHE_EXT_INDEXENTRYOFFSETTABLE: /* already handled in do_read_index() */ break; + case CACHE_EXT_SPARSE_DIRECTORIES: + /* no content, only an indicator */ + istate->sparse_index = 1; + break; default: if (*ext < 'A' || 'Z' < *ext) return error(_("index uses %.4s extension, which we do not understand"), @@ -2273,6 +2311,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist) trace2_data_intmax("index", the_repository, "read/cache_nr", istate->cache_nr); + if (!istate->repo) + istate->repo = the_repository; + prepare_repo_settings(istate->repo); + if (istate->repo->settings.command_requires_full_index) + ensure_full_index(istate); + return istate->cache_nr; unmap: @@ -2457,6 +2501,8 @@ int repo_index_has_changes(struct repository *repo, diff_flush(&opt); return opt.flags.has_changes != 0; } else { + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; sb && i < istate->cache_nr; i++) { if (i) strbuf_addch(sb, ' '); @@ -3012,6 +3058,10 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, if (err) return -1; } + if (istate->sparse_index) { + if (write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_SPARSE_DIRECTORIES, 0) < 0) + return -1; + } /* * CACHE_EXT_ENDOFINDEXENTRIES must be written as the last entry before the SHA1 @@ -3071,6 +3121,14 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l unsigned flags) { int ret; + int was_full = !istate->sparse_index; + + ret = convert_to_sparse(istate); + + if (ret) { + warning(_("failed to convert to a sparse-index")); + return ret; + } /* * TODO trace2: replace "the_repository" with the actual repo instance @@ -3082,6 +3140,9 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l trace2_region_leave_printf("index", "do_write_index", the_repository, "%s", get_lock_file_path(lock)); + if (was_full) + ensure_full_index(istate); + if (ret) return ret; if (flags & COMMIT_LOCK) @@ -3172,9 +3233,10 @@ static int write_shared_index(struct index_state *istate, struct tempfile **temp) { struct split_index *si = istate->split_index; - int ret; + int ret, was_full = !istate->sparse_index; move_cache_to_base_index(istate); + convert_to_sparse(istate); trace2_region_enter_printf("index", "shared/do_write_index", the_repository, "%s", get_tempfile_path(*temp)); @@ -3182,6 +3244,9 @@ static int write_shared_index(struct index_state *istate, trace2_region_leave_printf("index", "shared/do_write_index", the_repository, "%s", get_tempfile_path(*temp)); + if (was_full) + ensure_full_index(istate); + if (ret) return ret; ret = adjust_shared_perm(get_tempfile_path(*temp)); @@ -3350,8 +3415,8 @@ int repo_read_index_unmerged(struct repository *repo) * We helpfully remove a trailing "/" from directories so that * the output of read_directory can be used as-is. */ -int index_name_is_other(const struct index_state *istate, const char *name, - int namelen) +int index_name_is_other(struct index_state *istate, const char *name, + int namelen) { int pos; if (namelen && name[namelen - 1] == '/') @@ -3369,7 +3434,7 @@ int index_name_is_other(const struct index_state *istate, const char *name, return 1; } -void *read_blob_data_from_index(const struct index_state *istate, +void *read_blob_data_from_index(struct index_state *istate, const char *path, unsigned long *size) { int pos, len; diff --git a/repo-settings.c b/repo-settings.c index f7fff0f5ab..0cfe8b787d 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -77,4 +77,19 @@ void prepare_repo_settings(struct repository *r) UPDATE_DEFAULT_BOOL(r->settings.core_untracked_cache, UNTRACKED_CACHE_KEEP); UPDATE_DEFAULT_BOOL(r->settings.fetch_negotiation_algorithm, FETCH_NEGOTIATION_DEFAULT); + + /* + * This setting guards all index reads to require a full index + * over a sparse index. After suitable guards are placed in the + * codebase around uses of the index, this setting will be + * removed. + */ + r->settings.command_requires_full_index = 1; + + /* + * Initialize this as off. + */ + r->settings.sparse_index = 0; + if (!repo_config_get_bool(r, "index.sparse", &value) && value) + r->settings.sparse_index = 1; } diff --git a/repository.c b/repository.c index 87b355e7a6..448cd557d4 100644 --- a/repository.c +++ b/repository.c @@ -10,6 +10,7 @@ #include "object.h" #include "lockfile.h" #include "submodule-config.h" +#include "sparse-index.h" /* The main repository */ static struct repository the_repo; @@ -261,6 +262,8 @@ void repo_clear(struct repository *repo) int repo_read_index(struct repository *repo) { + int res; + if (!repo->index) CALLOC_ARRAY(repo->index, 1); @@ -270,7 +273,13 @@ int repo_read_index(struct repository *repo) else if (repo->index->repo != repo) BUG("repo's index should point back at itself"); - return read_index_from(repo->index, repo->index_file, repo->gitdir); + res = read_index_from(repo->index, repo->index_file, repo->gitdir); + + prepare_repo_settings(repo); + if (repo->settings.command_requires_full_index) + ensure_full_index(repo->index); + + return res; } int repo_hold_locked_index(struct repository *repo, diff --git a/repository.h b/repository.h index b385ca3c94..a45f7520fd 100644 --- a/repository.h +++ b/repository.h @@ -41,6 +41,9 @@ struct repo_settings { enum fetch_negotiation_setting fetch_negotiation_algorithm; int core_multi_pack_index; + + unsigned command_requires_full_index:1, + sparse_index:1; }; struct repository { diff --git a/resolve-undo.c b/resolve-undo.c index bbd2e57fe4..e81096e2d4 100644 --- a/resolve-undo.c +++ b/resolve-undo.c @@ -172,6 +172,8 @@ void unmerge_marked_index(struct index_state *istate) if (!istate->resolve_undo) return; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { const struct cache_entry *ce = istate->cache[i]; if (ce->ce_flags & CE_MATCHED) @@ -186,6 +188,8 @@ void unmerge_index(struct index_state *istate, const struct pathspec *pathspec) if (!istate->resolve_undo) return; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { const struct cache_entry *ce = istate->cache[i]; if (!ce_path_match(istate, ce, pathspec, NULL)) diff --git a/revision.c b/revision.c index 7e73dafd96..4853c85d0b 100644 --- a/revision.c +++ b/revision.c @@ -1680,6 +1680,8 @@ static void do_add_index_objects_to_pending(struct rev_info *revs, { int i; + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(istate); for (i = 0; i < istate->cache_nr; i++) { struct cache_entry *ce = istate->cache[i]; struct blob *blob; diff --git a/sparse-index.c b/sparse-index.c new file mode 100644 index 0000000000..6f21397e2e --- /dev/null +++ b/sparse-index.c @@ -0,0 +1,358 @@ +#include "cache.h" +#include "repository.h" +#include "sparse-index.h" +#include "tree.h" +#include "pathspec.h" +#include "trace2.h" +#include "cache-tree.h" +#include "config.h" +#include "dir.h" +#include "fsmonitor.h" + +static struct cache_entry *construct_sparse_dir_entry( + struct index_state *istate, + const char *sparse_dir, + struct cache_tree *tree) +{ + struct cache_entry *de; + + de = make_cache_entry(istate, S_IFDIR, &tree->oid, sparse_dir, 0, 0); + + de->ce_flags |= CE_SKIP_WORKTREE; + return de; +} + +/* + * Returns the number of entries "inserted" into the index. + */ +static int convert_to_sparse_rec(struct index_state *istate, + int num_converted, + int start, int end, + const char *ct_path, size_t ct_pathlen, + struct cache_tree *ct) +{ + int i, can_convert = 1; + int start_converted = num_converted; + enum pattern_match_result match; + int dtype; + struct strbuf child_path = STRBUF_INIT; + struct pattern_list *pl = istate->sparse_checkout_patterns; + + /* + * Is the current path outside of the sparse cone? + * Then check if the region can be replaced by a sparse + * directory entry (everything is sparse and merged). + */ + match = path_matches_pattern_list(ct_path, ct_pathlen, + NULL, &dtype, pl, istate); + if (match != NOT_MATCHED) + can_convert = 0; + + for (i = start; can_convert && i < end; i++) { + struct cache_entry *ce = istate->cache[i]; + + if (ce_stage(ce) || + S_ISGITLINK(ce->ce_mode) || + !(ce->ce_flags & CE_SKIP_WORKTREE)) + can_convert = 0; + } + + if (can_convert) { + struct cache_entry *se; + se = construct_sparse_dir_entry(istate, ct_path, ct); + + istate->cache[num_converted++] = se; + return 1; + } + + for (i = start; i < end; ) { + int count, span, pos = -1; + const char *base, *slash; + struct cache_entry *ce = istate->cache[i]; + + /* + * Detect if this is a normal entry outside of any subtree + * entry. + */ + base = ce->name + ct_pathlen; + slash = strchr(base, '/'); + + if (slash) + pos = cache_tree_subtree_pos(ct, base, slash - base); + + if (pos < 0) { + istate->cache[num_converted++] = ce; + i++; + continue; + } + + strbuf_setlen(&child_path, 0); + strbuf_add(&child_path, ce->name, slash - ce->name + 1); + + span = ct->down[pos]->cache_tree->entry_count; + count = convert_to_sparse_rec(istate, + num_converted, i, i + span, + child_path.buf, child_path.len, + ct->down[pos]->cache_tree); + num_converted += count; + i += span; + } + + strbuf_release(&child_path); + return num_converted - start_converted; +} + +static int set_index_sparse_config(struct repository *repo, int enable) +{ + int res; + char *config_path = repo_git_path(repo, "config.worktree"); + res = git_config_set_in_file_gently(config_path, + "index.sparse", + enable ? "true" : NULL); + free(config_path); + + prepare_repo_settings(repo); + repo->settings.sparse_index = 1; + return res; +} + +int set_sparse_index_config(struct repository *repo, int enable) +{ + int res = set_index_sparse_config(repo, enable); + + prepare_repo_settings(repo); + repo->settings.sparse_index = enable; + return res; +} + +int convert_to_sparse(struct index_state *istate) +{ + int test_env; + 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 + * index.sparse config variable to be on. + */ + test_env = git_env_bool("GIT_TEST_SPARSE_INDEX", -1); + if (test_env >= 0) + set_sparse_index_config(istate->repo, test_env); + + /* + * Only convert to sparse if index.sparse is set. + */ + prepare_repo_settings(istate->repo); + if (!istate->repo->settings.sparse_index) + return 0; + + if (!istate->sparse_checkout_patterns) { + istate->sparse_checkout_patterns = xcalloc(1, sizeof(struct pattern_list)); + if (get_sparse_checkout_patterns(istate->sparse_checkout_patterns) < 0) + return 0; + } + + if (!istate->sparse_checkout_patterns->use_cone_patterns) { + warning(_("attempting to use sparse-index without cone mode")); + return -1; + } + + if (cache_tree_update(istate, 0)) { + warning(_("unable to update cache-tree, staying full")); + return -1; + } + + remove_fsmonitor(istate); + + trace2_region_enter("index", "convert_to_sparse", istate->repo); + istate->cache_nr = convert_to_sparse_rec(istate, + 0, 0, istate->cache_nr, + "", 0, istate->cache_tree); + + /* Clear and recompute the cache-tree */ + cache_tree_free(&istate->cache_tree); + cache_tree_update(istate, 0); + + istate->sparse_index = 1; + trace2_region_leave("index", "convert_to_sparse", istate->repo); + return 0; +} + +static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce) +{ + ALLOC_GROW(istate->cache, nr + 1, istate->cache_alloc); + + istate->cache[nr] = ce; + add_name_hash(istate, ce); +} + +static int add_path_to_index(const struct object_id *oid, + struct strbuf *base, const char *path, + unsigned int mode, void *context) +{ + struct index_state *istate = (struct index_state *)context; + struct cache_entry *ce; + size_t len = base->len; + + if (S_ISDIR(mode)) + return READ_TREE_RECURSIVE; + + strbuf_addstr(base, path); + + ce = make_cache_entry(istate, mode, oid, base->buf, 0, 0); + ce->ce_flags |= CE_SKIP_WORKTREE; + set_index_entry(istate, istate->cache_nr++, ce); + + strbuf_setlen(base, len); + return 0; +} + +void ensure_full_index(struct index_state *istate) +{ + int i; + struct index_state *full; + struct strbuf base = STRBUF_INIT; + + if (!istate || !istate->sparse_index) + return; + + if (!istate->repo) + istate->repo = the_repository; + + trace2_region_enter("index", "ensure_full_index", istate->repo); + + /* initialize basics of new index */ + full = xcalloc(1, sizeof(struct index_state)); + memcpy(full, istate, sizeof(struct index_state)); + + /* then change the necessary things */ + full->sparse_index = 0; + full->cache_alloc = (3 * istate->cache_alloc) / 2; + full->cache_nr = 0; + ALLOC_ARRAY(full->cache, full->cache_alloc); + + for (i = 0; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i]; + struct tree *tree; + struct pathspec ps; + + if (!S_ISSPARSEDIR(ce->ce_mode)) { + set_index_entry(full, full->cache_nr++, ce); + continue; + } + if (!(ce->ce_flags & CE_SKIP_WORKTREE)) + warning(_("index entry is a directory, but not sparse (%08x)"), + ce->ce_flags); + + /* recursively walk into cd->name */ + tree = lookup_tree(istate->repo, &ce->oid); + + memset(&ps, 0, sizeof(ps)); + ps.recursive = 1; + ps.has_wildcard = 1; + ps.max_depth = -1; + + strbuf_setlen(&base, 0); + strbuf_add(&base, ce->name, strlen(ce->name)); + + read_tree_at(istate->repo, tree, &base, &ps, + add_path_to_index, full); + + /* free directory entries. full entries are re-used */ + discard_cache_entry(ce); + } + + /* Copy back into original index. */ + memcpy(&istate->name_hash, &full->name_hash, sizeof(full->name_hash)); + istate->sparse_index = 0; + free(istate->cache); + istate->cache = full->cache; + istate->cache_nr = full->cache_nr; + istate->cache_alloc = full->cache_alloc; + + strbuf_release(&base); + free(full); + + /* Clear and recompute the cache-tree */ + cache_tree_free(&istate->cache_tree); + cache_tree_update(istate, 0); + + trace2_region_leave("index", "ensure_full_index", istate->repo); +} + +/* + * This static global helps avoid infinite recursion between + * expand_to_path() and index_file_exists(). + */ +static int in_expand_to_path = 0; + +void expand_to_path(struct index_state *istate, + const char *path, size_t pathlen, int icase) +{ + struct strbuf path_mutable = STRBUF_INIT; + size_t substr_len; + + /* prevent extra recursion */ + if (in_expand_to_path) + return; + + if (!istate || !istate->sparse_index) + return; + + if (!istate->repo) + istate->repo = the_repository; + + in_expand_to_path = 1; + + /* + * We only need to actually expand a region if the + * following are both true: + * + * 1. 'path' is not already in the index. + * 2. Some parent directory of 'path' is a sparse directory. + */ + + if (index_file_exists(istate, path, pathlen, icase)) + goto cleanup; + + strbuf_add(&path_mutable, path, pathlen); + strbuf_addch(&path_mutable, '/'); + + /* Check the name hash for all parent directories */ + substr_len = 0; + while (substr_len < pathlen) { + char temp; + char *replace = strchr(path_mutable.buf + substr_len, '/'); + + if (!replace) + break; + + /* replace the character _after_ the slash */ + replace++; + temp = *replace; + *replace = '\0'; + if (index_file_exists(istate, path_mutable.buf, + path_mutable.len, icase)) { + /* + * We found a parent directory in the name-hash + * hashtable, because only sparse directory entries + * have a trailing '/' character. Since "path" wasn't + * in the index, perhaps it exists within this + * sparse-directory. Expand accordingly. + */ + ensure_full_index(istate); + break; + } + + *replace = temp; + substr_len = replace - path_mutable.buf; + } + +cleanup: + strbuf_release(&path_mutable); + in_expand_to_path = 0; +} diff --git a/sparse-index.h b/sparse-index.h new file mode 100644 index 0000000000..1115a0d7dd --- /dev/null +++ b/sparse-index.h @@ -0,0 +1,23 @@ +#ifndef SPARSE_INDEX_H__ +#define SPARSE_INDEX_H__ + +struct index_state; +int convert_to_sparse(struct index_state *istate); + +/* + * Some places in the codebase expect to search for a specific path. + * This path might be outside of the sparse-checkout definition, in + * which case a sparse-index may not contain a path for that index. + * + * Given an index and a path, check to see if a leading directory for + * 'path' exists in the index as a sparse directory. In that case, + * expand that sparse directory to a full range of cache entries and + * populate the index accordingly. + */ +void expand_to_path(struct index_state *istate, + const char *path, size_t pathlen, int icase); + +struct repository; +int set_sparse_index_config(struct repository *repo, int enable); + +#endif diff --git a/submodule.c b/submodule.c index 9767ba9893..83809a4f7b 100644 --- a/submodule.c +++ b/submodule.c @@ -33,7 +33,7 @@ static struct oid_array ref_tips_after_fetch; * will be disabled because we can't guess what might be configured in * .gitmodules unless the user resolves the conflict. */ -int is_gitmodules_unmerged(const struct index_state *istate) +int is_gitmodules_unmerged(struct index_state *istate) { int pos = index_name_pos(istate, GITMODULES_FILE, strlen(GITMODULES_FILE)); if (pos < 0) { /* .gitmodules not found or isn't merged */ @@ -301,7 +301,7 @@ int is_submodule_populated_gently(const char *path, int *return_error_code) /* * Dies if the provided 'prefix' corresponds to an unpopulated submodule */ -void die_in_unpopulated_submodule(const struct index_state *istate, +void die_in_unpopulated_submodule(struct index_state *istate, const char *prefix) { int i, prefixlen; @@ -331,7 +331,7 @@ void die_in_unpopulated_submodule(const struct index_state *istate, /* * Dies if any paths in the provided pathspec descends into a submodule */ -void die_path_inside_submodule(const struct index_state *istate, +void die_path_inside_submodule(struct index_state *istate, const struct pathspec *ps) { int i, j; diff --git a/submodule.h b/submodule.h index 4ac6e31cf1..84640c49c1 100644 --- a/submodule.h +++ b/submodule.h @@ -39,7 +39,7 @@ struct submodule_update_strategy { }; #define SUBMODULE_UPDATE_STRATEGY_INIT {SM_UPDATE_UNSPECIFIED, NULL} -int is_gitmodules_unmerged(const struct index_state *istate); +int is_gitmodules_unmerged(struct index_state *istate); int is_writing_gitmodules_ok(void); int is_staging_gitmodules_ok(struct index_state *istate); int update_path_in_gitmodules(const char *oldpath, const char *newpath); @@ -60,9 +60,9 @@ int is_submodule_active(struct repository *repo, const char *path); * Otherwise the return error code is the same as of resolve_gitdir_gently. */ int is_submodule_populated_gently(const char *path, int *return_error_code); -void die_in_unpopulated_submodule(const struct index_state *istate, +void die_in_unpopulated_submodule(struct index_state *istate, const char *prefix); -void die_path_inside_submodule(const struct index_state *istate, +void die_path_inside_submodule(struct index_state *istate, const struct pathspec *ps); enum submodule_update_type parse_submodule_update_type(const char *value); int parse_submodule_update_strategy(const char *value, diff --git a/t/README b/t/README index fd9375b146..8eb9e46b1d 100644 --- a/t/README +++ b/t/README @@ -436,6 +436,9 @@ and "sha256". GIT_TEST_WRITE_REV_INDEX=, when true enables the 'pack.writeReverseIndex' setting. +GIT_TEST_SPARSE_INDEX=, when true enables index writes to use the +sparse-index format by default. + Naming Tests ------------ diff --git a/t/helper/test-read-cache.c b/t/helper/test-read-cache.c index 244977a29b..b52c174acc 100644 --- a/t/helper/test-read-cache.c +++ b/t/helper/test-read-cache.c @@ -1,36 +1,82 @@ #include "test-tool.h" #include "cache.h" #include "config.h" +#include "blob.h" +#include "commit.h" +#include "tree.h" +#include "sparse-index.h" + +static void print_cache_entry(struct cache_entry *ce) +{ + const char *type; + printf("%06o ", ce->ce_mode & 0177777); + + if (S_ISSPARSEDIR(ce->ce_mode)) + type = tree_type; + else if (S_ISGITLINK(ce->ce_mode)) + type = commit_type; + else + type = blob_type; + + printf("%s %s\t%s\n", + type, + oid_to_hex(&ce->oid), + ce->name); +} + +static void print_cache(struct index_state *istate) +{ + int i; + for (i = 0; i < istate->cache_nr; i++) + print_cache_entry(istate->cache[i]); +} int cmd__read_cache(int argc, const char **argv) { + struct repository *r = the_repository; int i, cnt = 1; const char *name = NULL; + int table = 0, expand = 0; - if (argc > 1 && skip_prefix(argv[1], "--print-and-refresh=", &name)) { - argc--; - argv++; + initialize_the_repository(); + prepare_repo_settings(r); + r->settings.command_requires_full_index = 0; + + for (++argv, --argc; *argv && starts_with(*argv, "--"); ++argv, --argc) { + if (skip_prefix(*argv, "--print-and-refresh=", &name)) + continue; + if (!strcmp(*argv, "--table")) + table = 1; + else if (!strcmp(*argv, "--expand")) + expand = 1; } - if (argc == 2) - cnt = strtol(argv[1], NULL, 0); + if (argc == 1) + cnt = strtol(argv[0], NULL, 0); setup_git_directory(); git_config(git_default_config, NULL); + for (i = 0; i < cnt; i++) { - read_cache(); + repo_read_index(r); + + if (expand) + ensure_full_index(r->index); + if (name) { int pos; - refresh_index(&the_index, REFRESH_QUIET, + refresh_index(r->index, REFRESH_QUIET, NULL, NULL, NULL); - pos = index_name_pos(&the_index, name, strlen(name)); + pos = index_name_pos(r->index, name, strlen(name)); if (pos < 0) die("%s not in index", name); printf("%s is%s up to date\n", name, - ce_uptodate(the_index.cache[pos]) ? "" : " not"); + ce_uptodate(r->index->cache[pos]) ? "" : " not"); write_file(name, "%d\n", i); } - discard_cache(); + if (table) + print_cache(r->index); + discard_index(r->index); } return 0; } diff --git a/t/perf/p2000-sparse-operations.sh b/t/perf/p2000-sparse-operations.sh new file mode 100755 index 0000000000..94513c9774 --- /dev/null +++ b/t/perf/p2000-sparse-operations.sh @@ -0,0 +1,101 @@ +#!/bin/sh + +test_description="test performance of Git operations using the index" + +. ./perf-lib.sh + +test_perf_default_repo + +SPARSE_CONE=f2/f4/f1 + +test_expect_success 'setup repo and indexes' ' + git reset --hard HEAD && + + # Remove submodules from the example repo, because our + # duplication of the entire repo creates an unlikely data shape. + if git config --file .gitmodules --get-regexp "submodule.*.path" >modules + then + git rm $(awk "{print \$2}" modules) && + git commit -m "remove submodules" || return 1 + fi && + + echo bogus >a && + cp a b && + git add a b && + git commit -m "level 0" && + BLOB=$(git rev-parse HEAD:a) && + OLD_COMMIT=$(git rev-parse HEAD) && + OLD_TREE=$(git rev-parse HEAD^{tree}) && + + for i in $(test_seq 1 4) + do + cat >in <<-EOF && + 100755 blob $BLOB a + 040000 tree $OLD_TREE f1 + 040000 tree $OLD_TREE f2 + 040000 tree $OLD_TREE f3 + 040000 tree $OLD_TREE f4 + EOF + NEW_TREE=$(git mktree >$SPARSE_CONE/a && + $command + ) + " + done +} + +test_perf_on_all git status +test_perf_on_all git add -A +test_perf_on_all git add . +test_perf_on_all git commit -a -m A + +test_done diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh index fc64e9ed99..38fc8340f5 100755 --- a/t/t1091-sparse-checkout-builtin.sh +++ b/t/t1091-sparse-checkout-builtin.sh @@ -205,6 +205,19 @@ test_expect_success 'sparse-checkout disable' ' check_files repo a deep folder1 folder2 ' +test_expect_success 'sparse-index enabled and disabled' ' + git -C repo sparse-checkout init --cone --sparse-index && + test_cmp_config -C repo true index.sparse && + test-tool -C repo read-cache --table >cache && + grep " tree " cache && + + git -C repo sparse-checkout disable && + test-tool -C repo read-cache --table >cache && + ! grep " tree " cache && + git -C repo config --list >config && + ! grep index.sparse config +' + test_expect_success 'cone mode: init and set' ' git -C repo sparse-checkout init --cone && git -C repo config --list >config && diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh index 8cd3e5a8d2..12e6c45302 100755 --- a/t/t1092-sparse-checkout-compatibility.sh +++ b/t/t1092-sparse-checkout-compatibility.sh @@ -2,11 +2,15 @@ test_description='compare full workdir to sparse workdir' +GIT_TEST_SPLIT_INDEX=0 +GIT_TEST_SPARSE_INDEX= + . ./test-lib.sh test_expect_success 'setup' ' git init initial-repo && ( + GIT_TEST_SPARSE_INDEX=0 && cd initial-repo && echo a >a && echo "after deep" >e && @@ -87,39 +91,102 @@ init_repos () { cp -r initial-repo sparse-checkout && git -C sparse-checkout reset --hard && - git -C sparse-checkout sparse-checkout init --cone && + + cp -r initial-repo sparse-index && + git -C sparse-index reset --hard && # initialize sparse-checkout definitions - git -C sparse-checkout sparse-checkout set deep + git -C sparse-checkout sparse-checkout init --cone && + git -C sparse-checkout sparse-checkout set deep && + git -C sparse-index sparse-checkout init --cone --sparse-index && + test_cmp_config -C sparse-index true index.sparse && + git -C sparse-index sparse-checkout set deep } run_on_sparse () { ( cd sparse-checkout && - $* >../sparse-checkout-out 2>../sparse-checkout-err + "$@" >../sparse-checkout-out 2>../sparse-checkout-err + ) && + ( + cd sparse-index && + "$@" >../sparse-index-out 2>../sparse-index-err ) } run_on_all () { ( cd full-checkout && - $* >../full-checkout-out 2>../full-checkout-err + "$@" >../full-checkout-out 2>../full-checkout-err ) && - run_on_sparse $* + run_on_sparse "$@" } test_all_match () { - run_on_all $* && + run_on_all "$@" && test_cmp full-checkout-out sparse-checkout-out && - test_cmp full-checkout-err sparse-checkout-err + test_cmp full-checkout-out sparse-index-out && + test_cmp full-checkout-err sparse-checkout-err && + test_cmp full-checkout-err sparse-index-err } +test_sparse_match () { + run_on_sparse "$@" && + test_cmp sparse-checkout-out sparse-index-out && + test_cmp sparse-checkout-err sparse-index-err +} + +test_expect_success 'sparse-index contents' ' + init_repos && + + test-tool -C sparse-index read-cache --table >cache && + for dir in folder1 folder2 x + do + TREE=$(git -C sparse-index rev-parse HEAD:$dir) && + grep "040000 tree $TREE $dir/" cache \ + || return 1 + done && + + git -C sparse-index sparse-checkout set folder1 && + + test-tool -C sparse-index read-cache --table >cache && + for dir in deep folder2 x + do + TREE=$(git -C sparse-index rev-parse HEAD:$dir) && + grep "040000 tree $TREE $dir/" cache \ + || return 1 + done && + + git -C sparse-index sparse-checkout set deep/deeper1 && + + test-tool -C sparse-index read-cache --table >cache && + for dir in deep/deeper2 folder1 folder2 x + do + TREE=$(git -C sparse-index rev-parse HEAD:$dir) && + grep "040000 tree $TREE $dir/" cache \ + || return 1 + done && + + # Disabling the sparse-index removes tree entries with full ones + git -C sparse-index sparse-checkout init --no-sparse-index && + + test-tool -C sparse-index read-cache --table >cache && + ! grep "040000 tree" cache && + test_sparse_match test-tool read-cache --table +' + +test_expect_success 'expanded in-memory index matches full index' ' + init_repos && + test_sparse_match test-tool read-cache --expand --table +' + test_expect_success 'status with options' ' init_repos && + test_sparse_match ls && test_all_match git status --porcelain=v2 && test_all_match git status --porcelain=v2 -z -u && test_all_match git status --porcelain=v2 -uno && - run_on_all "touch README.md" && + run_on_all touch README.md && test_all_match git status --porcelain=v2 && test_all_match git status --porcelain=v2 -z -u && test_all_match git status --porcelain=v2 -uno && @@ -135,7 +202,7 @@ test_expect_success 'add, commit, checkout' ' write_script edit-contents <<-\EOF && echo text >>$1 EOF - run_on_all "../edit-contents README.md" && + run_on_all ../edit-contents README.md && test_all_match git add README.md && test_all_match git status --porcelain=v2 && @@ -144,7 +211,7 @@ test_expect_success 'add, commit, checkout' ' test_all_match git checkout HEAD~1 && test_all_match git checkout - && - run_on_all "../edit-contents README.md" && + run_on_all ../edit-contents README.md && test_all_match git add -A && test_all_match git status --porcelain=v2 && @@ -153,7 +220,7 @@ test_expect_success 'add, commit, checkout' ' test_all_match git checkout HEAD~1 && test_all_match git checkout - && - run_on_all "../edit-contents deep/newfile" && + run_on_all ../edit-contents deep/newfile && test_all_match git status --porcelain=v2 -uno && test_all_match git status --porcelain=v2 && @@ -186,7 +253,7 @@ test_expect_success 'diff --staged' ' write_script edit-contents <<-\EOF && echo text >>README.md EOF - run_on_all "../edit-contents" && + run_on_all ../edit-contents && test_all_match git diff && test_all_match git diff --staged && @@ -252,6 +319,17 @@ test_expect_failure 'checkout and reset (mixed)' ' test_all_match git reset update-folder2 ' +# Ensure that sparse-index behaves identically to +# sparse-checkout with a full index. +test_expect_success 'checkout and reset (mixed) [sparse]' ' + init_repos && + + test_sparse_match git checkout -b reset-test update-deep && + test_sparse_match git reset deepest && + test_sparse_match git reset update-folder1 && + test_sparse_match git reset update-folder2 +' + test_expect_success 'merge' ' init_repos && @@ -280,7 +358,7 @@ test_expect_success 'clean' ' echo bogus >>.gitignore && run_on_all cp ../.gitignore . && test_all_match git add .gitignore && - test_all_match git commit -m ignore-bogus-files && + test_all_match git commit -m "ignore bogus files" && run_on_sparse mkdir folder1 && run_on_all touch folder1/bogus && @@ -288,14 +366,51 @@ test_expect_success 'clean' ' test_all_match git status --porcelain=v2 && test_all_match git clean -f && test_all_match git status --porcelain=v2 && + test_sparse_match ls && + test_sparse_match ls folder1 && test_all_match git clean -xf && test_all_match git status --porcelain=v2 && + test_sparse_match ls && + test_sparse_match ls folder1 && test_all_match git clean -xdf && test_all_match git status --porcelain=v2 && + test_sparse_match ls && + test_sparse_match ls folder1 && - test_path_is_dir sparse-checkout/folder1 + test_sparse_match test_path_is_dir folder1 +' + +test_expect_success 'submodule handling' ' + init_repos && + + test_all_match mkdir modules && + test_all_match touch modules/a && + test_all_match git add modules && + test_all_match git commit -m "add modules directory" && + + run_on_all git submodule add "$(pwd)/initial-repo" modules/sub && + test_all_match git commit -m "add submodule" && + + # having a submodule prevents "modules" from collapse + test-tool -C sparse-index read-cache --table >cache && + grep "100644 blob .* modules/a" cache && + grep "160000 commit $(git -C initial-repo rev-parse HEAD) modules/sub" cache +' + +test_expect_success 'sparse-index is expanded and converted back' ' + init_repos && + + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \ + git -C sparse-index -c core.fsmonitor="" reset --hard && + test_region index convert_to_sparse trace2.txt && + test_region index ensure_full_index trace2.txt && + + rm trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \ + git -C sparse-index -c core.fsmonitor="" status -uno && + test_region index ensure_full_index trace2.txt ' test_done diff --git a/unpack-trees.c b/unpack-trees.c index 8a1afbc1e4..9cffa88af4 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -750,9 +750,13 @@ static int index_pos_by_traverse_info(struct name_entry *names, strbuf_make_traverse_path(&name, info, names->path, names->pathlen); strbuf_addch(&name, '/'); pos = index_name_pos(o->src_index, name.buf, name.len); - if (pos >= 0) - BUG("This is a directory and should not exist in index"); - pos = -pos - 1; + if (pos >= 0) { + if (!o->src_index->sparse_index || + !(o->src_index->cache[pos]->ce_flags & CE_SKIP_WORKTREE)) + BUG("This is a directory and should not exist in index"); + } else { + pos = -pos - 1; + } if (pos >= o->src_index->cache_nr || !starts_with(o->src_index->cache[pos]->name, name.buf) || (pos > 0 && starts_with(o->src_index->cache[pos-1]->name, name.buf))) @@ -1571,6 +1575,7 @@ static int verify_absent(const struct cache_entry *, */ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options *o) { + struct repository *repo = the_repository; int i, ret; static struct cache_entry *dfc; struct pattern_list pl; @@ -1582,6 +1587,12 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options trace_performance_enter(); trace2_region_enter("unpack_trees", "unpack_trees", the_repository); + prepare_repo_settings(repo); + if (repo->settings.command_requires_full_index) { + ensure_full_index(o->src_index); + ensure_full_index(o->dst_index); + } + if (!core_apply_sparse_checkout || !o->update) o->skip_sparse_checkout = 1; if (!o->skip_sparse_checkout && !o->pl) {