From 5a4e0547e2386f9bf0565316d7b751fe9459898b Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Wed, 22 Dec 2021 14:20:52 +0000 Subject: fetch/pull: use the sparse index The 'git fetch' and 'git pull' commands parse the index in order to determine if submodules exist. Without command_requires_full_index=0, this will expand a sparse index, causing slow performance even when there is no new data to fetch. The .gitmodules file will never be inside a sparse directory entry, and even if it was, the index_name_pos() method would expand the sparse index if needed as we search for the path by name. These commands do not iterate over the index, which is the typical thing we are careful about when integrating with the sparse index. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano diff --git a/builtin/fetch.c b/builtin/fetch.c index e45185c..a0757dd 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -1999,6 +1999,8 @@ int cmd_fetch(int argc, const char **argv, const char *prefix) } git_config(git_fetch_config, NULL); + prepare_repo_settings(the_repository); + the_repository->settings.command_requires_full_index = 0; argc = parse_options(argc, argv, prefix, builtin_fetch_options, builtin_fetch_usage, 0); diff --git a/builtin/pull.c b/builtin/pull.c index c845761..100cbf9 100644 --- a/builtin/pull.c +++ b/builtin/pull.c @@ -994,6 +994,8 @@ int cmd_pull(int argc, const char **argv, const char *prefix) set_reflog_message(argc, argv); git_config(git_pull_config, NULL); + prepare_repo_settings(the_repository); + the_repository->settings.command_requires_full_index = 0; argc = parse_options(argc, argv, prefix, pull_options, pull_usage, 0); diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh index 49f70a6..8d3c21f 100755 --- a/t/t1092-sparse-checkout-compatibility.sh +++ b/t/t1092-sparse-checkout-compatibility.sh @@ -1009,6 +1009,16 @@ test_expect_success 'sparse index is not expanded: blame' ' done ' +test_expect_success 'sparse index is not expanded: fetch/pull' ' + init_repos && + + git -C sparse-index remote add full "file://$(pwd)/full-checkout" && + ensure_not_expanded fetch full && + git -C full-checkout commit --allow-empty -m "for pull merge" && + git -C sparse-index commit --allow-empty -m "for pull merge" && + ensure_not_expanded pull full base +' + # NEEDSWORK: a sparse-checkout behaves differently from a full checkout # in this scenario, but it shouldn't. test_expect_success 'reset mixed and checkout orphan' ' -- cgit v0.10.2-6-g49f6 From 78087097b8b77aca355525ebaf98205eb7acad60 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Wed, 22 Dec 2021 14:20:53 +0000 Subject: ls-files: add --sparse option Existing callers to 'git ls-files' are expecting file names, not directories. It is best to expand a sparse index to show all of the contained files in this case. However, expert users may want to inspect the contents of the index itself including which directories are sparse. Add a --sparse option to allow users to request this information. During testing, I noticed that options such as --modified did not affect the output when the files in question were outside the sparse-checkout definition. Tests are added to document this preexisting behavior and how it remains unchanged with the sparse index and the --sparse option. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt index 2e3d695..48cc7c0 100644 --- a/Documentation/git-ls-files.txt +++ b/Documentation/git-ls-files.txt @@ -187,6 +187,11 @@ Both the in the index ("i/") and in the working tree ("w/") are shown for regular files, followed by the ("attr/"). +--sparse:: + If the index is sparse, show the sparse directories without expanding + to the contained files. Sparse directories will be shown with a + trailing slash, such as "x/" for a sparse directory "x". + \--:: Do not interpret any more arguments as options. diff --git a/builtin/ls-files.c b/builtin/ls-files.c index 031fef1..c151eb1 100644 --- a/builtin/ls-files.c +++ b/builtin/ls-files.c @@ -37,6 +37,7 @@ static int debug_mode; static int show_eol; static int recurse_submodules; static int skipping_duplicates; +static int show_sparse_dirs; static const char *prefix; static int max_prefix_len; @@ -315,8 +316,10 @@ 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); + + if (!show_sparse_dirs) + 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; @@ -670,6 +673,8 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix) OPT_BOOL(0, "debug", &debug_mode, N_("show debugging data")), OPT_BOOL(0, "deduplicate", &skipping_duplicates, N_("suppress duplicate entries")), + OPT_BOOL(0, "sparse", &show_sparse_dirs, + N_("show sparse directories in the presence of a sparse index")), OPT_END() }; int ret = 0; @@ -677,6 +682,9 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix) if (argc == 2 && !strcmp(argv[1], "-h")) usage_with_options(ls_files_usage, builtin_ls_files_options); + prepare_repo_settings(the_repository); + the_repository->settings.command_requires_full_index = 0; + prefix = cmd_prefix; if (prefix) prefix_len = strlen(prefix); diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh index 8d3c21f..0c51e9b 100755 --- a/t/t1092-sparse-checkout-compatibility.sh +++ b/t/t1092-sparse-checkout-compatibility.sh @@ -816,6 +816,12 @@ test_expect_success 'sparse-index is expanded and converted back' ' GIT_TRACE2_EVENT="$(pwd)/trace2.txt" \ git -C sparse-index reset -- folder1/a && test_region index convert_to_sparse trace2.txt && + test_region index ensure_full_index trace2.txt && + + # ls-files expands on read, but does not write. + rm trace2.txt && + GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \ + git -C sparse-index ls-files && test_region index ensure_full_index trace2.txt ' @@ -871,6 +877,7 @@ test_expect_success 'sparse-index is not expanded' ' init_repos && ensure_not_expanded status && + ensure_not_expanded ls-files --sparse && ensure_not_expanded commit --allow-empty -m empty && echo >>sparse-index/a && ensure_not_expanded commit -a -m a && @@ -1019,6 +1026,90 @@ test_expect_success 'sparse index is not expanded: fetch/pull' ' ensure_not_expanded pull full base ' +test_expect_success 'ls-files' ' + init_repos && + + # Use a smaller sparse-checkout for reduced output + test_sparse_match git sparse-checkout set && + + # Behavior agrees by default. Sparse index is expanded. + test_all_match git ls-files && + + # With --sparse, the sparse index data changes behavior. + git -C sparse-index ls-files --sparse >actual && + + cat >expect <<-\EOF && + a + deep/ + e + folder1- + folder1.x + folder1/ + folder10 + folder2/ + g + x/ + z + EOF + + test_cmp expect actual && + + # With --sparse and no sparse index, nothing changes. + git -C sparse-checkout ls-files >dense && + git -C sparse-checkout ls-files --sparse >sparse && + test_cmp dense sparse && + + # Set up a strange condition of having a file edit + # outside of the sparse-checkout cone. This is just + # to verify that sparse-checkout and sparse-index + # behave the same in this case. + write_script edit-content <<-\EOF && + mkdir folder1 && + echo content >>folder1/a + EOF + run_on_sparse ../edit-content && + + # ls-files does not currently notice modified files whose + # cache entries are marked SKIP_WORKTREE. This may change + # in the future, but here we test that sparse index does + # not accidentally create a change of behavior. + test_sparse_match git ls-files --modified && + test_must_be_empty sparse-checkout-out && + test_must_be_empty sparse-index-out && + + git -C sparse-index ls-files --sparse --modified >sparse-index-out && + test_must_be_empty sparse-index-out && + + # Add folder1 to the sparse-checkout cone and + # check that ls-files shows the expanded files. + test_sparse_match git sparse-checkout add folder1 && + test_sparse_match git ls-files --modified && + + test_all_match git ls-files && + git -C sparse-index ls-files --sparse >actual && + + cat >expect <<-\EOF && + a + deep/ + e + folder1- + folder1.x + folder1/0/0/0 + folder1/0/1 + folder1/a + folder10 + folder2/ + g + x/ + z + EOF + + test_cmp expect actual && + + # Double-check index expansion is avoided + ensure_not_expanded ls-files --sparse +' + # NEEDSWORK: a sparse-checkout behaves differently from a full checkout # in this scenario, but it shouldn't. test_expect_success 'reset mixed and checkout orphan' ' -- cgit v0.10.2-6-g49f6 From 3a9a6ac5d9df68152795e66acba02afd928bf705 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Wed, 22 Dec 2021 14:20:54 +0000 Subject: t1092: replace 'read-cache --table' with 'ls-files --sparse' Now that 'git ls-files --sparse' exists, we can use it to verify the state of a sparse index instead of 'test-tool read-cache table'. Replace these usages within t1092-sparse-checkout-compatibility.sh. The important changes are due to the different output format. We need to use the '--stage' output to get a file mode and OID, but it also includes a stage value and drops the object type. This leads to some differences in how we handle looking for specific entries. Some places where we previously looked for no 'tree' entries, we can instead directly compare the output across the repository with a sparse index and the one without. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh index 0c51e9b..4ba1617 100755 --- a/t/t1092-sparse-checkout-compatibility.sh +++ b/t/t1092-sparse-checkout-compatibility.sh @@ -206,45 +206,42 @@ test_sparse_unstaged () { test_expect_success 'sparse-index contents' ' init_repos && - test-tool -C sparse-index read-cache --table >cache && + git -C sparse-index ls-files --sparse --stage >cache && for dir in folder1 folder2 x do TREE=$(git -C sparse-index rev-parse HEAD:$dir) && - grep "040000 tree $TREE $dir/" cache \ + grep "040000 $TREE 0 $dir/" cache \ || return 1 done && git -C sparse-index sparse-checkout set folder1 && - test-tool -C sparse-index read-cache --table >cache && + git -C sparse-index ls-files --sparse --stage >cache && for dir in deep folder2 x do TREE=$(git -C sparse-index rev-parse HEAD:$dir) && - grep "040000 tree $TREE $dir/" cache \ + grep "040000 $TREE 0 $dir/" cache \ || return 1 done && git -C sparse-index sparse-checkout set deep/deeper1 && - test-tool -C sparse-index read-cache --table >cache && + git -C sparse-index ls-files --sparse --stage >cache && for dir in deep/deeper2 folder1 folder2 x do TREE=$(git -C sparse-index rev-parse HEAD:$dir) && - grep "040000 tree $TREE $dir/" cache \ + grep "040000 $TREE 0 $dir/" cache \ || return 1 done && - # Disabling the sparse-index removes tree entries with full ones + # Disabling the sparse-index replaces 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_sparse_match git ls-files --stage --sparse ' test_expect_success 'expanded in-memory index matches full index' ' init_repos && - test_sparse_match test-tool read-cache --expand --table + test_sparse_match git ls-files --stage ' test_expect_success 'status with options' ' @@ -801,9 +798,9 @@ test_expect_success 'submodule handling' ' # having a submodule prevents "modules" from collapse test_sparse_match git sparse-checkout set deep/deeper1 && - 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 + git -C sparse-index ls-files --sparse --stage >cache && + grep "100644 .* modules/a" cache && + grep "160000 $(git -C initial-repo rev-parse HEAD) 0 modules/sub" cache ' # When working with a sparse index, some commands will need to expand the @@ -1125,13 +1122,13 @@ test_expect_success 'reset mixed and checkout orphan' ' # the sparse checkouts skip "adding" the other side of # the conflict. test_sparse_match git reset --mixed HEAD~1 && - test_sparse_match test-tool read-cache --table --expand && + test_sparse_match git ls-files --stage && test_sparse_match git status --porcelain=v2 && # At this point, sparse-checkouts behave differently # from the full-checkout. test_sparse_match git checkout --orphan new-branch && - test_sparse_match test-tool read-cache --table --expand && + test_sparse_match git ls-files --stage && test_sparse_match git status --porcelain=v2 ' -- cgit v0.10.2-6-g49f6 From c2a2940510579bad9f5c63797542c47f14e8a2da Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Wed, 22 Dec 2021 14:20:55 +0000 Subject: t1091/t3705: remove 'test-tool read-cache --table' Now that 'git ls-files --sparse' exists, we can use it to verify the state of a sparse index instead of 'test-tool read-cache table'. Replace these usages within t1091-sparse-checkout-builtin.sh and t3705-add-sparse-checkout.sh. The important changes are due to the different output format. In t3705, we need to use the '--stage' output to get a file mode and OID, but it also includes a stage value and drops the object type. This leads to some differences in how we handle looking for specific entries. In t1091, the test focuses on enabling the sparse index, so we do not need the --stage flag to demonstrate how the index changes, and instead can use a diff. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh index 272ba1b..680e004 100755 --- a/t/t1091-sparse-checkout-builtin.sh +++ b/t/t1091-sparse-checkout-builtin.sh @@ -212,12 +212,27 @@ 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 ls-files --sparse >sparse && git -C repo sparse-checkout disable && - test-tool -C repo read-cache --table >cache && - ! grep " tree " cache && + git -C repo ls-files --sparse >full && + + cat >expect <<-\EOF && + @@ -1,4 +1,7 @@ + a + -deep/ + -folder1/ + -folder2/ + +deep/a + +deep/deeper1/a + +deep/deeper1/deepest/a + +deep/deeper2/a + +folder1/a + +folder2/a + EOF + + diff -u sparse full | tail -n +3 >actual && + test_cmp expect actual && + git -C repo config --list >config && ! grep index.sparse config ) diff --git a/t/t3705-add-sparse-checkout.sh b/t/t3705-add-sparse-checkout.sh index f3143c9..81f3384 100755 --- a/t/t3705-add-sparse-checkout.sh +++ b/t/t3705-add-sparse-checkout.sh @@ -181,13 +181,13 @@ test_expect_success 'git add fails outside of sparse-checkout definition' ' # Avoid munging CRLFs to avoid an error message git -c core.autocrlf=input add --sparse sparse_entry 2>stderr && test_must_be_empty stderr && - test-tool read-cache --table >actual && - grep "^100644 blob.*sparse_entry\$" actual && + git ls-files --stage >actual && + grep "^100644 .*sparse_entry\$" actual && git add --sparse --chmod=+x sparse_entry 2>stderr && test_must_be_empty stderr && - test-tool read-cache --table >actual && - grep "^100755 blob.*sparse_entry\$" actual && + git ls-files --stage >actual && + grep "^100755 .*sparse_entry\$" actual && git reset && -- cgit v0.10.2-6-g49f6 From 408c51f0b4b5f978ab3676a7dc8efaffe459bdee Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Wed, 22 Dec 2021 14:20:56 +0000 Subject: test-read-cache: remove --table, --expand options This commit effectively reverts 2782db3 (test-tool: don't force full index, 2021-03-30) and e2df6c3 (test-read-cache: print cache entries with --table, 2021-03-30) to remove the --table and --expand options from 'test-tool read-cache'. The previous changes already removed these options from the test suite in favor of 'git ls-files --sparse'. The initial thought of creating these options was to allow for tests to see additional information with every cache entry. In particular, the object type is still not mirrored in 'git ls-files'. Since sparse directory entries always end with a slash, the object type is not critical to verify the sparse index is enabled. It was thought that it would be helpful to have additional information, such as flags, but that was not needed for the FS Monitor integration and hasn't been needed since. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano diff --git a/t/helper/test-read-cache.c b/t/helper/test-read-cache.c index 0d9f089..b736ef1 100644 --- a/t/helper/test-read-cache.c +++ b/t/helper/test-read-cache.c @@ -1,83 +1,39 @@ #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; initialize_the_repository(); - 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 > 1 && skip_prefix(argv[1], "--print-and-refresh=", &name)) { + argc--; + argv++; } - if (argc == 1) - cnt = strtol(argv[0], NULL, 0); + if (argc == 2) + cnt = strtol(argv[1], NULL, 0); setup_git_directory(); git_config(git_default_config, NULL); - prepare_repo_settings(r); - r->settings.command_requires_full_index = 0; - for (i = 0; i < cnt; i++) { - repo_read_index(r); - - if (expand) - ensure_full_index(r->index); - + read_cache(); if (name) { int pos; - refresh_index(r->index, REFRESH_QUIET, + refresh_index(&the_index, REFRESH_QUIET, NULL, NULL, NULL); - pos = index_name_pos(r->index, name, strlen(name)); + pos = index_name_pos(&the_index, name, strlen(name)); if (pos < 0) die("%s not in index", name); printf("%s is%s up to date\n", name, - ce_uptodate(r->index->cache[pos]) ? "" : " not"); + ce_uptodate(the_index.cache[pos]) ? "" : " not"); write_file(name, "%d\n", i); } - if (table) - print_cache(r->index); - discard_index(r->index); + discard_cache(); } return 0; } -- cgit v0.10.2-6-g49f6