1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-12 05:56:09 +02:00

Merge branch 'vd/sparse-reset'

Various operating modes of "git reset" have been made to work
better with the sparse index.

* vd/sparse-reset:
  unpack-trees: improve performance of next_cache_entry
  reset: make --mixed sparse-aware
  reset: make sparse-aware (except --mixed)
  reset: integrate with sparse index
  reset: expand test coverage for sparse checkouts
  sparse-index: update command for expand/collapse test
  reset: preserve skip-worktree bit in mixed reset
  reset: rename is_missing to !is_in_reset_tree
This commit is contained in:
Junio C Hamano 2021-12-10 14:35:12 -08:00
commit f0850875fd
8 changed files with 356 additions and 37 deletions

View File

@ -25,6 +25,7 @@
#include "cache-tree.h"
#include "submodule.h"
#include "submodule-config.h"
#include "dir.h"
#define REFRESH_INDEX_DELAY_WARNING_IN_MS (2 * 1000)
@ -136,21 +137,36 @@ static void update_index_from_diff(struct diff_queue_struct *q,
int intent_to_add = *(int *)data;
for (i = 0; i < q->nr; i++) {
int pos;
struct diff_filespec *one = q->queue[i]->one;
int is_missing = !(one->mode && !is_null_oid(&one->oid));
int is_in_reset_tree = one->mode && !is_null_oid(&one->oid);
struct cache_entry *ce;
if (is_missing && !intent_to_add) {
if (!is_in_reset_tree && !intent_to_add) {
remove_file_from_cache(one->path);
continue;
}
ce = make_cache_entry(&the_index, one->mode, &one->oid, one->path,
0, 0);
/*
* If the file 1) corresponds to an existing index entry with
* skip-worktree set, or 2) does not exist in the index but is
* outside the sparse checkout definition, add a skip-worktree bit
* to the new index entry. Note that a sparse index will be expanded
* if this entry is outside the sparse cone - this is necessary
* to properly construct the reset sparse directory.
*/
pos = cache_name_pos(one->path, strlen(one->path));
if ((pos >= 0 && ce_skip_worktree(active_cache[pos])) ||
(pos < 0 && !path_in_sparse_checkout(one->path, &the_index)))
ce->ce_flags |= CE_SKIP_WORKTREE;
if (!ce)
die(_("make_cache_entry failed for path '%s'"),
one->path);
if (is_missing) {
if (!is_in_reset_tree) {
ce->ce_flags |= CE_INTENT_TO_ADD;
set_object_name_for_intent_to_add_entry(ce);
}
@ -158,6 +174,82 @@ static void update_index_from_diff(struct diff_queue_struct *q,
}
}
static int pathspec_needs_expanded_index(const struct pathspec *pathspec)
{
unsigned int i, pos;
int res = 0;
char *skip_worktree_seen = NULL;
/*
* When using a magic pathspec, assume for the sake of simplicity that
* the index needs to be expanded to match all matchable files.
*/
if (pathspec->magic)
return 1;
for (i = 0; i < pathspec->nr; i++) {
struct pathspec_item item = pathspec->items[i];
/*
* If the pathspec item has a wildcard, the index should be expanded
* if the pathspec has the possibility of matching a subset of entries inside
* of a sparse directory (but not the entire directory).
*
* If the pathspec item is a literal path, the index only needs to be expanded
* if a) the pathspec isn't in the sparse checkout cone (to make sure we don't
* expand for in-cone files) and b) it doesn't match any sparse directories
* (since we can reset whole sparse directories without expanding them).
*/
if (item.nowildcard_len < item.len) {
/*
* Special case: if the pattern is a path inside the cone
* followed by only wildcards, the pattern cannot match
* partial sparse directories, so we don't expand the index.
*/
if (path_in_cone_mode_sparse_checkout(item.original, &the_index) &&
strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len)
continue;
for (pos = 0; pos < active_nr; pos++) {
struct cache_entry *ce = active_cache[pos];
if (!S_ISSPARSEDIR(ce->ce_mode))
continue;
/*
* If the pre-wildcard length is longer than the sparse
* directory name and the sparse directory is the first
* component of the pathspec, need to expand the index.
*/
if (item.nowildcard_len > ce_namelen(ce) &&
!strncmp(item.original, ce->name, ce_namelen(ce))) {
res = 1;
break;
}
/*
* If the pre-wildcard length is shorter than the sparse
* directory and the pathspec does not match the whole
* directory, need to expand the index.
*/
if (!strncmp(item.original, ce->name, item.nowildcard_len) &&
wildmatch(item.original, ce->name, 0)) {
res = 1;
break;
}
}
} else if (!path_in_cone_mode_sparse_checkout(item.original, &the_index) &&
!matches_skip_worktree(pathspec, i, &skip_worktree_seen))
res = 1;
if (res > 0)
break;
}
free(skip_worktree_seen);
return res;
}
static int read_from_tree(const struct pathspec *pathspec,
struct object_id *tree_oid,
int intent_to_add)
@ -170,7 +262,13 @@ static int read_from_tree(const struct pathspec *pathspec,
opt.format_callback = update_index_from_diff;
opt.format_callback_data = &intent_to_add;
opt.flags.override_submodule_config = 1;
opt.flags.recursive = 1;
opt.repo = the_repository;
opt.change = diff_change;
opt.add_remove = diff_addremove;
if (pathspec->nr && the_index.sparse_index && pathspec_needs_expanded_index(pathspec))
ensure_full_index(&the_index);
if (do_diff_cache(tree_oid, &opt))
return 1;
@ -249,9 +347,6 @@ static void parse_args(struct pathspec *pathspec,
}
*rev_ret = rev;
if (read_cache() < 0)
die(_("index file corrupt"));
parse_pathspec(pathspec, 0,
PATHSPEC_PREFER_FULL |
(patch_mode ? PATHSPEC_PREFIX_ORIGIN : 0),
@ -397,6 +492,12 @@ int cmd_reset(int argc, const char **argv, const char *prefix)
if (intent_to_add && reset_type != MIXED)
die(_("-N can only be used with --mixed"));
prepare_repo_settings(the_repository);
the_repository->settings.command_requires_full_index = 0;
if (read_cache() < 0)
die(_("index file corrupt"));
/* Soft reset does not touch the index file nor the working tree
* at all, but requires them in a good order. Other resets reset
* the index file to the tree object we are switching to. */

View File

@ -741,15 +741,26 @@ int write_index_as_tree(struct object_id *oid, struct index_state *index_state,
return ret;
}
static void prime_cache_tree_sparse_dir(struct cache_tree *it,
struct tree *tree)
{
oidcpy(&it->oid, &tree->object.oid);
it->entry_count = 1;
}
static void prime_cache_tree_rec(struct repository *r,
struct cache_tree *it,
struct tree *tree)
struct tree *tree,
struct strbuf *tree_path)
{
struct tree_desc desc;
struct name_entry entry;
int cnt;
int base_path_len = tree_path->len;
oidcpy(&it->oid, &tree->object.oid);
init_tree_desc(&desc, tree->buffer, tree->size);
cnt = 0;
while (tree_entry(&desc, &entry)) {
@ -758,14 +769,40 @@ static void prime_cache_tree_rec(struct repository *r,
else {
struct cache_tree_sub *sub;
struct tree *subtree = lookup_tree(r, &entry.oid);
if (!subtree->object.parsed)
parse_tree(subtree);
sub = cache_tree_sub(it, entry.path);
sub->cache_tree = cache_tree();
prime_cache_tree_rec(r, sub->cache_tree, subtree);
/*
* Recursively-constructed subtree path is only needed when working
* in a sparse index (where it's used to determine whether the
* subtree is a sparse directory in the index).
*/
if (r->index->sparse_index) {
strbuf_setlen(tree_path, base_path_len);
strbuf_grow(tree_path, base_path_len + entry.pathlen + 1);
strbuf_add(tree_path, entry.path, entry.pathlen);
strbuf_addch(tree_path, '/');
}
/*
* If a sparse index is in use, the directory being processed may be
* sparse. To confirm that, we can check whether an entry with that
* exact name exists in the index. If it does, the created subtree
* should be sparse. Otherwise, cache tree expansion should continue
* as normal.
*/
if (r->index->sparse_index &&
index_entry_exists(r->index, tree_path->buf, tree_path->len))
prime_cache_tree_sparse_dir(sub->cache_tree, subtree);
else
prime_cache_tree_rec(r, sub->cache_tree, subtree, tree_path);
cnt += sub->cache_tree->entry_count;
}
}
it->entry_count = cnt;
}
@ -773,11 +810,14 @@ void prime_cache_tree(struct repository *r,
struct index_state *istate,
struct tree *tree)
{
struct strbuf tree_path = STRBUF_INIT;
trace2_region_enter("cache-tree", "prime_cache_tree", the_repository);
cache_tree_free(&istate->cache_tree);
istate->cache_tree = cache_tree();
prime_cache_tree_rec(r, istate->cache_tree, tree);
prime_cache_tree_rec(r, istate->cache_tree, tree, &tree_path);
strbuf_release(&tree_path);
istate->cache_changed |= CACHE_TREE_CHANGED;
trace2_region_leave("cache-tree", "prime_cache_tree", the_repository);
}

10
cache.h
View File

@ -816,6 +816,16 @@ struct cache_entry *index_file_exists(struct index_state *istate, const char *na
*/
int index_name_pos(struct index_state *, const char *name, int namelen);
/*
* Determines whether an entry with the given name exists within the
* given index. The return value is 1 if an exact match is found, otherwise
* it is 0. Note that, unlike index_name_pos, this function does not expand
* the index if it is sparse. If an item exists within the full index but it
* is contained within a sparse directory (and not in the sparse index), 0 is
* returned.
*/
int index_entry_exists(struct index_state *, const char *name, int namelen);
/*
* Some functions return the negative complement of an insert position when a
* precise match was not found but a position was found where the entry would

View File

@ -68,6 +68,11 @@
*/
#define CACHE_ENTRY_PATH_LENGTH 80
enum index_search_mode {
NO_EXPAND_SPARSE = 0,
EXPAND_SPARSE = 1
};
static inline struct cache_entry *mem_pool__ce_alloc(struct mem_pool *mem_pool, size_t len)
{
struct cache_entry *ce;
@ -551,7 +556,10 @@ int cache_name_stage_compare(const char *name1, int len1, int stage1, const char
return 0;
}
static int index_name_stage_pos(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,
enum index_search_mode search_mode)
{
int first, last;
@ -570,7 +578,7 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in
first = next+1;
}
if (istate->sparse_index &&
if (search_mode == EXPAND_SPARSE && istate->sparse_index &&
first > 0) {
/* Note: first <= istate->cache_nr */
struct cache_entry *ce = istate->cache[first - 1];
@ -586,7 +594,7 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in
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 index_name_stage_pos(istate, name, namelen, stage, search_mode);
}
}
@ -595,7 +603,12 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in
int index_name_pos(struct index_state *istate, const char *name, int namelen)
{
return index_name_stage_pos(istate, name, namelen, 0);
return index_name_stage_pos(istate, name, namelen, 0, EXPAND_SPARSE);
}
int index_entry_exists(struct index_state *istate, const char *name, int namelen)
{
return index_name_stage_pos(istate, name, namelen, 0, NO_EXPAND_SPARSE) >= 0;
}
int remove_index_entry_at(struct index_state *istate, int pos)
@ -1237,7 +1250,7 @@ static int has_dir_name(struct index_state *istate,
*/
}
pos = index_name_stage_pos(istate, name, len, stage);
pos = index_name_stage_pos(istate, name, len, stage, EXPAND_SPARSE);
if (pos >= 0) {
/*
* Found one, but not so fast. This could
@ -1337,7 +1350,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0)
pos = index_pos_to_insert_pos(istate->cache_nr);
else
pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE);
/* existing match? Just replace it. */
if (pos >= 0) {
@ -1372,7 +1385,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
if (!ok_to_replace)
return error(_("'%s' appears as both a file and as a directory"),
ce->name);
pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE);
pos = -pos-1;
}
return pos + 1;

View File

@ -110,5 +110,8 @@ test_perf_on_all git add -A
test_perf_on_all git add .
test_perf_on_all git commit -a -m A
test_perf_on_all git checkout -f -
test_perf_on_all git reset
test_perf_on_all git reset --hard
test_perf_on_all git reset -- does-not-exist
test_done

View File

@ -489,26 +489,118 @@ test_expect_failure 'blame with pathspec outside sparse definition' '
test_all_match git blame deep/deeper2/deepest/a
'
# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
# in this scenario, but it shouldn't.
test_expect_failure 'checkout and reset (mixed)' '
test_expect_success 'checkout and reset (mixed)' '
init_repos &&
test_all_match git checkout -b reset-test update-deep &&
test_all_match git reset deepest &&
test_all_match git reset update-folder1 &&
test_all_match git reset update-folder2
# Because skip-worktree is preserved, resetting to update-folder1
# will show worktree changes for folder1/a in full-checkout, but not
# in sparse-checkout or sparse-index.
git -C full-checkout reset update-folder1 >full-checkout-out &&
test_sparse_match git reset update-folder1 &&
grep "M folder1/a" full-checkout-out &&
! grep "M folder1/a" sparse-checkout-out &&
run_on_sparse test_path_is_missing folder1
'
# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
# in this scenario, but it shouldn't.
test_expect_success 'checkout and reset (mixed) [sparse]' '
test_expect_success 'checkout and reset (merge)' '
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
write_script edit-contents <<-\EOF &&
echo text >>$1
EOF
test_all_match git checkout -b reset-test update-deep &&
run_on_all ../edit-contents a &&
test_all_match git reset --merge deepest &&
test_all_match git status --porcelain=v2 &&
test_all_match git reset --hard update-deep &&
run_on_all ../edit-contents deep/a &&
test_all_match test_must_fail git reset --merge deepest
'
test_expect_success 'checkout and reset (keep)' '
init_repos &&
write_script edit-contents <<-\EOF &&
echo text >>$1
EOF
test_all_match git checkout -b reset-test update-deep &&
run_on_all ../edit-contents a &&
test_all_match git reset --keep deepest &&
test_all_match git status --porcelain=v2 &&
test_all_match git reset --hard update-deep &&
run_on_all ../edit-contents deep/a &&
test_all_match test_must_fail git reset --keep deepest
'
test_expect_success 'reset with pathspecs inside sparse definition' '
init_repos &&
write_script edit-contents <<-\EOF &&
echo text >>$1
EOF
test_all_match git checkout -b reset-test update-deep &&
run_on_all ../edit-contents deep/a &&
test_all_match git reset base -- deep/a &&
test_all_match git status --porcelain=v2 &&
test_all_match git reset base -- nonexistent-file &&
test_all_match git status --porcelain=v2 &&
test_all_match git reset deepest -- deep &&
test_all_match git status --porcelain=v2
'
# Although the working tree differs between full and sparse checkouts after
# reset, the state of the index is the same.
test_expect_success 'reset with pathspecs outside sparse definition' '
init_repos &&
test_all_match git checkout -b reset-test base &&
test_sparse_match git reset update-folder1 -- folder1 &&
git -C full-checkout reset update-folder1 -- folder1 &&
test_sparse_match git status --porcelain=v2 &&
test_all_match git rev-parse HEAD:folder1 &&
test_sparse_match git reset update-folder2 -- folder2/a &&
git -C full-checkout reset update-folder2 -- folder2/a &&
test_sparse_match git status --porcelain=v2 &&
test_all_match git rev-parse HEAD:folder2/a
'
test_expect_success 'reset with wildcard pathspec' '
init_repos &&
test_all_match git reset update-deep -- deep\* &&
test_all_match git ls-files -s -- deep &&
test_all_match git reset deepest -- deep\*\*\* &&
test_all_match git ls-files -s -- deep &&
# The following `git reset`s result in updating the index on files with
# `skip-worktree` enabled. To avoid failing due to discrepencies in reported
# "modified" files, `test_sparse_match` reset is performed separately from
# "full-checkout" reset, then the index contents of all repos are verified.
test_sparse_match git reset update-folder1 -- \*/a &&
git -C full-checkout reset update-folder1 -- \*/a &&
test_all_match git ls-files -s -- deep/a folder1/a &&
test_sparse_match git reset update-folder2 -- folder\* &&
git -C full-checkout reset update-folder2 -- folder\* &&
test_all_match git ls-files -s -- folder10 folder1 folder2 &&
test_sparse_match git reset base -- folder1/\* &&
git -C full-checkout reset base -- folder1/\* &&
test_all_match git ls-files -s -- folder1
'
test_expect_success 'merge, cherry-pick, and rebase' '
@ -685,11 +777,15 @@ test_expect_success 'submodule handling' '
grep "160000 commit $(git -C initial-repo rev-parse HEAD) modules/sub" cache
'
# When working with a sparse index, some commands will need to expand the
# index to operate properly. If those commands also write the index back
# to disk, they need to convert the index to sparse before writing.
# This test verifies that both of these events are logged in trace2 logs.
test_expect_success 'sparse-index is expanded and converted back' '
init_repos &&
GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
git -C sparse-index -c core.fsmonitor="" reset --hard &&
git -C sparse-index reset -- folder1/a &&
test_region index convert_to_sparse trace2.txt &&
test_region index ensure_full_index trace2.txt
'
@ -757,9 +853,9 @@ test_expect_success 'sparse-index is not expanded' '
ensure_not_expanded checkout - &&
ensure_not_expanded switch rename-out-to-out &&
ensure_not_expanded switch - &&
git -C sparse-index reset --hard &&
ensure_not_expanded reset --hard &&
ensure_not_expanded checkout rename-out-to-out -- deep/deeper1 &&
git -C sparse-index reset --hard &&
ensure_not_expanded reset --hard &&
ensure_not_expanded restore -s rename-out-to-out -- deep/deeper1 &&
echo >>sparse-index/README.md &&
@ -769,6 +865,34 @@ test_expect_success 'sparse-index is not expanded' '
echo >>sparse-index/untracked.txt &&
ensure_not_expanded add . &&
for ref in update-deep update-folder1 update-folder2 update-deep
do
echo >>sparse-index/README.md &&
ensure_not_expanded reset --hard $ref || return 1
done &&
ensure_not_expanded reset --mixed base &&
ensure_not_expanded reset --hard update-deep &&
ensure_not_expanded reset --keep base &&
ensure_not_expanded reset --merge update-deep &&
ensure_not_expanded reset --hard &&
ensure_not_expanded reset base -- deep/a &&
ensure_not_expanded reset base -- nonexistent-file &&
ensure_not_expanded reset deepest -- deep &&
# Although folder1 is outside the sparse definition, it exists as a
# directory entry in the index, so the pathspec will not force the
# index to be expanded.
ensure_not_expanded reset deepest -- folder1 &&
ensure_not_expanded reset deepest -- folder1/ &&
# Wildcard identifies only in-cone files, no index expansion
ensure_not_expanded reset deepest -- deep/\* &&
# Wildcard identifies only full sparse directories, no index expansion
ensure_not_expanded reset deepest -- folder\* &&
ensure_not_expanded checkout -f update-deep &&
test_config -C sparse-index pull.twohead ort &&
(

View File

@ -472,6 +472,23 @@ test_expect_success '--mixed refreshes the index' '
test_cmp expect output
'
test_expect_success '--mixed preserves skip-worktree' '
echo 123 >>file2 &&
git add file2 &&
git update-index --skip-worktree file2 &&
git reset --mixed HEAD >output &&
test_must_be_empty output &&
cat >expect <<-\EOF &&
Unstaged changes after reset:
M file2
EOF
git update-index --no-skip-worktree file2 &&
git add file2 &&
git reset --mixed HEAD >output &&
test_cmp expect output
'
test_expect_success 'resetting specific path that is unmerged' '
git rm --cached file2 &&
F1=$(git rev-parse HEAD:file1) &&

View File

@ -645,17 +645,24 @@ static void mark_ce_used_same_name(struct cache_entry *ce,
}
}
static struct cache_entry *next_cache_entry(struct unpack_trees_options *o)
static struct cache_entry *next_cache_entry(struct unpack_trees_options *o, int *hint)
{
const struct index_state *index = o->src_index;
int pos = o->cache_bottom;
if (*hint > pos)
pos = *hint;
while (pos < index->cache_nr) {
struct cache_entry *ce = index->cache[pos];
if (!(ce->ce_flags & CE_UNPACKED))
if (!(ce->ce_flags & CE_UNPACKED)) {
*hint = pos + 1;
return ce;
}
pos++;
}
*hint = pos;
return NULL;
}
@ -1365,12 +1372,13 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str
/* Are we supposed to look at the index too? */
if (o->merge) {
int hint = -1;
while (1) {
int cmp;
struct cache_entry *ce;
if (o->diff_index_cached)
ce = next_cache_entry(o);
ce = next_cache_entry(o, &hint);
else
ce = find_cache_entry(info, p);
@ -1690,7 +1698,7 @@ 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;
int i, hint, ret;
static struct cache_entry *dfc;
struct pattern_list pl;
int free_pattern_list = 0;
@ -1779,13 +1787,15 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
info.pathspec = o->pathspec;
if (o->prefix) {
hint = -1;
/*
* Unpack existing index entries that sort before the
* prefix the tree is spliced into. Note that o->merge
* is always true in this case.
*/
while (1) {
struct cache_entry *ce = next_cache_entry(o);
struct cache_entry *ce = next_cache_entry(o, &hint);
if (!ce)
break;
if (ce_in_traverse_path(ce, &info))
@ -1806,8 +1816,9 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
/* Any left-over entries in the index? */
if (o->merge) {
hint = -1;
while (1) {
struct cache_entry *ce = next_cache_entry(o);
struct cache_entry *ce = next_cache_entry(o, &hint);
if (!ce)
break;
if (unpack_index_entry(ce, o) < 0)