2021-03-30 13:10:47 +00:00
|
|
|
#include "cache.h"
|
|
|
|
#include "repository.h"
|
|
|
|
#include "sparse-index.h"
|
2021-03-30 13:10:48 +00:00
|
|
|
#include "tree.h"
|
|
|
|
#include "pathspec.h"
|
|
|
|
#include "trace2.h"
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
#include "cache-tree.h"
|
|
|
|
#include "config.h"
|
|
|
|
#include "dir.h"
|
|
|
|
#include "fsmonitor.h"
|
|
|
|
|
2022-05-23 13:48:43 +00:00
|
|
|
struct modify_index_context {
|
|
|
|
struct index_state *write;
|
|
|
|
struct pattern_list *pl;
|
|
|
|
};
|
|
|
|
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
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;
|
|
|
|
struct strbuf child_path = STRBUF_INIT;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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).
|
|
|
|
*/
|
2021-09-08 01:42:30 +00:00
|
|
|
if (path_in_sparse_checkout(ct_path, istate))
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
can_convert = 0;
|
|
|
|
|
|
|
|
for (i = start; can_convert && i < end; i++) {
|
|
|
|
struct cache_entry *ce = istate->cache[i];
|
|
|
|
|
|
|
|
if (ce_stage(ce) ||
|
2021-03-30 13:10:56 +00:00
|
|
|
S_ISGITLINK(ce->ce_mode) ||
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
!(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;
|
|
|
|
}
|
|
|
|
|
2021-05-05 12:11:58 +00:00
|
|
|
int set_sparse_index_config(struct repository *repo, int enable)
|
2021-03-30 13:10:59 +00:00
|
|
|
{
|
sparse-checkout: set worktree-config correctly
`git sparse-checkout set/init` enables worktree-specific
configuration[*] by setting extensions.worktreeConfig=true, but neglects
to perform the additional necessary bookkeeping of relocating
`core.bare=true` and `core.worktree` from $GIT_COMMON_DIR/config to
$GIT_COMMON_DIR/config.worktree, as documented in git-worktree.txt. As a
result of this oversight, these settings, which are nonsensical for
secondary worktrees, can cause Git commands to incorrectly consider a
worktree bare (in the case of `core.bare`) or operate on the wrong
worktree (in the case of `core.worktree`). Fix this problem by taking
advantage of the recently-added init_worktree_config() which enables
`extensions.worktreeConfig` and takes care of necessary bookkeeping.
While at it, for backward-compatibility reasons, also stop upgrading the
repository format to "1" since doing so is (unintentionally) not
required to take advantage of `extensions.worktreeConfig`, as explained
by 11664196ac ("Revert "check_repository_format_gently(): refuse
extensions for old repositories"", 2020-07-15).
[*] The main reason to use worktree-specific config for the
sparse-checkout builtin was to avoid enabling sparse-checkout patterns
in one and causing a loss of files in another. If a worktree does not
have a sparse-checkout patterns file, then the sparse-checkout logic
will not kick in on that worktree.
Reported-by: Sean Allred <allred.sean@gmail.com>
Helped-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-02-07 21:33:01 +00:00
|
|
|
int res = repo_config_set_worktree_gently(repo,
|
|
|
|
"index.sparse",
|
|
|
|
enable ? "true" : "false");
|
2021-03-30 13:11:00 +00:00
|
|
|
prepare_repo_settings(repo);
|
|
|
|
repo->settings.sparse_index = enable;
|
|
|
|
return res;
|
2021-03-30 13:10:59 +00:00
|
|
|
}
|
|
|
|
|
sparse-index: skip indexes with unmerged entries
The sparse-index format is designed to be compatible with merge
conflicts, even those outside the sparse-checkout definition. The reason
is that when converting a full index to a sparse one, a cache entry with
nonzero stage will not be collapsed into a sparse directory entry.
However, this behavior was not tested, and a different behavior within
convert_to_sparse() fails in this scenario. Specifically,
cache_tree_update() will fail when unmerged entries exist.
convert_to_sparse_rec() uses the cache-tree data to recursively walk the
tree structure, but also to compute the OIDs used in the
sparse-directory entries.
Add an index scan to convert_to_sparse() that will detect if these merge
conflict entries exist and skip the conversion before trying to update
the cache-tree. This is marked as NEEDSWORK because this can be removed
with a suitable update to cache_tree_update() or a similar method that
can construct a cache-tree with invalid nodes, but still allow creating
the nodes necessary for creating sparse directory entries.
It is possible that in the future we will not need to make such an
update, since if we do not expand a sparse-index into a full one, this
conversion does not need to happen. Thus, this can be deferred until the
merge machinery is made to integrate with the sparse-index.
Reviewed-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-14 13:12:25 +00:00
|
|
|
static int index_has_unmerged_entries(struct index_state *istate)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
for (i = 0; i < istate->cache_nr; i++) {
|
|
|
|
if (ce_stage(istate->cache[i]))
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-05-10 23:32:29 +00:00
|
|
|
int is_sparse_index_allowed(struct index_state *istate, int flags)
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
{
|
2021-11-23 00:20:32 +00:00
|
|
|
if (!core_apply_sparse_checkout || !core_sparse_checkout_cone)
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
return 0;
|
|
|
|
|
2021-09-08 01:42:32 +00:00
|
|
|
if (!(flags & SPARSE_INDEX_MEMORY_ONLY)) {
|
2021-11-23 00:20:32 +00:00
|
|
|
int test_env;
|
|
|
|
|
2021-09-08 01:42:32 +00:00
|
|
|
/*
|
|
|
|
* The sparse index is not (yet) integrated with a split index.
|
|
|
|
*/
|
2022-01-19 17:29:37 +00:00
|
|
|
if (istate->split_index || git_env_bool("GIT_TEST_SPLIT_INDEX", 0))
|
2021-09-08 01:42:32 +00:00
|
|
|
return 0;
|
|
|
|
/*
|
|
|
|
* 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);
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
|
2021-09-08 01:42:32 +00:00
|
|
|
/*
|
|
|
|
* Only convert to sparse if index.sparse is set.
|
|
|
|
*/
|
|
|
|
prepare_repo_settings(istate->repo);
|
|
|
|
if (!istate->repo->settings.sparse_index)
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2021-09-08 01:42:30 +00:00
|
|
|
if (init_sparse_checkout_patterns(istate))
|
|
|
|
return 0;
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
|
2021-09-08 01:42:26 +00:00
|
|
|
/*
|
|
|
|
* We need cone-mode patterns to use sparse-index. If a user edits
|
|
|
|
* their sparse-checkout file manually, then we can detect during
|
|
|
|
* parsing that they are not actually using cone-mode patterns and
|
|
|
|
* hence we need to abort this conversion _without error_. Warnings
|
|
|
|
* already exist in the pattern parsing to inform the user of their
|
|
|
|
* bad patterns.
|
|
|
|
*/
|
|
|
|
if (!istate->sparse_checkout_patterns->use_cone_patterns)
|
|
|
|
return 0;
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
|
2021-11-23 00:20:32 +00:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
int convert_to_sparse(struct index_state *istate, int flags)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* If the index is already sparse, empty, or otherwise
|
|
|
|
* cannot be converted to sparse, do not convert.
|
|
|
|
*/
|
2022-05-23 13:48:40 +00:00
|
|
|
if (istate->sparse_index == INDEX_COLLAPSED || !istate->cache_nr ||
|
2021-11-23 00:20:32 +00:00
|
|
|
!is_sparse_index_allowed(istate, flags))
|
|
|
|
return 0;
|
|
|
|
|
sparse-index: skip indexes with unmerged entries
The sparse-index format is designed to be compatible with merge
conflicts, even those outside the sparse-checkout definition. The reason
is that when converting a full index to a sparse one, a cache entry with
nonzero stage will not be collapsed into a sparse directory entry.
However, this behavior was not tested, and a different behavior within
convert_to_sparse() fails in this scenario. Specifically,
cache_tree_update() will fail when unmerged entries exist.
convert_to_sparse_rec() uses the cache-tree data to recursively walk the
tree structure, but also to compute the OIDs used in the
sparse-directory entries.
Add an index scan to convert_to_sparse() that will detect if these merge
conflict entries exist and skip the conversion before trying to update
the cache-tree. This is marked as NEEDSWORK because this can be removed
with a suitable update to cache_tree_update() or a similar method that
can construct a cache-tree with invalid nodes, but still allow creating
the nodes necessary for creating sparse directory entries.
It is possible that in the future we will not need to make such an
update, since if we do not expand a sparse-index into a full one, this
conversion does not need to happen. Thus, this can be deferred until the
merge machinery is made to integrate with the sparse-index.
Reviewed-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-07-14 13:12:25 +00:00
|
|
|
/*
|
|
|
|
* NEEDSWORK: If we have unmerged entries, then stay full.
|
|
|
|
* Unmerged entries prevent the cache-tree extension from working.
|
|
|
|
*/
|
|
|
|
if (index_has_unmerged_entries(istate))
|
|
|
|
return 0;
|
|
|
|
|
2021-11-23 00:20:31 +00:00
|
|
|
if (!cache_tree_fully_valid(istate->cache_tree)) {
|
|
|
|
/* Clear and recompute the cache-tree */
|
|
|
|
cache_tree_free(&istate->cache_tree);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Silently return if there is a problem with the cache tree update,
|
|
|
|
* which might just be due to a conflict state in some entry.
|
|
|
|
*
|
|
|
|
* This might create new tree objects, so be sure to use
|
|
|
|
* WRITE_TREE_MISSING_OK.
|
|
|
|
*/
|
|
|
|
if (cache_tree_update(istate, WRITE_TREE_MISSING_OK))
|
|
|
|
return 0;
|
|
|
|
}
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
|
|
|
|
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);
|
2021-03-30 13:11:02 +00:00
|
|
|
|
|
|
|
/* Clear and recompute the cache-tree */
|
|
|
|
cache_tree_free(&istate->cache_tree);
|
|
|
|
cache_tree_update(istate, 0);
|
|
|
|
|
2021-07-14 13:12:39 +00:00
|
|
|
istate->fsmonitor_has_run_once = 0;
|
|
|
|
FREE_AND_NULL(istate->fsmonitor_dirty);
|
|
|
|
FREE_AND_NULL(istate->fsmonitor_last_update);
|
|
|
|
|
2022-05-23 13:48:40 +00:00
|
|
|
istate->sparse_index = INDEX_COLLAPSED;
|
sparse-index: convert from full to sparse
If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.
For now, we avoid converting the index to a sparse index if:
1. the index is split.
2. the index is already sparse.
3. sparse-checkout is disabled.
4. sparse-checkout does not use cone mode.
Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.
The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.
The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.
Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."
We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.
The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-03-30 13:10:55 +00:00
|
|
|
trace2_region_leave("index", "convert_to_sparse", istate->repo);
|
|
|
|
return 0;
|
|
|
|
}
|
2021-03-30 13:10:48 +00:00
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
2022-05-23 13:48:43 +00:00
|
|
|
struct modify_index_context *ctx = (struct modify_index_context *)context;
|
2021-03-30 13:10:48 +00:00
|
|
|
struct cache_entry *ce;
|
|
|
|
size_t len = base->len;
|
|
|
|
|
2022-05-23 13:48:43 +00:00
|
|
|
if (S_ISDIR(mode)) {
|
|
|
|
int dtype;
|
|
|
|
size_t baselen = base->len;
|
|
|
|
if (!ctx->pl)
|
|
|
|
return READ_TREE_RECURSIVE;
|
2021-03-30 13:10:48 +00:00
|
|
|
|
2022-05-23 13:48:43 +00:00
|
|
|
/*
|
|
|
|
* Have we expanded to a point outside of the sparse-checkout?
|
|
|
|
*
|
|
|
|
* Artificially pad the path name with a slash "/" to
|
|
|
|
* indicate it as a directory, and add an arbitrary file
|
|
|
|
* name ("-") so we can consider base->buf as a file name
|
|
|
|
* to match against the cone-mode patterns.
|
|
|
|
*
|
|
|
|
* If we compared just "path", then we would expand more
|
|
|
|
* than we should. Since every file at root is always
|
|
|
|
* included, we would expand every directory at root at
|
|
|
|
* least one level deep instead of using sparse directory
|
|
|
|
* entries.
|
|
|
|
*/
|
|
|
|
strbuf_addstr(base, path);
|
|
|
|
strbuf_add(base, "/-", 2);
|
|
|
|
|
|
|
|
if (path_matches_pattern_list(base->buf, base->len,
|
|
|
|
NULL, &dtype,
|
|
|
|
ctx->pl, ctx->write)) {
|
|
|
|
strbuf_setlen(base, baselen);
|
|
|
|
return READ_TREE_RECURSIVE;
|
|
|
|
}
|
2021-03-30 13:10:48 +00:00
|
|
|
|
2022-05-23 13:48:43 +00:00
|
|
|
/*
|
|
|
|
* The path "{base}{path}/" is a sparse directory. Create the correct
|
|
|
|
* name for inserting the entry into the index.
|
|
|
|
*/
|
|
|
|
strbuf_setlen(base, base->len - 1);
|
|
|
|
} else {
|
|
|
|
strbuf_addstr(base, path);
|
|
|
|
}
|
2021-03-30 13:10:48 +00:00
|
|
|
|
2022-05-23 13:48:43 +00:00
|
|
|
ce = make_cache_entry(ctx->write, mode, oid, base->buf, 0, 0);
|
2021-07-14 13:12:26 +00:00
|
|
|
ce->ce_flags |= CE_SKIP_WORKTREE | CE_EXTENDED;
|
2022-05-23 13:48:43 +00:00
|
|
|
set_index_entry(ctx->write, ctx->write->cache_nr++, ce);
|
2021-03-30 13:10:48 +00:00
|
|
|
|
|
|
|
strbuf_setlen(base, len);
|
|
|
|
return 0;
|
|
|
|
}
|
2021-03-30 13:10:47 +00:00
|
|
|
|
2022-05-23 13:48:39 +00:00
|
|
|
void expand_index(struct index_state *istate, struct pattern_list *pl)
|
2021-03-30 13:10:47 +00:00
|
|
|
{
|
2021-03-30 13:10:48 +00:00
|
|
|
int i;
|
|
|
|
struct index_state *full;
|
|
|
|
struct strbuf base = STRBUF_INIT;
|
2022-05-23 13:48:39 +00:00
|
|
|
const char *tr_region;
|
2022-05-23 13:48:43 +00:00
|
|
|
struct modify_index_context ctx;
|
2021-03-30 13:10:48 +00:00
|
|
|
|
2022-05-23 13:48:39 +00:00
|
|
|
/*
|
|
|
|
* If the index is already full, then keep it full. We will convert
|
|
|
|
* it to a sparse index on write, if possible.
|
|
|
|
*/
|
2023-01-12 12:55:25 +00:00
|
|
|
if (istate->sparse_index == INDEX_EXPANDED)
|
2021-03-30 13:10:48 +00:00
|
|
|
return;
|
|
|
|
|
2022-05-23 13:48:39 +00:00
|
|
|
/*
|
|
|
|
* If our index is sparse, but our new pattern set does not use
|
|
|
|
* cone mode patterns, then we need to expand the index before we
|
|
|
|
* continue. A NULL pattern set indicates a full expansion to a
|
|
|
|
* full index.
|
|
|
|
*/
|
2022-05-23 13:48:44 +00:00
|
|
|
if (pl && !pl->use_cone_patterns) {
|
2022-05-23 13:48:39 +00:00
|
|
|
pl = NULL;
|
2022-05-23 13:48:44 +00:00
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* We might contract file entries into sparse-directory
|
|
|
|
* entries, and for that we will need the cache tree to
|
|
|
|
* be recomputed.
|
|
|
|
*/
|
|
|
|
cache_tree_free(&istate->cache_tree);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If there is a problem creating the cache tree, then we
|
|
|
|
* need to expand to a full index since we cannot satisfy
|
|
|
|
* the current request as a sparse index.
|
|
|
|
*/
|
|
|
|
if (cache_tree_update(istate, 0))
|
|
|
|
pl = NULL;
|
|
|
|
}
|
2022-05-23 13:48:39 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* A NULL pattern set indicates we are expanding a full index, so
|
|
|
|
* we use a special region name that indicates the full expansion.
|
|
|
|
* This is used by test cases, but also helps to differentiate the
|
|
|
|
* two cases.
|
|
|
|
*/
|
|
|
|
tr_region = pl ? "expand_index" : "ensure_full_index";
|
|
|
|
trace2_region_enter("index", tr_region, istate->repo);
|
2021-03-30 13:10:48 +00:00
|
|
|
|
|
|
|
/* initialize basics of new index */
|
|
|
|
full = xcalloc(1, sizeof(struct index_state));
|
|
|
|
memcpy(full, istate, sizeof(struct index_state));
|
|
|
|
|
2022-05-23 13:48:44 +00:00
|
|
|
/*
|
|
|
|
* This slightly-misnamed 'full' index might still be sparse if we
|
|
|
|
* are only modifying the list of sparse directories. This hinges
|
|
|
|
* on whether we have a non-NULL pattern list.
|
|
|
|
*/
|
|
|
|
full->sparse_index = pl ? INDEX_PARTIALLY_SPARSE : INDEX_EXPANDED;
|
|
|
|
|
2021-03-30 13:10:48 +00:00
|
|
|
/* then change the necessary things */
|
|
|
|
full->cache_alloc = (3 * istate->cache_alloc) / 2;
|
|
|
|
full->cache_nr = 0;
|
|
|
|
ALLOC_ARRAY(full->cache, full->cache_alloc);
|
|
|
|
|
2022-05-23 13:48:43 +00:00
|
|
|
ctx.write = full;
|
|
|
|
ctx.pl = pl;
|
|
|
|
|
2021-03-30 13:10:48 +00:00
|
|
|
for (i = 0; i < istate->cache_nr; i++) {
|
|
|
|
struct cache_entry *ce = istate->cache[i];
|
|
|
|
struct tree *tree;
|
|
|
|
struct pathspec ps;
|
2022-05-23 13:48:44 +00:00
|
|
|
int dtype;
|
2021-03-30 13:10:48 +00:00
|
|
|
|
|
|
|
if (!S_ISSPARSEDIR(ce->ce_mode)) {
|
|
|
|
set_index_entry(full, full->cache_nr++, ce);
|
|
|
|
continue;
|
|
|
|
}
|
2022-05-23 13:48:44 +00:00
|
|
|
|
|
|
|
/* We now have a sparse directory entry. Should we expand? */
|
|
|
|
if (pl &&
|
|
|
|
path_matches_pattern_list(ce->name, ce->ce_namelen,
|
|
|
|
NULL, &dtype,
|
|
|
|
pl, istate) == NOT_MATCHED) {
|
|
|
|
set_index_entry(full, full->cache_nr++, ce);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2021-03-30 13:10:48 +00:00
|
|
|
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,
|
2022-05-23 13:48:43 +00:00
|
|
|
add_path_to_index, &ctx);
|
2021-03-30 13:10:48 +00:00
|
|
|
|
|
|
|
/* 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));
|
2021-08-16 17:48:55 +00:00
|
|
|
memcpy(&istate->dir_hash, &full->dir_hash, sizeof(full->dir_hash));
|
2022-05-23 13:48:44 +00:00
|
|
|
istate->sparse_index = pl ? INDEX_PARTIALLY_SPARSE : INDEX_EXPANDED;
|
2021-03-30 13:10:48 +00:00
|
|
|
free(istate->cache);
|
|
|
|
istate->cache = full->cache;
|
|
|
|
istate->cache_nr = full->cache_nr;
|
|
|
|
istate->cache_alloc = full->cache_alloc;
|
2021-07-14 13:12:39 +00:00
|
|
|
istate->fsmonitor_has_run_once = 0;
|
|
|
|
FREE_AND_NULL(istate->fsmonitor_dirty);
|
|
|
|
FREE_AND_NULL(istate->fsmonitor_last_update);
|
2021-03-30 13:10:48 +00:00
|
|
|
|
|
|
|
strbuf_release(&base);
|
|
|
|
free(full);
|
|
|
|
|
2021-03-30 13:11:02 +00:00
|
|
|
/* Clear and recompute the cache-tree */
|
|
|
|
cache_tree_free(&istate->cache_tree);
|
|
|
|
cache_tree_update(istate, 0);
|
|
|
|
|
2022-05-23 13:48:39 +00:00
|
|
|
trace2_region_leave("index", tr_region, istate->repo);
|
|
|
|
}
|
|
|
|
|
|
|
|
void ensure_full_index(struct index_state *istate)
|
|
|
|
{
|
2023-01-12 12:55:25 +00:00
|
|
|
if (!istate)
|
|
|
|
BUG("ensure_full_index() must get an index!");
|
2022-05-23 13:48:39 +00:00
|
|
|
expand_index(istate, NULL);
|
2021-03-30 13:10:47 +00:00
|
|
|
}
|
sparse-index: expand_to_path()
Some users of the index API have a specific path they are looking for,
but choose to use index_file_exists() to rely on the name-hash hashtable
instead of doing binary search with index_name_pos(). These users only
need to know a yes/no answer, not a position within the cache array.
When the index is sparse, the name-hash hash table does not contain the
full list of paths within sparse directories. It _does_ contain the
directory names for the sparse-directory entries.
Create a helper function, expand_to_path(), for intended use with the
name-hash hashtable functions. The integration with name-hash.c will
follow in a later change.
The solution here is to use ensure_full_index() when we determine that
the requested path is within a sparse directory entry. This will
populate the name-hash hashtable as the index is recomputed from
scratch.
There may be cases where the caller is trying to find an untracked path
that is not in the index but also is not within a sparse directory
entry. We want to minimize the overhead for these requests. If we used
index_name_pos() to find the insertion order of the path, then we could
determine from that position if a sparse-directory exists. (In fact,
just calling index_name_pos() in that case would lead to expanding the
index to a full index.) However, this takes O(log N) time where N is the
number of cache entries.
To keep the performance of this call based mostly on the input string,
use index_file_exists() to look for the ancestors of the path. Using the
heuristic that a sparse directory is likely to have a small number of
parent directories, we start from the bottom and build up. Use a string
buffer to allow mutating the path name to terminate after each slash for
each hashset test.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-12 21:08:16 +00:00
|
|
|
|
2021-11-23 00:20:32 +00:00
|
|
|
void ensure_correct_sparsity(struct index_state *istate)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* If the index can be sparse, make it sparse. Otherwise,
|
|
|
|
* ensure the index is full.
|
|
|
|
*/
|
|
|
|
if (is_sparse_index_allowed(istate, 0))
|
|
|
|
convert_to_sparse(istate, 0);
|
|
|
|
else
|
|
|
|
ensure_full_index(istate);
|
|
|
|
}
|
|
|
|
|
Accelerate clear_skip_worktree_from_present_files() by caching
Trying to clear the skip-worktree bit from files that are present does
present some computational overhead, for sparse-checkouts. (We do not
do the bit clearing in non-sparse-checkouts.) Optimize it as follows:
Rather than lstat()'ing every SKIP_WORKTREE path, take advantage of the
fact that entire directories will often be missing, especially for cone
mode and even more so ever since commit 55dfcf9591 ("sparse-checkout:
clear tracked sparse dirs", 2021-09-08). If we have already determined
that the parent directory of a file (or other previous ancestor) does
not exist, then the file cannot exist either so we do not need to
lstat() it separately.
Timings for p2000 included below, reformatted to fit in normal commit
message line lengths, which compare three things:
* Timings before this series
* Timings of the unoptimized version of
clear_skip_worktree_from_present_files() from a few commits ago
* Timings after the optimization in this commit
(NOTE: t/perf/ appears to have timing resolution only down to 0.01 s,
which presents significant measurement error when timings only differ by
0.01s. I don't trust any such timings below, and yet all the optimized
results differ by at most 0.01s.)
Test Before Series Unoptimized Optimized
-----------------------------------------------------------------------------
*git status*
full-v3 0.15(0.10+0.06) 0.32(0.16+0.17) +113.3% 0.16(0.10+0.07) +6.7%
full-v4 0.15(0.11+0.05) 0.32(0.17+0.16) +113.3% 0.16(0.11+0.05) +6.7%
sparse-v3 0.04(0.03+0.04) 0.04(0.02+0.05) +0.0% 0.04(0.02+0.05) +0.0%
sparse-v4 0.04(0.03+0.04) 0.04(0.02+0.05) +0.0% 0.04(0.03+0.05) +0.0%
*git add -A*
full-v3 0.40(0.30+0.07) 0.56(0.36+0.17) +40.0% 0.39(0.30+0.07) -2.5%
full-v4 0.37(0.28+0.07) 0.54(0.37+0.16) +45.9% 0.38(0.29+0.07) +2.7%
sparse-v3 0.06(0.04+0.05) 0.08(0.05+0.05) +33.3% 0.06(0.05+0.04) +0.0%
sparse-v4 0.05(0.03+0.05) 0.05(0.04+0.04) +0.0% 0.06(0.04+0.05) +20.0%
*git add .*
full-v3 0.40(0.31+0.07) 0.57(0.37+0.17) +42.5% 0.41(0.30+0.08) +2.5%
full-v4 0.38(0.30+0.06) 0.55(0.37+0.16) +44.7% 0.38(0.30+0.06) +0.0%
sparse-v3 0.06(0.04+0.05) 0.06(0.05+0.04) +0.0% 0.06(0.03+0.05) +0.0%
sparse-v4 0.06(0.05+0.05) 0.06(0.04+0.05) +0.0% 0.06(0.04+0.06) +0.0%
*git commit -a -m A*
full-v3 0.41(0.32+0.06) 0.58(0.39+0.17) +41.5% 0.42(0.32+0.07) +2.4%
full-v4 0.39(0.30+0.07) 0.56(0.38+0.17) +43.6% 0.40(0.31+0.07) +2.6%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.04(0.03+0.05) 0.04(0.03+0.05) +0.0% 0.04(0.03+0.04) +0.0%
*git checkout -f -*
full-v3 0.56(0.46+0.07) 0.73(0.55+0.16) +30.4% 0.57(0.47+0.08) +1.8%
full-v4 0.54(0.45+0.07) 0.71(0.53+0.17) +31.5% 0.55(0.45+0.07) +1.9%
sparse-v3 0.06(0.04+0.04) 0.06(0.04+0.05) +0.0% 0.06(0.04+0.05) +0.0%
sparse-v4 0.05(0.05+0.04) 0.05(0.04+0.05) +0.0% 0.06(0.04+0.05) +20.0%
*git reset*
full-v3 0.34(0.26+0.05) 0.51(0.34+0.15) +50.0% 0.34(0.26+0.06) +0.0%
full-v4 0.32(0.24+0.06) 0.49(0.32+0.15) +53.1% 0.33(0.25+0.06) +3.1%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.03(0.03+0.04) 0.03(0.02+0.04) +0.0% 0.03(0.03+0.04) +0.0%
*git reset --hard*
full-v3 0.57(0.46+0.07) 0.90(0.61+0.25) +57.9% 0.57(0.45+0.08) +0.0%
full-v4 0.54(0.46+0.05) 0.88(0.59+0.26) +63.0% 0.55(0.45+0.07) +1.9%
sparse-v3 0.07(0.03+0.03) 0.07(0.04+0.03) +0.0% 0.07(0.03+0.03) +0.0%
sparse-v4 0.06(0.03+0.03) 0.06(0.04+0.02) +0.0% 0.06(0.03+0.03) +0.0%
*git reset -- does-not-exist*
full-v3 0.35(0.27+0.06) 0.52(0.32+0.17) +48.6% 0.35(0.27+0.06) +0.0%
full-v4 0.33(0.26+0.05) 0.50(0.33+0.15) +51.5% 0.33(0.26+0.06) +0.0%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.04(0.02+0.04) 0.03(0.02+0.04) -25.0% 0.03(0.02+0.04) -25.0%
*git diff*
full-v3 0.07(0.04+0.04) 0.24(0.11+0.14) +242.9% 0.07(0.04+0.04) +0.0%
full-v4 0.07(0.03+0.05) 0.24(0.13+0.12) +242.9% 0.08(0.04+0.05) +14.3%
sparse-v3 0.02(0.01+0.04) 0.02(0.01+0.04) +0.0% 0.02(0.01+0.05) +0.0%
sparse-v4 0.02(0.02+0.03) 0.02(0.01+0.04) +0.0% 0.02(0.01+0.04) +0.0%
*git diff --cached*
full-v3 0.05(0.03+0.02) 0.22(0.12+0.09) +340.0% 0.05(0.03+0.01) +0.0%
full-v4 0.05(0.03+0.01) 0.23(0.12+0.11) +360.0% 0.05(0.03+0.02) +0.0%
sparse-v3 0.01(0.00+0.00) 0.01(0.00+0.00) +0.0% 0.01(0.00+0.00) +0.0%
sparse-v4 0.01(0.00+0.00) 0.01(0.00+0.00) +0.0% 0.01(0.00+0.00) +0.0%
*git blame f2/f4/a*
full-v3 0.18(0.13+0.05) 0.52(0.29+0.23) +188.9% 0.19(0.15+0.04) +5.6%
full-v4 0.19(0.15+0.04) 0.52(0.28+0.23) +173.7% 0.19(0.14+0.04) +0.0%
sparse-v3 0.10(0.08+0.02) 0.10(0.09+0.01) +0.0% 0.10(0.09+0.01) +0.0%
sparse-v4 0.10(0.08+0.02) 0.10(0.08+0.02) +0.0% 0.10(0.08+0.02) +0.0%
*git blame f2/f4/f3/a*
full-v3 0.45(0.36+0.08) 0.78(0.51+0.27) +73.3% 0.45(0.37+0.08) +0.0%
full-v4 0.45(0.37+0.08) 0.78(0.51+0.26) +73.3% 0.45(0.37+0.08) +0.0%
sparse-v3 0.36(0.32+0.04) 0.36(0.31+0.05) +0.0% 0.36(0.31+0.04) +0.0%
sparse-v4 0.36(0.31+0.05) 0.36(0.31+0.05) +0.0% 0.36(0.31+0.04) +0.0%
*git checkout-index -f --all*
full-v3 0.07(0.02+0.05) 0.24(0.12+0.12) +242.9% 0.08(0.04+0.04) +14.3%
full-v4 0.07(0.03+0.04) 0.24(0.11+0.13) +242.9% 0.08(0.03+0.04) +14.3%
sparse-v3 0.04(0.01+0.03) 0.04(0.00+0.03) +0.0% 0.04(0.01+0.03) +0.0%
sparse-v4 0.04(0.01+0.02) 0.04(0.01+0.03) +0.0% 0.04(0.01+0.02) +0.0%
*git update-index --add --remove f2/f4/a*
full-v3 0.29(0.23+0.02) 0.46(0.30+0.12) +58.6% 0.30(0.24+0.02) +3.4%
full-v4 0.27(0.22+0.02) 0.45(0.29+0.12) +66.7% 0.28(0.22+0.03) +3.7%
sparse-v3 0.02(0.02+0.00) 0.02(0.01+0.00) +0.0% 0.02(0.01+0.00) +0.0%
sparse-v4 0.02(0.02+0.00) 0.02(0.02+0.00) +0.0% 0.02(0.02+0.00) +0.0%
So, with the optimization, the extra work appears to be essentially 0
for sparse-checkouts that are also using sparse-indexes (even before my
optimization), and the extra work appears to be just marginally more
than 0 for sparse-checkouts that are using full indexes.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:43 +00:00
|
|
|
static int path_found(const char *path, const char **dirname, size_t *dir_len,
|
|
|
|
int *dir_found)
|
|
|
|
{
|
|
|
|
struct stat st;
|
|
|
|
char *newdir;
|
|
|
|
char *tmp;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If dirname corresponds to a directory that doesn't exist, and this
|
|
|
|
* path starts with dirname, then path can't exist.
|
|
|
|
*/
|
|
|
|
if (!*dir_found && !memcmp(path, *dirname, *dir_len))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If path itself exists, return 1.
|
|
|
|
*/
|
|
|
|
if (!lstat(path, &st))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Otherwise, path does not exist so we'll return 0...but we'll first
|
|
|
|
* determine some info about its parent directory so we can avoid
|
|
|
|
* lstat calls for future cache entries.
|
|
|
|
*/
|
|
|
|
newdir = strrchr(path, '/');
|
|
|
|
if (!newdir)
|
|
|
|
return 0; /* Didn't find a parent dir; just return 0 now. */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If path starts with directory (which we already lstat'ed and found),
|
|
|
|
* then no need to lstat parent directory again.
|
|
|
|
*/
|
|
|
|
if (*dir_found && *dirname && memcmp(path, *dirname, *dir_len))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Free previous dirname, and cache path's dirname */
|
|
|
|
*dirname = path;
|
|
|
|
*dir_len = newdir - path + 1;
|
|
|
|
|
|
|
|
tmp = xstrndup(path, *dir_len);
|
|
|
|
*dir_found = !lstat(tmp, &st);
|
|
|
|
free(tmp);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
repo_read_index: clear SKIP_WORKTREE bit from files present in worktree
The fix is short (~30 lines), but the description is not. Sorry.
There is a set of problems caused by files in what I'll refer to as the
"present-despite-SKIP_WORKTREE" state. This commit aims to not just fix
these problems, but remove the entire class as a possibility -- for
those using sparse checkouts. But first, we need to understand the
problems this class presents. A quick outline:
* Problems
* User facing issues
* Problem space complexity
* Maintenance and code correctness challenges
* SKIP_WORKTREE expectations in Git
* Suggested solution
* Pros/Cons of suggested solution
* Notes on testcase modifications
=== User facing issues ===
There are various ways for users to get files to be present in the
working copy despite having the SKIP_WORKTREE bit set for that file in
the index. This may come from:
* various git commands not really supporting the SKIP_WORKTREE bit[1,2]
* users grabbing files from elsewhere and writing them to the worktree
(perhaps even cached in their editor)
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
Once users have present-despite-SKIP_WORKTREE files, any modifications
users make to these files will be ignored, possibly to users' confusion.
Further:
* these files will degrade performance for the sparse-index case due
to requiring the index to be expanded (see commit 55dfcf9591
("sparse-checkout: clear tracked sparse dirs", 2021-09-08) for why
we try to delete entire directories outside the sparse cone).
* these files will not be updated by by standard commands
(switch/checkout/pull/merge/rebase will leave them alone unless
conflicts happen -- and even then, the conflicted file may be
written somewhere else to avoid overwriting the SKIP_WORKTREE file
that is present and in the way)
* there is nothing in Git that users can use to discover such
files (status, diff, grep, etc. all ignore it)
* there is no reasonable mechanism to "recover" from such a condition
(neither `git sparse-checkout reapply` nor `git reset --hard` will
correct it).
So, not only are users modifications ignored, but the files get
progressively more stale over time. At some point in the future, they
may change their sparseness specification or disable sparse-checkouts.
At that time, all present-despite-SKIP_WORKTREE files will show up as
having lots of modifications because they represent a version from a
different branch or commit. These might include user-made local changes
from days before, but the only way to tell is to have users look through
them all closely.
If these users come to others for help, there will be no logs that
explain the issue; it's just a mysterious list of changes. Users might
adamantly claim (correctly, as it turns out) that they didn't modify
these files, while others presume they did.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
=== Problem space complexity ===
SKIP_WORKTREE has been part of Git for over a decade. Duy did lots of
work on it initially, and several others have since come along and put
lots of work into it. Stolee spent most of 2021 on the sparse-index,
with lots of bugfixes along the way including to non-sparse-index cases
as we are still trying to get sparse checkouts to behave reasonably.
Basically every codepath throughout the treat needs to be aware of an
additional type of file: tracked-but-not-present. The extra type
results in lots of extra testcases and lots of extra code everywhere.
But, the sad thing is that we actually have more than one extra type.
We have tracked, tracked-but-not-present (SKIP_WORKTREE), and
tracked-but-promised-to-not-be-present-but-is-present-anyway
(present-despite-SKIP_WORKTREE). Two types is a monumental amount of
effort to support, and adding a third feels a bit like insanity[4].
[4] Some examples of which can be seen at
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
=== Maintenance and code correctness challenges ===
Matheus' patches to grep stalled for nearly a year, in part because of
complications of how to handle sparse-checkouts appropriately in all
cases[5][6] (with trying to sanely figure out how to sanely handle
present-despite-SKIP_WORKTREE files being one of the complications).
His rm/add follow-ups also took months because of those kinds of
issues[7]. The corner cases with things like submodules and
SKIP_WORKTREE with the addition of present-despite-SKIP_WORKTREE start
becoming really complex[8].
We've had to add ugly logic to merge-ort to attempt to handle
present-despite-SKIP_WORKTREE files[9], and basically just been forced
to give up in merge-recursive knowing full well that we'll sometimes
silently discard user modifications. Despite stash essentially being a
merge, it needed extra code (beyond what was in merge-ort and
merge-recursive) to manually tweak SKIP_WORKTREE bits in order to avoid
a few different bugs that'd result in an early abort with a partial
stash application[10].
[5] See https://lore.kernel.org/git/5f3f7ac77039d41d1692ceae4b0c5df3bb45b74a.1612901326.git.matheus.bernardino@usp.br/#t
and the dates on the thread; also Matheus and I had several
conversations off-list trying to resolve the issues over that time
[6] ...it finally kind of got unstuck after
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
[7] See for example
https://lore.kernel.org/git/CABPp-BHwNoVnooqDFPAsZxBT9aR5Dwk5D9sDRCvYSb8akxAJgA@mail.gmail.com/#t
and quotes like "The core functionality of sparse-checkout has always
been only partially implemented", a statement I still believe is true
today.
[8] https://lore.kernel.org/git/pull.809.git.git.1592356884310.gitgitgadget@gmail.com/
[9] See commit 66b209b86a ("merge-ort: implement CE_SKIP_WORKTREE
handling with conflicted entries", 2021-03-20)
[10] See commit ba359fd507 ("stash: fix stash application in
sparse-checkouts", 2020-12-01)
=== SKIP_WORKTREE expectations in Git ===
A couple quotes:
* From [11] (before the "sparse-checkout" command existed):
If it needs too many special cases, hacks, and conditionals, then it
is not worth the complexity---if it is easier to write a correct code
by allowing Git to populate working tree files, it is perfectly fine
to do so.
In a sense, the sparse checkout "feature" itself is a hack by itself,
and that is why I think this part should be "best effort" as well.
* From the git-sparse-checkout manual (still present today):
THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
THE FUTURE.
[11] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
=== Suggested solution ===
SKIP_WORKTREE was written to allow sparse-checkouts, in particular, as
the name of the option implies, to allow the file to NOT be in the
worktree but consider it to be unchanged rather than deleted.
The suggests a simple solution: present-despite-SKIP_WORKTREE files
should not exist, for those using sparse-checkouts.
Enforce this at index loading time by checking if core.sparseCheckout is
true; if so, check files in the index with the SKIP_WORKTREE bit set to
verify that they are absent from the working tree. If they are present,
unset the bit (in memory, though any commands that write to the index
will record the update).
Users can, of course, can get the SKIP_WORKTREE bit back such as by
running `git sparse-checkout reapply` (if they have ensured the file is
unmodified and doesn't match the specified sparsity patterns).
=== Pros/Cons of suggested solution ===
Pros:
* Solves the user visible problems reported above, which I've been
complaining about for nearly a year but couldn't find a solution to.
* Helps prevent slow performance degradation with a sparse-index.
* Much easier behavior in sparse-checkouts for users to reason about
* Very simple, ~30 lines of code.
* Significantly simplifies some ugly testcases, and obviates the need
to test an entire class of potential issues.
* Reduces code complexity, reasoning, and maintenance. Avoids
disagreements about weird corner cases[12].
* It has been reported that some users might be (ab)using
SKIP_WORKTREE as a let-me-modify-but-keep-the-file-in-the-worktree
mechanism[13, and a few other similar references]. These users know
of multiple caveats and shortcomings in doing so; perhaps not
surprising given the "SKIP_WORKTREE expecations" section above.
However, these users use `git update-index --skip-worktree`, and not
`git sparse-checkout` or core.sparseCheckout=true. As such, these
users would be unaffected by this change and can continue abusing
the system as before.
[12] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[13] https://stackoverflow.com/questions/13630849/git-difference-between-assume-unchanged-and-skip-worktree
Cons:
* When core.sparseCheckout is enabled, this adds a performance cost to
reading the index. I'll defer discussion of this cost to a subsequent
patch, since I have some optimizations to add.
=== Notes on testcase modifications ===
The good:
* t1011: Compare to two cases above it ('read-tree will not throw away
dirty changes, non-sparse'); since the file is present, it should
match the non-sparse case now
* t1092: sparse-index & sparse-checkout now match full-worktree
behavior in more cases! Yaay for consistency!
* t6428, t7012: look at how much simpler the tests become! Merge and
stash can just fail early telling the user there's a file in the
way, instead of not noticing until it's about to write a file and
then have to implement sudden crash avoidance. Hurray for sanity!
* t7817: sparse behavior better matches full tree behavior. Hurray
for sanity!
The confusing:
* t3705: These changes were ONLY needed on Windows, but they don't
hurt other platforms. Let's discuss each individually:
* core.sparseCheckout should be false by default. Nothing in this
testcase toggles that until many, many tests later. However,
early tests (#5 in particular) were testing `update-index
--skip-worktree` behavior in a non-sparse-checkout, but the
Windows tests in CI were behaving as if core.sparseCheckout=true
had been specified somewhere. I do not have access to a Windows
machine. But I just manually did what should have been a no-op
and turned the config off. And it fixed the test.
* I have no idea why the leftover .gitattributes file from this
test was causing failures for test #18 on Windows, but only with
these changes of mine. Test #18 was checking for empty stderr,
and specifically wanted to know that some error completely
unrelated to file endings did not appear. The leftover
.gitattributes file thus caused some spurious stderr unrelated to
the thing being checked. Since other tests did not intend to
test normalization, just proactively remove the .gitattributes
file. I'm certain this is cleaner and better, I'm just unsure
why/how this didn't trigger problems before.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:41 +00:00
|
|
|
void clear_skip_worktree_from_present_files(struct index_state *istate)
|
|
|
|
{
|
Accelerate clear_skip_worktree_from_present_files() by caching
Trying to clear the skip-worktree bit from files that are present does
present some computational overhead, for sparse-checkouts. (We do not
do the bit clearing in non-sparse-checkouts.) Optimize it as follows:
Rather than lstat()'ing every SKIP_WORKTREE path, take advantage of the
fact that entire directories will often be missing, especially for cone
mode and even more so ever since commit 55dfcf9591 ("sparse-checkout:
clear tracked sparse dirs", 2021-09-08). If we have already determined
that the parent directory of a file (or other previous ancestor) does
not exist, then the file cannot exist either so we do not need to
lstat() it separately.
Timings for p2000 included below, reformatted to fit in normal commit
message line lengths, which compare three things:
* Timings before this series
* Timings of the unoptimized version of
clear_skip_worktree_from_present_files() from a few commits ago
* Timings after the optimization in this commit
(NOTE: t/perf/ appears to have timing resolution only down to 0.01 s,
which presents significant measurement error when timings only differ by
0.01s. I don't trust any such timings below, and yet all the optimized
results differ by at most 0.01s.)
Test Before Series Unoptimized Optimized
-----------------------------------------------------------------------------
*git status*
full-v3 0.15(0.10+0.06) 0.32(0.16+0.17) +113.3% 0.16(0.10+0.07) +6.7%
full-v4 0.15(0.11+0.05) 0.32(0.17+0.16) +113.3% 0.16(0.11+0.05) +6.7%
sparse-v3 0.04(0.03+0.04) 0.04(0.02+0.05) +0.0% 0.04(0.02+0.05) +0.0%
sparse-v4 0.04(0.03+0.04) 0.04(0.02+0.05) +0.0% 0.04(0.03+0.05) +0.0%
*git add -A*
full-v3 0.40(0.30+0.07) 0.56(0.36+0.17) +40.0% 0.39(0.30+0.07) -2.5%
full-v4 0.37(0.28+0.07) 0.54(0.37+0.16) +45.9% 0.38(0.29+0.07) +2.7%
sparse-v3 0.06(0.04+0.05) 0.08(0.05+0.05) +33.3% 0.06(0.05+0.04) +0.0%
sparse-v4 0.05(0.03+0.05) 0.05(0.04+0.04) +0.0% 0.06(0.04+0.05) +20.0%
*git add .*
full-v3 0.40(0.31+0.07) 0.57(0.37+0.17) +42.5% 0.41(0.30+0.08) +2.5%
full-v4 0.38(0.30+0.06) 0.55(0.37+0.16) +44.7% 0.38(0.30+0.06) +0.0%
sparse-v3 0.06(0.04+0.05) 0.06(0.05+0.04) +0.0% 0.06(0.03+0.05) +0.0%
sparse-v4 0.06(0.05+0.05) 0.06(0.04+0.05) +0.0% 0.06(0.04+0.06) +0.0%
*git commit -a -m A*
full-v3 0.41(0.32+0.06) 0.58(0.39+0.17) +41.5% 0.42(0.32+0.07) +2.4%
full-v4 0.39(0.30+0.07) 0.56(0.38+0.17) +43.6% 0.40(0.31+0.07) +2.6%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.04(0.03+0.05) 0.04(0.03+0.05) +0.0% 0.04(0.03+0.04) +0.0%
*git checkout -f -*
full-v3 0.56(0.46+0.07) 0.73(0.55+0.16) +30.4% 0.57(0.47+0.08) +1.8%
full-v4 0.54(0.45+0.07) 0.71(0.53+0.17) +31.5% 0.55(0.45+0.07) +1.9%
sparse-v3 0.06(0.04+0.04) 0.06(0.04+0.05) +0.0% 0.06(0.04+0.05) +0.0%
sparse-v4 0.05(0.05+0.04) 0.05(0.04+0.05) +0.0% 0.06(0.04+0.05) +20.0%
*git reset*
full-v3 0.34(0.26+0.05) 0.51(0.34+0.15) +50.0% 0.34(0.26+0.06) +0.0%
full-v4 0.32(0.24+0.06) 0.49(0.32+0.15) +53.1% 0.33(0.25+0.06) +3.1%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.03(0.03+0.04) 0.03(0.02+0.04) +0.0% 0.03(0.03+0.04) +0.0%
*git reset --hard*
full-v3 0.57(0.46+0.07) 0.90(0.61+0.25) +57.9% 0.57(0.45+0.08) +0.0%
full-v4 0.54(0.46+0.05) 0.88(0.59+0.26) +63.0% 0.55(0.45+0.07) +1.9%
sparse-v3 0.07(0.03+0.03) 0.07(0.04+0.03) +0.0% 0.07(0.03+0.03) +0.0%
sparse-v4 0.06(0.03+0.03) 0.06(0.04+0.02) +0.0% 0.06(0.03+0.03) +0.0%
*git reset -- does-not-exist*
full-v3 0.35(0.27+0.06) 0.52(0.32+0.17) +48.6% 0.35(0.27+0.06) +0.0%
full-v4 0.33(0.26+0.05) 0.50(0.33+0.15) +51.5% 0.33(0.26+0.06) +0.0%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.04(0.02+0.04) 0.03(0.02+0.04) -25.0% 0.03(0.02+0.04) -25.0%
*git diff*
full-v3 0.07(0.04+0.04) 0.24(0.11+0.14) +242.9% 0.07(0.04+0.04) +0.0%
full-v4 0.07(0.03+0.05) 0.24(0.13+0.12) +242.9% 0.08(0.04+0.05) +14.3%
sparse-v3 0.02(0.01+0.04) 0.02(0.01+0.04) +0.0% 0.02(0.01+0.05) +0.0%
sparse-v4 0.02(0.02+0.03) 0.02(0.01+0.04) +0.0% 0.02(0.01+0.04) +0.0%
*git diff --cached*
full-v3 0.05(0.03+0.02) 0.22(0.12+0.09) +340.0% 0.05(0.03+0.01) +0.0%
full-v4 0.05(0.03+0.01) 0.23(0.12+0.11) +360.0% 0.05(0.03+0.02) +0.0%
sparse-v3 0.01(0.00+0.00) 0.01(0.00+0.00) +0.0% 0.01(0.00+0.00) +0.0%
sparse-v4 0.01(0.00+0.00) 0.01(0.00+0.00) +0.0% 0.01(0.00+0.00) +0.0%
*git blame f2/f4/a*
full-v3 0.18(0.13+0.05) 0.52(0.29+0.23) +188.9% 0.19(0.15+0.04) +5.6%
full-v4 0.19(0.15+0.04) 0.52(0.28+0.23) +173.7% 0.19(0.14+0.04) +0.0%
sparse-v3 0.10(0.08+0.02) 0.10(0.09+0.01) +0.0% 0.10(0.09+0.01) +0.0%
sparse-v4 0.10(0.08+0.02) 0.10(0.08+0.02) +0.0% 0.10(0.08+0.02) +0.0%
*git blame f2/f4/f3/a*
full-v3 0.45(0.36+0.08) 0.78(0.51+0.27) +73.3% 0.45(0.37+0.08) +0.0%
full-v4 0.45(0.37+0.08) 0.78(0.51+0.26) +73.3% 0.45(0.37+0.08) +0.0%
sparse-v3 0.36(0.32+0.04) 0.36(0.31+0.05) +0.0% 0.36(0.31+0.04) +0.0%
sparse-v4 0.36(0.31+0.05) 0.36(0.31+0.05) +0.0% 0.36(0.31+0.04) +0.0%
*git checkout-index -f --all*
full-v3 0.07(0.02+0.05) 0.24(0.12+0.12) +242.9% 0.08(0.04+0.04) +14.3%
full-v4 0.07(0.03+0.04) 0.24(0.11+0.13) +242.9% 0.08(0.03+0.04) +14.3%
sparse-v3 0.04(0.01+0.03) 0.04(0.00+0.03) +0.0% 0.04(0.01+0.03) +0.0%
sparse-v4 0.04(0.01+0.02) 0.04(0.01+0.03) +0.0% 0.04(0.01+0.02) +0.0%
*git update-index --add --remove f2/f4/a*
full-v3 0.29(0.23+0.02) 0.46(0.30+0.12) +58.6% 0.30(0.24+0.02) +3.4%
full-v4 0.27(0.22+0.02) 0.45(0.29+0.12) +66.7% 0.28(0.22+0.03) +3.7%
sparse-v3 0.02(0.02+0.00) 0.02(0.01+0.00) +0.0% 0.02(0.01+0.00) +0.0%
sparse-v4 0.02(0.02+0.00) 0.02(0.02+0.00) +0.0% 0.02(0.02+0.00) +0.0%
So, with the optimization, the extra work appears to be essentially 0
for sparse-checkouts that are also using sparse-indexes (even before my
optimization), and the extra work appears to be just marginally more
than 0 for sparse-checkouts that are using full indexes.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:43 +00:00
|
|
|
const char *last_dirname = NULL;
|
|
|
|
size_t dir_len = 0;
|
|
|
|
int dir_found = 1;
|
|
|
|
|
repo_read_index: clear SKIP_WORKTREE bit from files present in worktree
The fix is short (~30 lines), but the description is not. Sorry.
There is a set of problems caused by files in what I'll refer to as the
"present-despite-SKIP_WORKTREE" state. This commit aims to not just fix
these problems, but remove the entire class as a possibility -- for
those using sparse checkouts. But first, we need to understand the
problems this class presents. A quick outline:
* Problems
* User facing issues
* Problem space complexity
* Maintenance and code correctness challenges
* SKIP_WORKTREE expectations in Git
* Suggested solution
* Pros/Cons of suggested solution
* Notes on testcase modifications
=== User facing issues ===
There are various ways for users to get files to be present in the
working copy despite having the SKIP_WORKTREE bit set for that file in
the index. This may come from:
* various git commands not really supporting the SKIP_WORKTREE bit[1,2]
* users grabbing files from elsewhere and writing them to the worktree
(perhaps even cached in their editor)
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
Once users have present-despite-SKIP_WORKTREE files, any modifications
users make to these files will be ignored, possibly to users' confusion.
Further:
* these files will degrade performance for the sparse-index case due
to requiring the index to be expanded (see commit 55dfcf9591
("sparse-checkout: clear tracked sparse dirs", 2021-09-08) for why
we try to delete entire directories outside the sparse cone).
* these files will not be updated by by standard commands
(switch/checkout/pull/merge/rebase will leave them alone unless
conflicts happen -- and even then, the conflicted file may be
written somewhere else to avoid overwriting the SKIP_WORKTREE file
that is present and in the way)
* there is nothing in Git that users can use to discover such
files (status, diff, grep, etc. all ignore it)
* there is no reasonable mechanism to "recover" from such a condition
(neither `git sparse-checkout reapply` nor `git reset --hard` will
correct it).
So, not only are users modifications ignored, but the files get
progressively more stale over time. At some point in the future, they
may change their sparseness specification or disable sparse-checkouts.
At that time, all present-despite-SKIP_WORKTREE files will show up as
having lots of modifications because they represent a version from a
different branch or commit. These might include user-made local changes
from days before, but the only way to tell is to have users look through
them all closely.
If these users come to others for help, there will be no logs that
explain the issue; it's just a mysterious list of changes. Users might
adamantly claim (correctly, as it turns out) that they didn't modify
these files, while others presume they did.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
=== Problem space complexity ===
SKIP_WORKTREE has been part of Git for over a decade. Duy did lots of
work on it initially, and several others have since come along and put
lots of work into it. Stolee spent most of 2021 on the sparse-index,
with lots of bugfixes along the way including to non-sparse-index cases
as we are still trying to get sparse checkouts to behave reasonably.
Basically every codepath throughout the treat needs to be aware of an
additional type of file: tracked-but-not-present. The extra type
results in lots of extra testcases and lots of extra code everywhere.
But, the sad thing is that we actually have more than one extra type.
We have tracked, tracked-but-not-present (SKIP_WORKTREE), and
tracked-but-promised-to-not-be-present-but-is-present-anyway
(present-despite-SKIP_WORKTREE). Two types is a monumental amount of
effort to support, and adding a third feels a bit like insanity[4].
[4] Some examples of which can be seen at
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
=== Maintenance and code correctness challenges ===
Matheus' patches to grep stalled for nearly a year, in part because of
complications of how to handle sparse-checkouts appropriately in all
cases[5][6] (with trying to sanely figure out how to sanely handle
present-despite-SKIP_WORKTREE files being one of the complications).
His rm/add follow-ups also took months because of those kinds of
issues[7]. The corner cases with things like submodules and
SKIP_WORKTREE with the addition of present-despite-SKIP_WORKTREE start
becoming really complex[8].
We've had to add ugly logic to merge-ort to attempt to handle
present-despite-SKIP_WORKTREE files[9], and basically just been forced
to give up in merge-recursive knowing full well that we'll sometimes
silently discard user modifications. Despite stash essentially being a
merge, it needed extra code (beyond what was in merge-ort and
merge-recursive) to manually tweak SKIP_WORKTREE bits in order to avoid
a few different bugs that'd result in an early abort with a partial
stash application[10].
[5] See https://lore.kernel.org/git/5f3f7ac77039d41d1692ceae4b0c5df3bb45b74a.1612901326.git.matheus.bernardino@usp.br/#t
and the dates on the thread; also Matheus and I had several
conversations off-list trying to resolve the issues over that time
[6] ...it finally kind of got unstuck after
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
[7] See for example
https://lore.kernel.org/git/CABPp-BHwNoVnooqDFPAsZxBT9aR5Dwk5D9sDRCvYSb8akxAJgA@mail.gmail.com/#t
and quotes like "The core functionality of sparse-checkout has always
been only partially implemented", a statement I still believe is true
today.
[8] https://lore.kernel.org/git/pull.809.git.git.1592356884310.gitgitgadget@gmail.com/
[9] See commit 66b209b86a ("merge-ort: implement CE_SKIP_WORKTREE
handling with conflicted entries", 2021-03-20)
[10] See commit ba359fd507 ("stash: fix stash application in
sparse-checkouts", 2020-12-01)
=== SKIP_WORKTREE expectations in Git ===
A couple quotes:
* From [11] (before the "sparse-checkout" command existed):
If it needs too many special cases, hacks, and conditionals, then it
is not worth the complexity---if it is easier to write a correct code
by allowing Git to populate working tree files, it is perfectly fine
to do so.
In a sense, the sparse checkout "feature" itself is a hack by itself,
and that is why I think this part should be "best effort" as well.
* From the git-sparse-checkout manual (still present today):
THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
THE FUTURE.
[11] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
=== Suggested solution ===
SKIP_WORKTREE was written to allow sparse-checkouts, in particular, as
the name of the option implies, to allow the file to NOT be in the
worktree but consider it to be unchanged rather than deleted.
The suggests a simple solution: present-despite-SKIP_WORKTREE files
should not exist, for those using sparse-checkouts.
Enforce this at index loading time by checking if core.sparseCheckout is
true; if so, check files in the index with the SKIP_WORKTREE bit set to
verify that they are absent from the working tree. If they are present,
unset the bit (in memory, though any commands that write to the index
will record the update).
Users can, of course, can get the SKIP_WORKTREE bit back such as by
running `git sparse-checkout reapply` (if they have ensured the file is
unmodified and doesn't match the specified sparsity patterns).
=== Pros/Cons of suggested solution ===
Pros:
* Solves the user visible problems reported above, which I've been
complaining about for nearly a year but couldn't find a solution to.
* Helps prevent slow performance degradation with a sparse-index.
* Much easier behavior in sparse-checkouts for users to reason about
* Very simple, ~30 lines of code.
* Significantly simplifies some ugly testcases, and obviates the need
to test an entire class of potential issues.
* Reduces code complexity, reasoning, and maintenance. Avoids
disagreements about weird corner cases[12].
* It has been reported that some users might be (ab)using
SKIP_WORKTREE as a let-me-modify-but-keep-the-file-in-the-worktree
mechanism[13, and a few other similar references]. These users know
of multiple caveats and shortcomings in doing so; perhaps not
surprising given the "SKIP_WORKTREE expecations" section above.
However, these users use `git update-index --skip-worktree`, and not
`git sparse-checkout` or core.sparseCheckout=true. As such, these
users would be unaffected by this change and can continue abusing
the system as before.
[12] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[13] https://stackoverflow.com/questions/13630849/git-difference-between-assume-unchanged-and-skip-worktree
Cons:
* When core.sparseCheckout is enabled, this adds a performance cost to
reading the index. I'll defer discussion of this cost to a subsequent
patch, since I have some optimizations to add.
=== Notes on testcase modifications ===
The good:
* t1011: Compare to two cases above it ('read-tree will not throw away
dirty changes, non-sparse'); since the file is present, it should
match the non-sparse case now
* t1092: sparse-index & sparse-checkout now match full-worktree
behavior in more cases! Yaay for consistency!
* t6428, t7012: look at how much simpler the tests become! Merge and
stash can just fail early telling the user there's a file in the
way, instead of not noticing until it's about to write a file and
then have to implement sudden crash avoidance. Hurray for sanity!
* t7817: sparse behavior better matches full tree behavior. Hurray
for sanity!
The confusing:
* t3705: These changes were ONLY needed on Windows, but they don't
hurt other platforms. Let's discuss each individually:
* core.sparseCheckout should be false by default. Nothing in this
testcase toggles that until many, many tests later. However,
early tests (#5 in particular) were testing `update-index
--skip-worktree` behavior in a non-sparse-checkout, but the
Windows tests in CI were behaving as if core.sparseCheckout=true
had been specified somewhere. I do not have access to a Windows
machine. But I just manually did what should have been a no-op
and turned the config off. And it fixed the test.
* I have no idea why the leftover .gitattributes file from this
test was causing failures for test #18 on Windows, but only with
these changes of mine. Test #18 was checking for empty stderr,
and specifically wanted to know that some error completely
unrelated to file endings did not appear. The leftover
.gitattributes file thus caused some spurious stderr unrelated to
the thing being checked. Since other tests did not intend to
test normalization, just proactively remove the .gitattributes
file. I'm certain this is cleaner and better, I'm just unsure
why/how this didn't trigger problems before.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:41 +00:00
|
|
|
int i;
|
2022-11-03 23:05:00 +00:00
|
|
|
int path_count[2] = {0, 0};
|
|
|
|
int restarted = 0;
|
Accelerate clear_skip_worktree_from_present_files() by caching
Trying to clear the skip-worktree bit from files that are present does
present some computational overhead, for sparse-checkouts. (We do not
do the bit clearing in non-sparse-checkouts.) Optimize it as follows:
Rather than lstat()'ing every SKIP_WORKTREE path, take advantage of the
fact that entire directories will often be missing, especially for cone
mode and even more so ever since commit 55dfcf9591 ("sparse-checkout:
clear tracked sparse dirs", 2021-09-08). If we have already determined
that the parent directory of a file (or other previous ancestor) does
not exist, then the file cannot exist either so we do not need to
lstat() it separately.
Timings for p2000 included below, reformatted to fit in normal commit
message line lengths, which compare three things:
* Timings before this series
* Timings of the unoptimized version of
clear_skip_worktree_from_present_files() from a few commits ago
* Timings after the optimization in this commit
(NOTE: t/perf/ appears to have timing resolution only down to 0.01 s,
which presents significant measurement error when timings only differ by
0.01s. I don't trust any such timings below, and yet all the optimized
results differ by at most 0.01s.)
Test Before Series Unoptimized Optimized
-----------------------------------------------------------------------------
*git status*
full-v3 0.15(0.10+0.06) 0.32(0.16+0.17) +113.3% 0.16(0.10+0.07) +6.7%
full-v4 0.15(0.11+0.05) 0.32(0.17+0.16) +113.3% 0.16(0.11+0.05) +6.7%
sparse-v3 0.04(0.03+0.04) 0.04(0.02+0.05) +0.0% 0.04(0.02+0.05) +0.0%
sparse-v4 0.04(0.03+0.04) 0.04(0.02+0.05) +0.0% 0.04(0.03+0.05) +0.0%
*git add -A*
full-v3 0.40(0.30+0.07) 0.56(0.36+0.17) +40.0% 0.39(0.30+0.07) -2.5%
full-v4 0.37(0.28+0.07) 0.54(0.37+0.16) +45.9% 0.38(0.29+0.07) +2.7%
sparse-v3 0.06(0.04+0.05) 0.08(0.05+0.05) +33.3% 0.06(0.05+0.04) +0.0%
sparse-v4 0.05(0.03+0.05) 0.05(0.04+0.04) +0.0% 0.06(0.04+0.05) +20.0%
*git add .*
full-v3 0.40(0.31+0.07) 0.57(0.37+0.17) +42.5% 0.41(0.30+0.08) +2.5%
full-v4 0.38(0.30+0.06) 0.55(0.37+0.16) +44.7% 0.38(0.30+0.06) +0.0%
sparse-v3 0.06(0.04+0.05) 0.06(0.05+0.04) +0.0% 0.06(0.03+0.05) +0.0%
sparse-v4 0.06(0.05+0.05) 0.06(0.04+0.05) +0.0% 0.06(0.04+0.06) +0.0%
*git commit -a -m A*
full-v3 0.41(0.32+0.06) 0.58(0.39+0.17) +41.5% 0.42(0.32+0.07) +2.4%
full-v4 0.39(0.30+0.07) 0.56(0.38+0.17) +43.6% 0.40(0.31+0.07) +2.6%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.04(0.03+0.05) 0.04(0.03+0.05) +0.0% 0.04(0.03+0.04) +0.0%
*git checkout -f -*
full-v3 0.56(0.46+0.07) 0.73(0.55+0.16) +30.4% 0.57(0.47+0.08) +1.8%
full-v4 0.54(0.45+0.07) 0.71(0.53+0.17) +31.5% 0.55(0.45+0.07) +1.9%
sparse-v3 0.06(0.04+0.04) 0.06(0.04+0.05) +0.0% 0.06(0.04+0.05) +0.0%
sparse-v4 0.05(0.05+0.04) 0.05(0.04+0.05) +0.0% 0.06(0.04+0.05) +20.0%
*git reset*
full-v3 0.34(0.26+0.05) 0.51(0.34+0.15) +50.0% 0.34(0.26+0.06) +0.0%
full-v4 0.32(0.24+0.06) 0.49(0.32+0.15) +53.1% 0.33(0.25+0.06) +3.1%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.03(0.03+0.04) 0.03(0.02+0.04) +0.0% 0.03(0.03+0.04) +0.0%
*git reset --hard*
full-v3 0.57(0.46+0.07) 0.90(0.61+0.25) +57.9% 0.57(0.45+0.08) +0.0%
full-v4 0.54(0.46+0.05) 0.88(0.59+0.26) +63.0% 0.55(0.45+0.07) +1.9%
sparse-v3 0.07(0.03+0.03) 0.07(0.04+0.03) +0.0% 0.07(0.03+0.03) +0.0%
sparse-v4 0.06(0.03+0.03) 0.06(0.04+0.02) +0.0% 0.06(0.03+0.03) +0.0%
*git reset -- does-not-exist*
full-v3 0.35(0.27+0.06) 0.52(0.32+0.17) +48.6% 0.35(0.27+0.06) +0.0%
full-v4 0.33(0.26+0.05) 0.50(0.33+0.15) +51.5% 0.33(0.26+0.06) +0.0%
sparse-v3 0.04(0.03+0.04) 0.04(0.03+0.04) +0.0% 0.04(0.03+0.04) +0.0%
sparse-v4 0.04(0.02+0.04) 0.03(0.02+0.04) -25.0% 0.03(0.02+0.04) -25.0%
*git diff*
full-v3 0.07(0.04+0.04) 0.24(0.11+0.14) +242.9% 0.07(0.04+0.04) +0.0%
full-v4 0.07(0.03+0.05) 0.24(0.13+0.12) +242.9% 0.08(0.04+0.05) +14.3%
sparse-v3 0.02(0.01+0.04) 0.02(0.01+0.04) +0.0% 0.02(0.01+0.05) +0.0%
sparse-v4 0.02(0.02+0.03) 0.02(0.01+0.04) +0.0% 0.02(0.01+0.04) +0.0%
*git diff --cached*
full-v3 0.05(0.03+0.02) 0.22(0.12+0.09) +340.0% 0.05(0.03+0.01) +0.0%
full-v4 0.05(0.03+0.01) 0.23(0.12+0.11) +360.0% 0.05(0.03+0.02) +0.0%
sparse-v3 0.01(0.00+0.00) 0.01(0.00+0.00) +0.0% 0.01(0.00+0.00) +0.0%
sparse-v4 0.01(0.00+0.00) 0.01(0.00+0.00) +0.0% 0.01(0.00+0.00) +0.0%
*git blame f2/f4/a*
full-v3 0.18(0.13+0.05) 0.52(0.29+0.23) +188.9% 0.19(0.15+0.04) +5.6%
full-v4 0.19(0.15+0.04) 0.52(0.28+0.23) +173.7% 0.19(0.14+0.04) +0.0%
sparse-v3 0.10(0.08+0.02) 0.10(0.09+0.01) +0.0% 0.10(0.09+0.01) +0.0%
sparse-v4 0.10(0.08+0.02) 0.10(0.08+0.02) +0.0% 0.10(0.08+0.02) +0.0%
*git blame f2/f4/f3/a*
full-v3 0.45(0.36+0.08) 0.78(0.51+0.27) +73.3% 0.45(0.37+0.08) +0.0%
full-v4 0.45(0.37+0.08) 0.78(0.51+0.26) +73.3% 0.45(0.37+0.08) +0.0%
sparse-v3 0.36(0.32+0.04) 0.36(0.31+0.05) +0.0% 0.36(0.31+0.04) +0.0%
sparse-v4 0.36(0.31+0.05) 0.36(0.31+0.05) +0.0% 0.36(0.31+0.04) +0.0%
*git checkout-index -f --all*
full-v3 0.07(0.02+0.05) 0.24(0.12+0.12) +242.9% 0.08(0.04+0.04) +14.3%
full-v4 0.07(0.03+0.04) 0.24(0.11+0.13) +242.9% 0.08(0.03+0.04) +14.3%
sparse-v3 0.04(0.01+0.03) 0.04(0.00+0.03) +0.0% 0.04(0.01+0.03) +0.0%
sparse-v4 0.04(0.01+0.02) 0.04(0.01+0.03) +0.0% 0.04(0.01+0.02) +0.0%
*git update-index --add --remove f2/f4/a*
full-v3 0.29(0.23+0.02) 0.46(0.30+0.12) +58.6% 0.30(0.24+0.02) +3.4%
full-v4 0.27(0.22+0.02) 0.45(0.29+0.12) +66.7% 0.28(0.22+0.03) +3.7%
sparse-v3 0.02(0.02+0.00) 0.02(0.01+0.00) +0.0% 0.02(0.01+0.00) +0.0%
sparse-v4 0.02(0.02+0.00) 0.02(0.02+0.00) +0.0% 0.02(0.02+0.00) +0.0%
So, with the optimization, the extra work appears to be essentially 0
for sparse-checkouts that are also using sparse-indexes (even before my
optimization), and the extra work appears to be just marginally more
than 0 for sparse-checkouts that are using full indexes.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:43 +00:00
|
|
|
|
repo_read_index: add config to expect files outside sparse patterns
Typically with sparse checkouts, we expect files outside the sparsity
patterns to be marked as SKIP_WORKTREE and be missing from the working
tree. Sometimes this expectation would be violated however; including
in cases such as:
* users grabbing files from elsewhere and writing them to the worktree
(perhaps by editing a cached copy in an editor, copying/renaming, or
even untarring)
* various git commands having incomplete or no support for the
SKIP_WORKTREE bit[1,2]
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
When the SKIP_WORKTREE bit in the index did not reflect the presence of
the file in the working tree, it traditionally caused confusion and was
difficult to detect and recover from. So, in a sparse checkout, since
af6a51875a (repo_read_index: clear SKIP_WORKTREE bit from files present
in worktree, 2022-01-14), Git automatically clears the SKIP_WORKTREE
bit at index read time for entries corresponding to files that are
present in the working tree.
There is another workflow, however, where it is expected that paths
outside the sparsity patterns appear to exist in the working tree and
that they do not lose the SKIP_WORKTREE bit, at least until they get
modified. A Git-aware virtual file system[4] takes advantage of its
position as a file system driver to expose all files in the working
tree, fetch them on demand using partial clone on access, and tell Git
to pay attention to them on demand by updating the sparse checkout
pattern on writes. This means that commands like "git status" only have
to examine files that have potentially been modified, whereas commands
like "ls" are able to show the entire codebase without requiring manual
updates to the sparse checkout pattern.
Thus since af6a51875a, Git with such Git-aware virtual file systems
unsets the SKIP_WORKTREE bit for all files and commands like "git
status" have to fetch and examine them all.
Introduce a configuration setting sparse.expectFilesOutsideOfPatterns to
allow limiting the tracked set of files to a small set once again. A
Git-aware virtual file system or other application that wants to
maintain files outside of the sparse checkout can set this in a
repository to instruct Git not to check for the presence of
SKIP_WORKTREE files. The setting defaults to false, so most users of
sparse checkout will still get the benefit of an automatically updating
index to recover from the variety of difficult issues detailed in
af6a51875a for paths with SKIP_WORKTREE set despite the path being
present.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] The three long paragraphs in the middle of
https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
[4] such as the vfsd described in
https://lore.kernel.org/git/20220207190320.2960362-1-jonathantanmy@google.com/
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Elijah Newren <newren@gmail.com>
Reviewed-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-02-26 06:12:22 +00:00
|
|
|
if (!core_apply_sparse_checkout ||
|
|
|
|
sparse_expect_files_outside_of_patterns)
|
repo_read_index: clear SKIP_WORKTREE bit from files present in worktree
The fix is short (~30 lines), but the description is not. Sorry.
There is a set of problems caused by files in what I'll refer to as the
"present-despite-SKIP_WORKTREE" state. This commit aims to not just fix
these problems, but remove the entire class as a possibility -- for
those using sparse checkouts. But first, we need to understand the
problems this class presents. A quick outline:
* Problems
* User facing issues
* Problem space complexity
* Maintenance and code correctness challenges
* SKIP_WORKTREE expectations in Git
* Suggested solution
* Pros/Cons of suggested solution
* Notes on testcase modifications
=== User facing issues ===
There are various ways for users to get files to be present in the
working copy despite having the SKIP_WORKTREE bit set for that file in
the index. This may come from:
* various git commands not really supporting the SKIP_WORKTREE bit[1,2]
* users grabbing files from elsewhere and writing them to the worktree
(perhaps even cached in their editor)
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
Once users have present-despite-SKIP_WORKTREE files, any modifications
users make to these files will be ignored, possibly to users' confusion.
Further:
* these files will degrade performance for the sparse-index case due
to requiring the index to be expanded (see commit 55dfcf9591
("sparse-checkout: clear tracked sparse dirs", 2021-09-08) for why
we try to delete entire directories outside the sparse cone).
* these files will not be updated by by standard commands
(switch/checkout/pull/merge/rebase will leave them alone unless
conflicts happen -- and even then, the conflicted file may be
written somewhere else to avoid overwriting the SKIP_WORKTREE file
that is present and in the way)
* there is nothing in Git that users can use to discover such
files (status, diff, grep, etc. all ignore it)
* there is no reasonable mechanism to "recover" from such a condition
(neither `git sparse-checkout reapply` nor `git reset --hard` will
correct it).
So, not only are users modifications ignored, but the files get
progressively more stale over time. At some point in the future, they
may change their sparseness specification or disable sparse-checkouts.
At that time, all present-despite-SKIP_WORKTREE files will show up as
having lots of modifications because they represent a version from a
different branch or commit. These might include user-made local changes
from days before, but the only way to tell is to have users look through
them all closely.
If these users come to others for help, there will be no logs that
explain the issue; it's just a mysterious list of changes. Users might
adamantly claim (correctly, as it turns out) that they didn't modify
these files, while others presume they did.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
=== Problem space complexity ===
SKIP_WORKTREE has been part of Git for over a decade. Duy did lots of
work on it initially, and several others have since come along and put
lots of work into it. Stolee spent most of 2021 on the sparse-index,
with lots of bugfixes along the way including to non-sparse-index cases
as we are still trying to get sparse checkouts to behave reasonably.
Basically every codepath throughout the treat needs to be aware of an
additional type of file: tracked-but-not-present. The extra type
results in lots of extra testcases and lots of extra code everywhere.
But, the sad thing is that we actually have more than one extra type.
We have tracked, tracked-but-not-present (SKIP_WORKTREE), and
tracked-but-promised-to-not-be-present-but-is-present-anyway
(present-despite-SKIP_WORKTREE). Two types is a monumental amount of
effort to support, and adding a third feels a bit like insanity[4].
[4] Some examples of which can be seen at
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
=== Maintenance and code correctness challenges ===
Matheus' patches to grep stalled for nearly a year, in part because of
complications of how to handle sparse-checkouts appropriately in all
cases[5][6] (with trying to sanely figure out how to sanely handle
present-despite-SKIP_WORKTREE files being one of the complications).
His rm/add follow-ups also took months because of those kinds of
issues[7]. The corner cases with things like submodules and
SKIP_WORKTREE with the addition of present-despite-SKIP_WORKTREE start
becoming really complex[8].
We've had to add ugly logic to merge-ort to attempt to handle
present-despite-SKIP_WORKTREE files[9], and basically just been forced
to give up in merge-recursive knowing full well that we'll sometimes
silently discard user modifications. Despite stash essentially being a
merge, it needed extra code (beyond what was in merge-ort and
merge-recursive) to manually tweak SKIP_WORKTREE bits in order to avoid
a few different bugs that'd result in an early abort with a partial
stash application[10].
[5] See https://lore.kernel.org/git/5f3f7ac77039d41d1692ceae4b0c5df3bb45b74a.1612901326.git.matheus.bernardino@usp.br/#t
and the dates on the thread; also Matheus and I had several
conversations off-list trying to resolve the issues over that time
[6] ...it finally kind of got unstuck after
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
[7] See for example
https://lore.kernel.org/git/CABPp-BHwNoVnooqDFPAsZxBT9aR5Dwk5D9sDRCvYSb8akxAJgA@mail.gmail.com/#t
and quotes like "The core functionality of sparse-checkout has always
been only partially implemented", a statement I still believe is true
today.
[8] https://lore.kernel.org/git/pull.809.git.git.1592356884310.gitgitgadget@gmail.com/
[9] See commit 66b209b86a ("merge-ort: implement CE_SKIP_WORKTREE
handling with conflicted entries", 2021-03-20)
[10] See commit ba359fd507 ("stash: fix stash application in
sparse-checkouts", 2020-12-01)
=== SKIP_WORKTREE expectations in Git ===
A couple quotes:
* From [11] (before the "sparse-checkout" command existed):
If it needs too many special cases, hacks, and conditionals, then it
is not worth the complexity---if it is easier to write a correct code
by allowing Git to populate working tree files, it is perfectly fine
to do so.
In a sense, the sparse checkout "feature" itself is a hack by itself,
and that is why I think this part should be "best effort" as well.
* From the git-sparse-checkout manual (still present today):
THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
THE FUTURE.
[11] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
=== Suggested solution ===
SKIP_WORKTREE was written to allow sparse-checkouts, in particular, as
the name of the option implies, to allow the file to NOT be in the
worktree but consider it to be unchanged rather than deleted.
The suggests a simple solution: present-despite-SKIP_WORKTREE files
should not exist, for those using sparse-checkouts.
Enforce this at index loading time by checking if core.sparseCheckout is
true; if so, check files in the index with the SKIP_WORKTREE bit set to
verify that they are absent from the working tree. If they are present,
unset the bit (in memory, though any commands that write to the index
will record the update).
Users can, of course, can get the SKIP_WORKTREE bit back such as by
running `git sparse-checkout reapply` (if they have ensured the file is
unmodified and doesn't match the specified sparsity patterns).
=== Pros/Cons of suggested solution ===
Pros:
* Solves the user visible problems reported above, which I've been
complaining about for nearly a year but couldn't find a solution to.
* Helps prevent slow performance degradation with a sparse-index.
* Much easier behavior in sparse-checkouts for users to reason about
* Very simple, ~30 lines of code.
* Significantly simplifies some ugly testcases, and obviates the need
to test an entire class of potential issues.
* Reduces code complexity, reasoning, and maintenance. Avoids
disagreements about weird corner cases[12].
* It has been reported that some users might be (ab)using
SKIP_WORKTREE as a let-me-modify-but-keep-the-file-in-the-worktree
mechanism[13, and a few other similar references]. These users know
of multiple caveats and shortcomings in doing so; perhaps not
surprising given the "SKIP_WORKTREE expecations" section above.
However, these users use `git update-index --skip-worktree`, and not
`git sparse-checkout` or core.sparseCheckout=true. As such, these
users would be unaffected by this change and can continue abusing
the system as before.
[12] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[13] https://stackoverflow.com/questions/13630849/git-difference-between-assume-unchanged-and-skip-worktree
Cons:
* When core.sparseCheckout is enabled, this adds a performance cost to
reading the index. I'll defer discussion of this cost to a subsequent
patch, since I have some optimizations to add.
=== Notes on testcase modifications ===
The good:
* t1011: Compare to two cases above it ('read-tree will not throw away
dirty changes, non-sparse'); since the file is present, it should
match the non-sparse case now
* t1092: sparse-index & sparse-checkout now match full-worktree
behavior in more cases! Yaay for consistency!
* t6428, t7012: look at how much simpler the tests become! Merge and
stash can just fail early telling the user there's a file in the
way, instead of not noticing until it's about to write a file and
then have to implement sudden crash avoidance. Hurray for sanity!
* t7817: sparse behavior better matches full tree behavior. Hurray
for sanity!
The confusing:
* t3705: These changes were ONLY needed on Windows, but they don't
hurt other platforms. Let's discuss each individually:
* core.sparseCheckout should be false by default. Nothing in this
testcase toggles that until many, many tests later. However,
early tests (#5 in particular) were testing `update-index
--skip-worktree` behavior in a non-sparse-checkout, but the
Windows tests in CI were behaving as if core.sparseCheckout=true
had been specified somewhere. I do not have access to a Windows
machine. But I just manually did what should have been a no-op
and turned the config off. And it fixed the test.
* I have no idea why the leftover .gitattributes file from this
test was causing failures for test #18 on Windows, but only with
these changes of mine. Test #18 was checking for empty stderr,
and specifically wanted to know that some error completely
unrelated to file endings did not appear. The leftover
.gitattributes file thus caused some spurious stderr unrelated to
the thing being checked. Since other tests did not intend to
test normalization, just proactively remove the .gitattributes
file. I'm certain this is cleaner and better, I'm just unsure
why/how this didn't trigger problems before.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:41 +00:00
|
|
|
return;
|
|
|
|
|
2022-11-03 23:05:00 +00:00
|
|
|
trace2_region_enter("index", "clear_skip_worktree_from_present_files",
|
|
|
|
istate->repo);
|
repo_read_index: clear SKIP_WORKTREE bit from files present in worktree
The fix is short (~30 lines), but the description is not. Sorry.
There is a set of problems caused by files in what I'll refer to as the
"present-despite-SKIP_WORKTREE" state. This commit aims to not just fix
these problems, but remove the entire class as a possibility -- for
those using sparse checkouts. But first, we need to understand the
problems this class presents. A quick outline:
* Problems
* User facing issues
* Problem space complexity
* Maintenance and code correctness challenges
* SKIP_WORKTREE expectations in Git
* Suggested solution
* Pros/Cons of suggested solution
* Notes on testcase modifications
=== User facing issues ===
There are various ways for users to get files to be present in the
working copy despite having the SKIP_WORKTREE bit set for that file in
the index. This may come from:
* various git commands not really supporting the SKIP_WORKTREE bit[1,2]
* users grabbing files from elsewhere and writing them to the worktree
(perhaps even cached in their editor)
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
Once users have present-despite-SKIP_WORKTREE files, any modifications
users make to these files will be ignored, possibly to users' confusion.
Further:
* these files will degrade performance for the sparse-index case due
to requiring the index to be expanded (see commit 55dfcf9591
("sparse-checkout: clear tracked sparse dirs", 2021-09-08) for why
we try to delete entire directories outside the sparse cone).
* these files will not be updated by by standard commands
(switch/checkout/pull/merge/rebase will leave them alone unless
conflicts happen -- and even then, the conflicted file may be
written somewhere else to avoid overwriting the SKIP_WORKTREE file
that is present and in the way)
* there is nothing in Git that users can use to discover such
files (status, diff, grep, etc. all ignore it)
* there is no reasonable mechanism to "recover" from such a condition
(neither `git sparse-checkout reapply` nor `git reset --hard` will
correct it).
So, not only are users modifications ignored, but the files get
progressively more stale over time. At some point in the future, they
may change their sparseness specification or disable sparse-checkouts.
At that time, all present-despite-SKIP_WORKTREE files will show up as
having lots of modifications because they represent a version from a
different branch or commit. These might include user-made local changes
from days before, but the only way to tell is to have users look through
them all closely.
If these users come to others for help, there will be no logs that
explain the issue; it's just a mysterious list of changes. Users might
adamantly claim (correctly, as it turns out) that they didn't modify
these files, while others presume they did.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
=== Problem space complexity ===
SKIP_WORKTREE has been part of Git for over a decade. Duy did lots of
work on it initially, and several others have since come along and put
lots of work into it. Stolee spent most of 2021 on the sparse-index,
with lots of bugfixes along the way including to non-sparse-index cases
as we are still trying to get sparse checkouts to behave reasonably.
Basically every codepath throughout the treat needs to be aware of an
additional type of file: tracked-but-not-present. The extra type
results in lots of extra testcases and lots of extra code everywhere.
But, the sad thing is that we actually have more than one extra type.
We have tracked, tracked-but-not-present (SKIP_WORKTREE), and
tracked-but-promised-to-not-be-present-but-is-present-anyway
(present-despite-SKIP_WORKTREE). Two types is a monumental amount of
effort to support, and adding a third feels a bit like insanity[4].
[4] Some examples of which can be seen at
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
=== Maintenance and code correctness challenges ===
Matheus' patches to grep stalled for nearly a year, in part because of
complications of how to handle sparse-checkouts appropriately in all
cases[5][6] (with trying to sanely figure out how to sanely handle
present-despite-SKIP_WORKTREE files being one of the complications).
His rm/add follow-ups also took months because of those kinds of
issues[7]. The corner cases with things like submodules and
SKIP_WORKTREE with the addition of present-despite-SKIP_WORKTREE start
becoming really complex[8].
We've had to add ugly logic to merge-ort to attempt to handle
present-despite-SKIP_WORKTREE files[9], and basically just been forced
to give up in merge-recursive knowing full well that we'll sometimes
silently discard user modifications. Despite stash essentially being a
merge, it needed extra code (beyond what was in merge-ort and
merge-recursive) to manually tweak SKIP_WORKTREE bits in order to avoid
a few different bugs that'd result in an early abort with a partial
stash application[10].
[5] See https://lore.kernel.org/git/5f3f7ac77039d41d1692ceae4b0c5df3bb45b74a.1612901326.git.matheus.bernardino@usp.br/#t
and the dates on the thread; also Matheus and I had several
conversations off-list trying to resolve the issues over that time
[6] ...it finally kind of got unstuck after
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
[7] See for example
https://lore.kernel.org/git/CABPp-BHwNoVnooqDFPAsZxBT9aR5Dwk5D9sDRCvYSb8akxAJgA@mail.gmail.com/#t
and quotes like "The core functionality of sparse-checkout has always
been only partially implemented", a statement I still believe is true
today.
[8] https://lore.kernel.org/git/pull.809.git.git.1592356884310.gitgitgadget@gmail.com/
[9] See commit 66b209b86a ("merge-ort: implement CE_SKIP_WORKTREE
handling with conflicted entries", 2021-03-20)
[10] See commit ba359fd507 ("stash: fix stash application in
sparse-checkouts", 2020-12-01)
=== SKIP_WORKTREE expectations in Git ===
A couple quotes:
* From [11] (before the "sparse-checkout" command existed):
If it needs too many special cases, hacks, and conditionals, then it
is not worth the complexity---if it is easier to write a correct code
by allowing Git to populate working tree files, it is perfectly fine
to do so.
In a sense, the sparse checkout "feature" itself is a hack by itself,
and that is why I think this part should be "best effort" as well.
* From the git-sparse-checkout manual (still present today):
THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
THE FUTURE.
[11] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
=== Suggested solution ===
SKIP_WORKTREE was written to allow sparse-checkouts, in particular, as
the name of the option implies, to allow the file to NOT be in the
worktree but consider it to be unchanged rather than deleted.
The suggests a simple solution: present-despite-SKIP_WORKTREE files
should not exist, for those using sparse-checkouts.
Enforce this at index loading time by checking if core.sparseCheckout is
true; if so, check files in the index with the SKIP_WORKTREE bit set to
verify that they are absent from the working tree. If they are present,
unset the bit (in memory, though any commands that write to the index
will record the update).
Users can, of course, can get the SKIP_WORKTREE bit back such as by
running `git sparse-checkout reapply` (if they have ensured the file is
unmodified and doesn't match the specified sparsity patterns).
=== Pros/Cons of suggested solution ===
Pros:
* Solves the user visible problems reported above, which I've been
complaining about for nearly a year but couldn't find a solution to.
* Helps prevent slow performance degradation with a sparse-index.
* Much easier behavior in sparse-checkouts for users to reason about
* Very simple, ~30 lines of code.
* Significantly simplifies some ugly testcases, and obviates the need
to test an entire class of potential issues.
* Reduces code complexity, reasoning, and maintenance. Avoids
disagreements about weird corner cases[12].
* It has been reported that some users might be (ab)using
SKIP_WORKTREE as a let-me-modify-but-keep-the-file-in-the-worktree
mechanism[13, and a few other similar references]. These users know
of multiple caveats and shortcomings in doing so; perhaps not
surprising given the "SKIP_WORKTREE expecations" section above.
However, these users use `git update-index --skip-worktree`, and not
`git sparse-checkout` or core.sparseCheckout=true. As such, these
users would be unaffected by this change and can continue abusing
the system as before.
[12] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[13] https://stackoverflow.com/questions/13630849/git-difference-between-assume-unchanged-and-skip-worktree
Cons:
* When core.sparseCheckout is enabled, this adds a performance cost to
reading the index. I'll defer discussion of this cost to a subsequent
patch, since I have some optimizations to add.
=== Notes on testcase modifications ===
The good:
* t1011: Compare to two cases above it ('read-tree will not throw away
dirty changes, non-sparse'); since the file is present, it should
match the non-sparse case now
* t1092: sparse-index & sparse-checkout now match full-worktree
behavior in more cases! Yaay for consistency!
* t6428, t7012: look at how much simpler the tests become! Merge and
stash can just fail early telling the user there's a file in the
way, instead of not noticing until it's about to write a file and
then have to implement sudden crash avoidance. Hurray for sanity!
* t7817: sparse behavior better matches full tree behavior. Hurray
for sanity!
The confusing:
* t3705: These changes were ONLY needed on Windows, but they don't
hurt other platforms. Let's discuss each individually:
* core.sparseCheckout should be false by default. Nothing in this
testcase toggles that until many, many tests later. However,
early tests (#5 in particular) were testing `update-index
--skip-worktree` behavior in a non-sparse-checkout, but the
Windows tests in CI were behaving as if core.sparseCheckout=true
had been specified somewhere. I do not have access to a Windows
machine. But I just manually did what should have been a no-op
and turned the config off. And it fixed the test.
* I have no idea why the leftover .gitattributes file from this
test was causing failures for test #18 on Windows, but only with
these changes of mine. Test #18 was checking for empty stderr,
and specifically wanted to know that some error completely
unrelated to file endings did not appear. The leftover
.gitattributes file thus caused some spurious stderr unrelated to
the thing being checked. Since other tests did not intend to
test normalization, just proactively remove the .gitattributes
file. I'm certain this is cleaner and better, I'm just unsure
why/how this didn't trigger problems before.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:41 +00:00
|
|
|
restart:
|
|
|
|
for (i = 0; i < istate->cache_nr; i++) {
|
|
|
|
struct cache_entry *ce = istate->cache[i];
|
|
|
|
|
2022-11-03 23:05:00 +00:00
|
|
|
if (ce_skip_worktree(ce)) {
|
|
|
|
path_count[restarted]++;
|
|
|
|
if (path_found(ce->name, &last_dirname, &dir_len, &dir_found)) {
|
|
|
|
if (S_ISSPARSEDIR(ce->ce_mode)) {
|
2022-11-03 23:05:01 +00:00
|
|
|
if (restarted)
|
|
|
|
BUG("ensure-full-index did not fully flatten?");
|
2022-11-03 23:05:00 +00:00
|
|
|
ensure_full_index(istate);
|
|
|
|
restarted = 1;
|
|
|
|
goto restart;
|
|
|
|
}
|
|
|
|
ce->ce_flags &= ~CE_SKIP_WORKTREE;
|
repo_read_index: clear SKIP_WORKTREE bit from files present in worktree
The fix is short (~30 lines), but the description is not. Sorry.
There is a set of problems caused by files in what I'll refer to as the
"present-despite-SKIP_WORKTREE" state. This commit aims to not just fix
these problems, but remove the entire class as a possibility -- for
those using sparse checkouts. But first, we need to understand the
problems this class presents. A quick outline:
* Problems
* User facing issues
* Problem space complexity
* Maintenance and code correctness challenges
* SKIP_WORKTREE expectations in Git
* Suggested solution
* Pros/Cons of suggested solution
* Notes on testcase modifications
=== User facing issues ===
There are various ways for users to get files to be present in the
working copy despite having the SKIP_WORKTREE bit set for that file in
the index. This may come from:
* various git commands not really supporting the SKIP_WORKTREE bit[1,2]
* users grabbing files from elsewhere and writing them to the worktree
(perhaps even cached in their editor)
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
Once users have present-despite-SKIP_WORKTREE files, any modifications
users make to these files will be ignored, possibly to users' confusion.
Further:
* these files will degrade performance for the sparse-index case due
to requiring the index to be expanded (see commit 55dfcf9591
("sparse-checkout: clear tracked sparse dirs", 2021-09-08) for why
we try to delete entire directories outside the sparse cone).
* these files will not be updated by by standard commands
(switch/checkout/pull/merge/rebase will leave them alone unless
conflicts happen -- and even then, the conflicted file may be
written somewhere else to avoid overwriting the SKIP_WORKTREE file
that is present and in the way)
* there is nothing in Git that users can use to discover such
files (status, diff, grep, etc. all ignore it)
* there is no reasonable mechanism to "recover" from such a condition
(neither `git sparse-checkout reapply` nor `git reset --hard` will
correct it).
So, not only are users modifications ignored, but the files get
progressively more stale over time. At some point in the future, they
may change their sparseness specification or disable sparse-checkouts.
At that time, all present-despite-SKIP_WORKTREE files will show up as
having lots of modifications because they represent a version from a
different branch or commit. These might include user-made local changes
from days before, but the only way to tell is to have users look through
them all closely.
If these users come to others for help, there will be no logs that
explain the issue; it's just a mysterious list of changes. Users might
adamantly claim (correctly, as it turns out) that they didn't modify
these files, while others presume they did.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
=== Problem space complexity ===
SKIP_WORKTREE has been part of Git for over a decade. Duy did lots of
work on it initially, and several others have since come along and put
lots of work into it. Stolee spent most of 2021 on the sparse-index,
with lots of bugfixes along the way including to non-sparse-index cases
as we are still trying to get sparse checkouts to behave reasonably.
Basically every codepath throughout the treat needs to be aware of an
additional type of file: tracked-but-not-present. The extra type
results in lots of extra testcases and lots of extra code everywhere.
But, the sad thing is that we actually have more than one extra type.
We have tracked, tracked-but-not-present (SKIP_WORKTREE), and
tracked-but-promised-to-not-be-present-but-is-present-anyway
(present-despite-SKIP_WORKTREE). Two types is a monumental amount of
effort to support, and adding a third feels a bit like insanity[4].
[4] Some examples of which can be seen at
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
=== Maintenance and code correctness challenges ===
Matheus' patches to grep stalled for nearly a year, in part because of
complications of how to handle sparse-checkouts appropriately in all
cases[5][6] (with trying to sanely figure out how to sanely handle
present-despite-SKIP_WORKTREE files being one of the complications).
His rm/add follow-ups also took months because of those kinds of
issues[7]. The corner cases with things like submodules and
SKIP_WORKTREE with the addition of present-despite-SKIP_WORKTREE start
becoming really complex[8].
We've had to add ugly logic to merge-ort to attempt to handle
present-despite-SKIP_WORKTREE files[9], and basically just been forced
to give up in merge-recursive knowing full well that we'll sometimes
silently discard user modifications. Despite stash essentially being a
merge, it needed extra code (beyond what was in merge-ort and
merge-recursive) to manually tweak SKIP_WORKTREE bits in order to avoid
a few different bugs that'd result in an early abort with a partial
stash application[10].
[5] See https://lore.kernel.org/git/5f3f7ac77039d41d1692ceae4b0c5df3bb45b74a.1612901326.git.matheus.bernardino@usp.br/#t
and the dates on the thread; also Matheus and I had several
conversations off-list trying to resolve the issues over that time
[6] ...it finally kind of got unstuck after
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
[7] See for example
https://lore.kernel.org/git/CABPp-BHwNoVnooqDFPAsZxBT9aR5Dwk5D9sDRCvYSb8akxAJgA@mail.gmail.com/#t
and quotes like "The core functionality of sparse-checkout has always
been only partially implemented", a statement I still believe is true
today.
[8] https://lore.kernel.org/git/pull.809.git.git.1592356884310.gitgitgadget@gmail.com/
[9] See commit 66b209b86a ("merge-ort: implement CE_SKIP_WORKTREE
handling with conflicted entries", 2021-03-20)
[10] See commit ba359fd507 ("stash: fix stash application in
sparse-checkouts", 2020-12-01)
=== SKIP_WORKTREE expectations in Git ===
A couple quotes:
* From [11] (before the "sparse-checkout" command existed):
If it needs too many special cases, hacks, and conditionals, then it
is not worth the complexity---if it is easier to write a correct code
by allowing Git to populate working tree files, it is perfectly fine
to do so.
In a sense, the sparse checkout "feature" itself is a hack by itself,
and that is why I think this part should be "best effort" as well.
* From the git-sparse-checkout manual (still present today):
THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
THE FUTURE.
[11] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
=== Suggested solution ===
SKIP_WORKTREE was written to allow sparse-checkouts, in particular, as
the name of the option implies, to allow the file to NOT be in the
worktree but consider it to be unchanged rather than deleted.
The suggests a simple solution: present-despite-SKIP_WORKTREE files
should not exist, for those using sparse-checkouts.
Enforce this at index loading time by checking if core.sparseCheckout is
true; if so, check files in the index with the SKIP_WORKTREE bit set to
verify that they are absent from the working tree. If they are present,
unset the bit (in memory, though any commands that write to the index
will record the update).
Users can, of course, can get the SKIP_WORKTREE bit back such as by
running `git sparse-checkout reapply` (if they have ensured the file is
unmodified and doesn't match the specified sparsity patterns).
=== Pros/Cons of suggested solution ===
Pros:
* Solves the user visible problems reported above, which I've been
complaining about for nearly a year but couldn't find a solution to.
* Helps prevent slow performance degradation with a sparse-index.
* Much easier behavior in sparse-checkouts for users to reason about
* Very simple, ~30 lines of code.
* Significantly simplifies some ugly testcases, and obviates the need
to test an entire class of potential issues.
* Reduces code complexity, reasoning, and maintenance. Avoids
disagreements about weird corner cases[12].
* It has been reported that some users might be (ab)using
SKIP_WORKTREE as a let-me-modify-but-keep-the-file-in-the-worktree
mechanism[13, and a few other similar references]. These users know
of multiple caveats and shortcomings in doing so; perhaps not
surprising given the "SKIP_WORKTREE expecations" section above.
However, these users use `git update-index --skip-worktree`, and not
`git sparse-checkout` or core.sparseCheckout=true. As such, these
users would be unaffected by this change and can continue abusing
the system as before.
[12] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[13] https://stackoverflow.com/questions/13630849/git-difference-between-assume-unchanged-and-skip-worktree
Cons:
* When core.sparseCheckout is enabled, this adds a performance cost to
reading the index. I'll defer discussion of this cost to a subsequent
patch, since I have some optimizations to add.
=== Notes on testcase modifications ===
The good:
* t1011: Compare to two cases above it ('read-tree will not throw away
dirty changes, non-sparse'); since the file is present, it should
match the non-sparse case now
* t1092: sparse-index & sparse-checkout now match full-worktree
behavior in more cases! Yaay for consistency!
* t6428, t7012: look at how much simpler the tests become! Merge and
stash can just fail early telling the user there's a file in the
way, instead of not noticing until it's about to write a file and
then have to implement sudden crash avoidance. Hurray for sanity!
* t7817: sparse behavior better matches full tree behavior. Hurray
for sanity!
The confusing:
* t3705: These changes were ONLY needed on Windows, but they don't
hurt other platforms. Let's discuss each individually:
* core.sparseCheckout should be false by default. Nothing in this
testcase toggles that until many, many tests later. However,
early tests (#5 in particular) were testing `update-index
--skip-worktree` behavior in a non-sparse-checkout, but the
Windows tests in CI were behaving as if core.sparseCheckout=true
had been specified somewhere. I do not have access to a Windows
machine. But I just manually did what should have been a no-op
and turned the config off. And it fixed the test.
* I have no idea why the leftover .gitattributes file from this
test was causing failures for test #18 on Windows, but only with
these changes of mine. Test #18 was checking for empty stderr,
and specifically wanted to know that some error completely
unrelated to file endings did not appear. The leftover
.gitattributes file thus caused some spurious stderr unrelated to
the thing being checked. Since other tests did not intend to
test normalization, just proactively remove the .gitattributes
file. I'm certain this is cleaner and better, I'm just unsure
why/how this didn't trigger problems before.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:41 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2022-11-03 23:05:00 +00:00
|
|
|
|
|
|
|
if (path_count[0])
|
|
|
|
trace2_data_intmax("index", istate->repo,
|
|
|
|
"sparse_path_count", path_count[0]);
|
|
|
|
if (restarted)
|
|
|
|
trace2_data_intmax("index", istate->repo,
|
|
|
|
"sparse_path_count_full", path_count[1]);
|
|
|
|
trace2_region_leave("index", "clear_skip_worktree_from_present_files",
|
|
|
|
istate->repo);
|
repo_read_index: clear SKIP_WORKTREE bit from files present in worktree
The fix is short (~30 lines), but the description is not. Sorry.
There is a set of problems caused by files in what I'll refer to as the
"present-despite-SKIP_WORKTREE" state. This commit aims to not just fix
these problems, but remove the entire class as a possibility -- for
those using sparse checkouts. But first, we need to understand the
problems this class presents. A quick outline:
* Problems
* User facing issues
* Problem space complexity
* Maintenance and code correctness challenges
* SKIP_WORKTREE expectations in Git
* Suggested solution
* Pros/Cons of suggested solution
* Notes on testcase modifications
=== User facing issues ===
There are various ways for users to get files to be present in the
working copy despite having the SKIP_WORKTREE bit set for that file in
the index. This may come from:
* various git commands not really supporting the SKIP_WORKTREE bit[1,2]
* users grabbing files from elsewhere and writing them to the worktree
(perhaps even cached in their editor)
* users attempting to "abort" a sparse-checkout operation with a
not-so-early Ctrl+C (updating $GIT_DIR/info/sparse-checkout and the
working tree is not atomic)[3].
Once users have present-despite-SKIP_WORKTREE files, any modifications
users make to these files will be ignored, possibly to users' confusion.
Further:
* these files will degrade performance for the sparse-index case due
to requiring the index to be expanded (see commit 55dfcf9591
("sparse-checkout: clear tracked sparse dirs", 2021-09-08) for why
we try to delete entire directories outside the sparse cone).
* these files will not be updated by by standard commands
(switch/checkout/pull/merge/rebase will leave them alone unless
conflicts happen -- and even then, the conflicted file may be
written somewhere else to avoid overwriting the SKIP_WORKTREE file
that is present and in the way)
* there is nothing in Git that users can use to discover such
files (status, diff, grep, etc. all ignore it)
* there is no reasonable mechanism to "recover" from such a condition
(neither `git sparse-checkout reapply` nor `git reset --hard` will
correct it).
So, not only are users modifications ignored, but the files get
progressively more stale over time. At some point in the future, they
may change their sparseness specification or disable sparse-checkouts.
At that time, all present-despite-SKIP_WORKTREE files will show up as
having lots of modifications because they represent a version from a
different branch or commit. These might include user-made local changes
from days before, but the only way to tell is to have users look through
them all closely.
If these users come to others for help, there will be no logs that
explain the issue; it's just a mysterious list of changes. Users might
adamantly claim (correctly, as it turns out) that they didn't modify
these files, while others presume they did.
[1] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
[2] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[3] https://lore.kernel.org/git/CABPp-BFnFpzwGC11TLoLs8YK5yiisA5D5-fFjXnJsbESVDwZsA@mail.gmail.com/
=== Problem space complexity ===
SKIP_WORKTREE has been part of Git for over a decade. Duy did lots of
work on it initially, and several others have since come along and put
lots of work into it. Stolee spent most of 2021 on the sparse-index,
with lots of bugfixes along the way including to non-sparse-index cases
as we are still trying to get sparse checkouts to behave reasonably.
Basically every codepath throughout the treat needs to be aware of an
additional type of file: tracked-but-not-present. The extra type
results in lots of extra testcases and lots of extra code everywhere.
But, the sad thing is that we actually have more than one extra type.
We have tracked, tracked-but-not-present (SKIP_WORKTREE), and
tracked-but-promised-to-not-be-present-but-is-present-anyway
(present-despite-SKIP_WORKTREE). Two types is a monumental amount of
effort to support, and adding a third feels a bit like insanity[4].
[4] Some examples of which can be seen at
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
=== Maintenance and code correctness challenges ===
Matheus' patches to grep stalled for nearly a year, in part because of
complications of how to handle sparse-checkouts appropriately in all
cases[5][6] (with trying to sanely figure out how to sanely handle
present-despite-SKIP_WORKTREE files being one of the complications).
His rm/add follow-ups also took months because of those kinds of
issues[7]. The corner cases with things like submodules and
SKIP_WORKTREE with the addition of present-despite-SKIP_WORKTREE start
becoming really complex[8].
We've had to add ugly logic to merge-ort to attempt to handle
present-despite-SKIP_WORKTREE files[9], and basically just been forced
to give up in merge-recursive knowing full well that we'll sometimes
silently discard user modifications. Despite stash essentially being a
merge, it needed extra code (beyond what was in merge-ort and
merge-recursive) to manually tweak SKIP_WORKTREE bits in order to avoid
a few different bugs that'd result in an early abort with a partial
stash application[10].
[5] See https://lore.kernel.org/git/5f3f7ac77039d41d1692ceae4b0c5df3bb45b74a.1612901326.git.matheus.bernardino@usp.br/#t
and the dates on the thread; also Matheus and I had several
conversations off-list trying to resolve the issues over that time
[6] ...it finally kind of got unstuck after
https://lore.kernel.org/git/CABPp-BGJ_Nvi5TmgriD9Bh6eNXE2EDq2f8e8QKXAeYG3BxZafA@mail.gmail.com/
[7] See for example
https://lore.kernel.org/git/CABPp-BHwNoVnooqDFPAsZxBT9aR5Dwk5D9sDRCvYSb8akxAJgA@mail.gmail.com/#t
and quotes like "The core functionality of sparse-checkout has always
been only partially implemented", a statement I still believe is true
today.
[8] https://lore.kernel.org/git/pull.809.git.git.1592356884310.gitgitgadget@gmail.com/
[9] See commit 66b209b86a ("merge-ort: implement CE_SKIP_WORKTREE
handling with conflicted entries", 2021-03-20)
[10] See commit ba359fd507 ("stash: fix stash application in
sparse-checkouts", 2020-12-01)
=== SKIP_WORKTREE expectations in Git ===
A couple quotes:
* From [11] (before the "sparse-checkout" command existed):
If it needs too many special cases, hacks, and conditionals, then it
is not worth the complexity---if it is easier to write a correct code
by allowing Git to populate working tree files, it is perfectly fine
to do so.
In a sense, the sparse checkout "feature" itself is a hack by itself,
and that is why I think this part should be "best effort" as well.
* From the git-sparse-checkout manual (still present today):
THIS COMMAND IS EXPERIMENTAL. ITS BEHAVIOR, AND THE BEHAVIOR OF OTHER
COMMANDS IN THE PRESENCE OF SPARSE-CHECKOUTS, WILL LIKELY CHANGE IN
THE FUTURE.
[11] https://lore.kernel.org/git/xmqqbmb1a7ga.fsf@gitster-ct.c.googlers.com/
=== Suggested solution ===
SKIP_WORKTREE was written to allow sparse-checkouts, in particular, as
the name of the option implies, to allow the file to NOT be in the
worktree but consider it to be unchanged rather than deleted.
The suggests a simple solution: present-despite-SKIP_WORKTREE files
should not exist, for those using sparse-checkouts.
Enforce this at index loading time by checking if core.sparseCheckout is
true; if so, check files in the index with the SKIP_WORKTREE bit set to
verify that they are absent from the working tree. If they are present,
unset the bit (in memory, though any commands that write to the index
will record the update).
Users can, of course, can get the SKIP_WORKTREE bit back such as by
running `git sparse-checkout reapply` (if they have ensured the file is
unmodified and doesn't match the specified sparsity patterns).
=== Pros/Cons of suggested solution ===
Pros:
* Solves the user visible problems reported above, which I've been
complaining about for nearly a year but couldn't find a solution to.
* Helps prevent slow performance degradation with a sparse-index.
* Much easier behavior in sparse-checkouts for users to reason about
* Very simple, ~30 lines of code.
* Significantly simplifies some ugly testcases, and obviates the need
to test an entire class of potential issues.
* Reduces code complexity, reasoning, and maintenance. Avoids
disagreements about weird corner cases[12].
* It has been reported that some users might be (ab)using
SKIP_WORKTREE as a let-me-modify-but-keep-the-file-in-the-worktree
mechanism[13, and a few other similar references]. These users know
of multiple caveats and shortcomings in doing so; perhaps not
surprising given the "SKIP_WORKTREE expecations" section above.
However, these users use `git update-index --skip-worktree`, and not
`git sparse-checkout` or core.sparseCheckout=true. As such, these
users would be unaffected by this change and can continue abusing
the system as before.
[12] https://lore.kernel.org/git/CABPp-BH9tju7WVm=QZDOvaMDdZbpNXrVWQdN-jmfN8wC6YVhmw@mail.gmail.com/
[13] https://stackoverflow.com/questions/13630849/git-difference-between-assume-unchanged-and-skip-worktree
Cons:
* When core.sparseCheckout is enabled, this adds a performance cost to
reading the index. I'll defer discussion of this cost to a subsequent
patch, since I have some optimizations to add.
=== Notes on testcase modifications ===
The good:
* t1011: Compare to two cases above it ('read-tree will not throw away
dirty changes, non-sparse'); since the file is present, it should
match the non-sparse case now
* t1092: sparse-index & sparse-checkout now match full-worktree
behavior in more cases! Yaay for consistency!
* t6428, t7012: look at how much simpler the tests become! Merge and
stash can just fail early telling the user there's a file in the
way, instead of not noticing until it's about to write a file and
then have to implement sudden crash avoidance. Hurray for sanity!
* t7817: sparse behavior better matches full tree behavior. Hurray
for sanity!
The confusing:
* t3705: These changes were ONLY needed on Windows, but they don't
hurt other platforms. Let's discuss each individually:
* core.sparseCheckout should be false by default. Nothing in this
testcase toggles that until many, many tests later. However,
early tests (#5 in particular) were testing `update-index
--skip-worktree` behavior in a non-sparse-checkout, but the
Windows tests in CI were behaving as if core.sparseCheckout=true
had been specified somewhere. I do not have access to a Windows
machine. But I just manually did what should have been a no-op
and turned the config off. And it fixed the test.
* I have no idea why the leftover .gitattributes file from this
test was causing failures for test #18 on Windows, but only with
these changes of mine. Test #18 was checking for empty stderr,
and specifically wanted to know that some error completely
unrelated to file endings did not appear. The leftover
.gitattributes file thus caused some spurious stderr unrelated to
the thing being checked. Since other tests did not intend to
test normalization, just proactively remove the .gitattributes
file. I'm certain this is cleaner and better, I'm just unsure
why/how this didn't trigger problems before.
Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-14 15:59:41 +00:00
|
|
|
}
|
|
|
|
|
sparse-index: expand_to_path()
Some users of the index API have a specific path they are looking for,
but choose to use index_file_exists() to rely on the name-hash hashtable
instead of doing binary search with index_name_pos(). These users only
need to know a yes/no answer, not a position within the cache array.
When the index is sparse, the name-hash hash table does not contain the
full list of paths within sparse directories. It _does_ contain the
directory names for the sparse-directory entries.
Create a helper function, expand_to_path(), for intended use with the
name-hash hashtable functions. The integration with name-hash.c will
follow in a later change.
The solution here is to use ensure_full_index() when we determine that
the requested path is within a sparse directory entry. This will
populate the name-hash hashtable as the index is recomputed from
scratch.
There may be cases where the caller is trying to find an untracked path
that is not in the index but also is not within a sparse directory
entry. We want to minimize the overhead for these requests. If we used
index_name_pos() to find the insertion order of the path, then we could
determine from that position if a sparse-directory exists. (In fact,
just calling index_name_pos() in that case would lead to expanding the
index to a full index.) However, this takes O(log N) time where N is the
number of cache entries.
To keep the performance of this call based mostly on the input string,
use index_file_exists() to look for the ancestors of the path. Using the
heuristic that a sparse directory is likely to have a small number of
parent directories, we start from the bottom and build up. Use a string
buffer to allow mutating the path name to terminate after each slash for
each hashset test.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-12 21:08:16 +00:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
|
2023-01-12 12:55:24 +00:00
|
|
|
if (!istate->sparse_index)
|
sparse-index: expand_to_path()
Some users of the index API have a specific path they are looking for,
but choose to use index_file_exists() to rely on the name-hash hashtable
instead of doing binary search with index_name_pos(). These users only
need to know a yes/no answer, not a position within the cache array.
When the index is sparse, the name-hash hash table does not contain the
full list of paths within sparse directories. It _does_ contain the
directory names for the sparse-directory entries.
Create a helper function, expand_to_path(), for intended use with the
name-hash hashtable functions. The integration with name-hash.c will
follow in a later change.
The solution here is to use ensure_full_index() when we determine that
the requested path is within a sparse directory entry. This will
populate the name-hash hashtable as the index is recomputed from
scratch.
There may be cases where the caller is trying to find an untracked path
that is not in the index but also is not within a sparse directory
entry. We want to minimize the overhead for these requests. If we used
index_name_pos() to find the insertion order of the path, then we could
determine from that position if a sparse-directory exists. (In fact,
just calling index_name_pos() in that case would lead to expanding the
index to a full index.) However, this takes O(log N) time where N is the
number of cache entries.
To keep the performance of this call based mostly on the input string,
use index_file_exists() to look for the ancestors of the path. Using the
heuristic that a sparse directory is likely to have a small number of
parent directories, we start from the bottom and build up. Use a string
buffer to allow mutating the path name to terminate after each slash for
each hashset test.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-12 21:08:16 +00:00
|
|
|
return;
|
|
|
|
|
|
|
|
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;
|
|
|
|
}
|