From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail•com>
To: git@vger•kernel.org
Cc: gitster@pobox•com, Derrick Stolee <stolee@gmail•com>,
Derrick Stolee <stolee@gmail•com>
Subject: [PATCH v2 2/2] restore: avoid sparse index expansion
Date: Tue, 26 May 2026 20:26:34 +0000 [thread overview]
Message-ID: <88f5d26a3345bf524bdef872027704c8fb955e74.1779827195.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.2121.v2.git.1779827195.gitgitgadget@gmail.com>
From: Derrick Stolee <stolee@gmail•com>
Teach update_some() to handle sparse directory entries at the tree
level rather than expanding the entire sparse index. When iterating a
source tree during checkout/restore operations:
- If a directory matches a sparse directory entry with the same OID,
skip it entirely (no change needed).
- If the OID differs and we are in non-overlay mode (e.g., restore
--staged), update the sparse directory entry's OID in place. This
is semantically correct because non-overlay mode removes paths not
in the source tree anyway.
- In overlay mode (e.g., checkout <tree> -- .), fall through to
recursive descent so individual file entries are preserved
correctly.
Also switch from index_name_pos() to index_name_pos_sparse() for
individual file lookups to avoid triggering ensure_full_index() when
the file is already individually tracked in the index.
Update the test expectation in t1092 to assert that 'restore --staged'
no longer expands the sparse index.
Signed-off-by: Derrick Stolee <stolee@gmail•com>
---
builtin/checkout.c | 65 +++++++++++++++++++++---
t/t1092-sparse-checkout-compatibility.sh | 8 +--
2 files changed, 63 insertions(+), 10 deletions(-)
diff --git a/builtin/checkout.c b/builtin/checkout.c
index 1345e8574a..86e23a07b1 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -31,6 +31,7 @@
#include "revision.h"
#include "sequencer.h"
#include "setup.h"
+#include "sparse-index.h"
#include "strvec.h"
#include "submodule.h"
#include "symlinks.h"
@@ -141,15 +142,65 @@ static int post_checkout_hook(struct commit *old_commit, struct commit *new_comm
return run_hooks_opt(the_repository, "post-checkout", &opt);
}
+/*
+ * Handle a tree object and determine if we need to recurse into the
+ * tree (READ_TREE_RECURSIVE) or skip it (0).
+ */
+static int try_update_sparse_directory(const struct object_id *oid,
+ struct strbuf *base,
+ const char *pathname,
+ int overlay_mode)
+{
+ struct strbuf dirpath = STRBUF_INIT;
+ struct cache_entry *old;
+ int pos, result = READ_TREE_RECURSIVE;
+
+ if (!the_repository->index->sparse_index)
+ return result;
+
+ strbuf_addbuf(&dirpath, base);
+ strbuf_addstr(&dirpath, pathname);
+ strbuf_addch(&dirpath, '/');
+
+ pos = index_name_pos_sparse(the_repository->index,
+ dirpath.buf, dirpath.len);
+ if (pos < 0)
+ goto cleanup;
+
+ old = the_repository->index->cache[pos];
+ if (!S_ISSPARSEDIR(old->ce_mode))
+ goto cleanup;
+
+ if (oideq(oid, &old->oid)) {
+ /* Tree content already matches; no need to descend. */
+ result = 0;
+ } else if (!overlay_mode) {
+ /*
+ * In non-overlay mode (e.g., restore --staged), replace the
+ * sparse directory OID directly since files not present in
+ * the source tree should be removed anyway.
+ */
+ oidcpy(&old->oid, oid);
+ old->ce_flags |= CE_UPDATE;
+ result = 0;
+ }
+
+cleanup:
+ strbuf_release(&dirpath);
+ return result;
+}
+
static int update_some(const struct object_id *oid, struct strbuf *base,
- const char *pathname, unsigned mode, void *context UNUSED)
+ const char *pathname, unsigned mode, void *context)
{
int len;
struct cache_entry *ce;
int pos;
+ int overlay_mode = context ? *((int *)context) : 1;
if (S_ISDIR(mode))
- return READ_TREE_RECURSIVE;
+ return try_update_sparse_directory(oid, base, pathname,
+ overlay_mode);
len = base->len + strlen(pathname);
ce = make_empty_cache_entry(the_repository->index, len);
@@ -165,7 +216,7 @@ static int update_some(const struct object_id *oid, struct strbuf *base,
* entry in place. Whether it is UPTODATE or not, checkout_entry will
* do the right thing.
*/
- pos = index_name_pos(the_repository->index, ce->name, ce->ce_namelen);
+ pos = index_name_pos_sparse(the_repository->index, ce->name, ce->ce_namelen);
if (pos >= 0) {
struct cache_entry *old = the_repository->index->cache[pos];
if (ce->ce_mode == old->ce_mode &&
@@ -182,10 +233,11 @@ static int update_some(const struct object_id *oid, struct strbuf *base,
return 0;
}
-static int read_tree_some(struct tree *tree, const struct pathspec *pathspec)
+static int read_tree_some(struct tree *tree, const struct pathspec *pathspec,
+ int overlay_mode)
{
read_tree(the_repository, tree,
- pathspec, update_some, NULL);
+ pathspec, update_some, &overlay_mode);
/* update the index with the given tree's info
* for all args, expanding wildcards, and exit
@@ -580,7 +632,8 @@ static int checkout_paths(const struct checkout_opts *opts,
return error(_("index file corrupt"));
if (opts->source_tree)
- read_tree_some(opts->source_tree, &opts->pathspec);
+ read_tree_some(opts->source_tree, &opts->pathspec,
+ opts->overlay_mode);
if (opts->merge)
unmerge_index(the_repository->index, &opts->pathspec, CE_MATCHED);
diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh
index d69434e7ab..8186da5c88 100755
--- a/t/t1092-sparse-checkout-compatibility.sh
+++ b/t/t1092-sparse-checkout-compatibility.sh
@@ -2608,19 +2608,19 @@ test_expect_success 'restore --staged with wildcards' '
test_all_match git diff --cached
'
-test_expect_success 'sparse-index is expanded: restore --staged' '
+test_expect_success 'sparse-index is not expanded: restore --staged' '
init_repos &&
git -C sparse-index checkout -b restore-staged-exp base &&
git -C sparse-index reset --soft update-folder1 &&
- ensure_expanded restore --staged .
+ ensure_not_expanded restore --staged .
'
-test_expect_success 'sparse-index is expanded: restore --source --staged' '
+test_expect_success 'sparse-index is not expanded: restore --source --staged' '
init_repos &&
git -C sparse-index checkout -b restore-source-staged base &&
- ensure_expanded restore --source update-folder1 --staged .
+ ensure_not_expanded restore --source update-folder1 --staged .
'
test_done
--
gitgitgadget
prev parent reply other threads:[~2026-05-26 20:26 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-24 17:40 [PATCH 0/2] restore: better integrate with sparse index Derrick Stolee via GitGitGadget
2026-05-24 17:40 ` [PATCH 1/2] t1092: test 'git restore' " Derrick Stolee via GitGitGadget
2026-05-24 22:51 ` Junio C Hamano
2026-05-24 17:40 ` [PATCH 2/2] restore: avoid sparse index expansion Derrick Stolee via GitGitGadget
2026-05-24 23:05 ` Junio C Hamano
2026-05-26 2:54 ` Derrick Stolee
2026-05-26 20:26 ` [PATCH v2 0/2] restore: better integrate with sparse index Derrick Stolee via GitGitGadget
2026-05-26 20:26 ` [PATCH v2 1/2] t1092: test 'git restore' " Derrick Stolee via GitGitGadget
2026-05-26 20:26 ` Derrick Stolee via GitGitGadget [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=88f5d26a3345bf524bdef872027704c8fb955e74.1779827195.git.gitgitgadget@gmail.com \
--to=gitgitgadget@gmail$(echo .)com \
--cc=git@vger$(echo .)kernel.org \
--cc=gitster@pobox$(echo .)com \
--cc=stolee@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox