From: Han Xin <hanxin.hx@xxxxxxxxxxxxxxx>
In dry_run mode, "get_data()" is used to verify the inflation of data,
and the returned buffer will not be used at all and will be freed
immediately. Even in dry_run mode, it is dangerous to allocate a
full-size buffer for a large blob object. Therefore, only allocate a
low memory footprint when calling "get_data()" in dry_run mode.
Suggested-by: Jiang Xin <zhiyou.jx@xxxxxxxxxxxxxxx>
Signed-off-by: Han Xin <hanxin.hx@xxxxxxxxxxxxxxx>
---
builtin/unpack-objects.c | 23 +++++++++---
t/t5590-unpack-non-delta-objects.sh | 57 +++++++++++++++++++++++++++++
2 files changed, 74 insertions(+), 6 deletions(-)
create mode 100755 t/t5590-unpack-non-delta-objects.sh
diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index 4a9466295b..9104eb48da 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -96,15 +96,21 @@ static void use(int bytes)
display_throughput(progress, consumed_bytes);
}
-static void *get_data(unsigned long size)
+static void *get_data(size_t size, int dry_run)
{
git_zstream stream;
- void *buf = xmallocz(size);
+ size_t bufsize;
+ void *buf;
memset(&stream, 0, sizeof(stream));
+ if (dry_run && size > 8192)
+ bufsize = 8192;
+ else
+ bufsize = size;
+ buf = xmallocz(bufsize);
stream.next_out = buf;
- stream.avail_out = size;
+ stream.avail_out = bufsize;
stream.next_in = fill(1);
stream.avail_in = len;
git_inflate_init(&stream);
@@ -124,6 +130,11 @@ static void *get_data(unsigned long size)
}
stream.next_in = fill(1);
stream.avail_in = len;
+ if (dry_run) {
+ /* reuse the buffer in dry_run mode */
+ stream.next_out = buf;
+ stream.avail_out = bufsize;
+ }
}
git_inflate_end(&stream);
return buf;
@@ -323,7 +334,7 @@ static void added_object(unsigned nr, enum object_type type,
static void unpack_non_delta_entry(enum object_type type, unsigned long size,
unsigned nr)
{
- void *buf = get_data(size);
+ void *buf = get_data(size, dry_run);
if (!dry_run && buf)
write_object(nr, type, buf, size);
@@ -357,7 +368,7 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
if (type == OBJ_REF_DELTA) {
oidread(&base_oid, fill(the_hash_algo->rawsz));
use(the_hash_algo->rawsz);
- delta_data = get_data(delta_size);
+ delta_data = get_data(delta_size, dry_run);
if (dry_run || !delta_data) {
free(delta_data);
return;
@@ -396,7 +407,7 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
if (base_offset <= 0 || base_offset >= obj_list[nr].offset)
die("offset value out of bound for delta base object");
- delta_data = get_data(delta_size);
+ delta_data = get_data(delta_size, dry_run);
if (dry_run || !delta_data) {
free(delta_data);
return;
diff --git a/t/t5590-unpack-non-delta-objects.sh b/t/t5590-unpack-non-delta-objects.sh
new file mode 100755
index 0000000000..48c4fb1ba3
--- /dev/null
+++ b/t/t5590-unpack-non-delta-objects.sh
@@ -0,0 +1,57 @@
+#!/bin/sh
+#
+# Copyright (c) 2021 Han Xin
+#
+
+test_description='Test unpack-objects with non-delta objects'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+
+prepare_dest () {
+ test_when_finished "rm -rf dest.git" &&
+ git init --bare dest.git
+}
+
+test_expect_success "setup repo with big blobs (1.5 MB)" '
+ test-tool genrandom foo 1500000 >big-blob &&
+ test_commit --append foo big-blob &&
+ test-tool genrandom bar 1500000 >big-blob &&
+ test_commit --append bar big-blob &&
+ (
+ cd .git &&
+ find objects/?? -type f | sort
+ ) >expect &&
+ PACK=$(echo main | git pack-objects --revs test)
+'
+
+test_expect_success 'setup env: GIT_ALLOC_LIMIT to 1MB' '
+ GIT_ALLOC_LIMIT=1m &&
+ export GIT_ALLOC_LIMIT
+'
+
+test_expect_success 'fail to unpack-objects: cannot allocate' '
+ prepare_dest &&
+ test_must_fail git -C dest.git unpack-objects <test-$PACK.pack 2>err &&
+ grep "fatal: attempting to allocate" err &&
+ (
+ cd dest.git &&
+ find objects/?? -type f | sort
+ ) >actual &&
+ test_file_not_empty actual &&
+ ! test_cmp expect actual
+'
+
+test_expect_success 'unpack-objects dry-run' '
+ prepare_dest &&
+ git -C dest.git unpack-objects -n <test-$PACK.pack &&
+ (
+ cd dest.git &&
+ find objects/ -type f
+ ) >actual &&
+ test_must_be_empty actual
+'
+
+test_done
--
2.34.1.52.g80008efde6.agit.6.5.6
