[PATCH v14 1/7] unpack-objects: low memory footprint for get_data() in dry_run mode

[Han Xin <chiyutianyi@gmail.com>]

From: Han Xin <hanxin.hx@alibaba-inc.com>

As the name implies, "get_data(size)" will allocate and return a given
amount of memory. Allocating memory for a large blob object may cause the
system to run out of memory. Before preparing to replace calling of
"get_data()" to unpack large blob objects in latter commits, refactor
"get_data()" to reduce memory footprint for dry_run mode.

Because in dry_run mode, "get_data()" is only used to check the
integrity of data, and the returned buffer is not used at all, we can
allocate a smaller buffer and use it as zstream output. Make the function
return NULL in the dry-run mode, as no callers use the returned buffer.

The "find [...]objects/?? -type f | wc -l" test idiom being used here
is adapted from the same "find" use added to another test in
d9545c7f465 (fast-import: implement unpack limit, 2016-04-25).

Suggested-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <hanxin.hx@alibaba-inc.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
---
 builtin/unpack-objects.c        | 37 ++++++++++++++++++++---------
 t/t5351-unpack-large-objects.sh | 41 +++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+), 11 deletions(-)
 create mode 100755 t/t5351-unpack-large-objects.sh

diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index 56d05e2725..32e8b47059 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -97,15 +97,27 @@ static void use(int bytes)
 	display_throughput(progress, consumed_bytes);
 }
 
+/*
+ * Decompress zstream from the standard input into a newly
+ * allocated buffer of specified size and return the buffer.
+ * The caller is responsible to free the returned buffer.
+ *
+ * But for dry_run mode, "get_data()" is only used to check the
+ * integrity of data, and the returned buffer is not used at all.
+ * Therefore, in dry_run mode, "get_data()" will release the small
+ * allocated buffer which is reused to hold temporary zstream output
+ * and return NULL instead of returning garbage data.
+ */
 static void *get_data(unsigned long size)
 {
 	git_zstream stream;
-	void *buf = xmallocz(size);
+	unsigned long bufsize = dry_run && size > 8192 ? 8192 : size;
+	void *buf = xmallocz(bufsize);
 
 	memset(&stream, 0, sizeof(stream));
 
 	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);
@@ -125,8 +137,17 @@ 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 > size - stream.total_out ?
+						   size - stream.total_out :
+						   bufsize;
+		}
 	}
 	git_inflate_end(&stream);
+	if (dry_run)
+		FREE_AND_NULL(buf);
 	return buf;
 }
 
@@ -326,10 +347,8 @@ static void unpack_non_delta_entry(enum object_type type, unsigned long size,
 {
 	void *buf = get_data(size);
 
-	if (!dry_run && buf)
+	if (buf)
 		write_object(nr, type, buf, size);
-	else
-		free(buf);
 }
 
 static int resolve_against_held(unsigned nr, const struct object_id *base,
@@ -359,10 +378,8 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
 		oidread(&base_oid, fill(the_hash_algo->rawsz));
 		use(the_hash_algo->rawsz);
 		delta_data = get_data(delta_size);
-		if (dry_run || !delta_data) {
-			free(delta_data);
+		if (!delta_data)
 			return;
-		}
 		if (has_object_file(&base_oid))
 			; /* Ok we have this one */
 		else if (resolve_against_held(nr, &base_oid,
@@ -398,10 +415,8 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
 			die("offset value out of bound for delta base object");
 
 		delta_data = get_data(delta_size);
-		if (dry_run || !delta_data) {
-			free(delta_data);
+		if (!delta_data)
 			return;
-		}
 		lo = 0;
 		hi = nr;
 		while (lo < hi) {
diff --git a/t/t5351-unpack-large-objects.sh b/t/t5351-unpack-large-objects.sh
new file mode 100755
index 0000000000..8d84313221
--- /dev/null
+++ b/t/t5351-unpack-large-objects.sh
@@ -0,0 +1,41 @@
+#!/bin/sh
+#
+# Copyright (c) 2022 Han Xin
+#
+
+test_description='git unpack-objects with large objects'
+
+. ./test-lib.sh
+
+prepare_dest () {
+	test_when_finished "rm -rf dest.git" &&
+	git init --bare dest.git
+}
+
+test_expect_success "create large objects (1.5 MB) and PACK" '
+	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 &&
+	PACK=$(echo HEAD | git pack-objects --revs pack)
+'
+
+test_expect_success 'set memory limitation to 1MB' '
+	GIT_ALLOC_LIMIT=1m &&
+	export GIT_ALLOC_LIMIT
+'
+
+test_expect_success 'unpack-objects failed under memory limitation' '
+	prepare_dest &&
+	test_must_fail git -C dest.git unpack-objects <pack-$PACK.pack 2>err &&
+	grep "fatal: attempting to allocate" err
+'
+
+test_expect_success 'unpack-objects works with memory limitation in dry-run mode' '
+	prepare_dest &&
+	git -C dest.git unpack-objects -n <pack-$PACK.pack &&
+	test_stdout_line_count = 0 find dest.git/objects -type f &&
+	test_dir_is_empty dest.git/objects/pack
+'
+
+test_done
-- 
2.36.1