read-cache: force_verify_index_checksum

Teach git to skip verification of the SHA1-1 checksum at the end of
the index file in verify_hdr() which is called from read_index()
unless the "force_verify_index_checksum" global variable is set.

Teach fsck to force this verification.

The checksum verification is for detecting disk corruption, and for
small projects, the time it takes to compute SHA-1 is not that
significant, but for gigantic repositories this calculation adds
significant time to every command.

These effect can be seen using t/perf/p0002-read-cache.sh:

Test                                          HEAD~1            HEAD
--------------------------------------------------------------------------------------
0002.1: read_cache/discard_cache 1000 times   0.66(0.44+0.20)   0.30(0.27+0.02) -54.5%

Signed-off-by: Jeff Hostetler <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jeffhostetler

builtin/fsck.c

@@ -771,6 +771,7 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 	}
 
 	if (keep_cache_objects) {
+		verify_index_checksum = 1;
 		read_cache();
 		for (i = 0; i < active_nr; i++) {
 			unsigned int mode;

cache.h

@@ -705,6 +705,8 @@ extern void update_index_if_able(struct index_state *, struct lock_file *);
 extern int hold_locked_index(struct lock_file *, int);
 extern void set_alternate_index_output(const char *);
 
+extern int verify_index_checksum;
+
 /* Environment bits from configuration mechanism */
 extern int trust_executable_bit;
 extern int trust_ctime;

read-cache.c

@@ -1371,6 +1371,9 @@ struct ondisk_cache_entry_extended {
 			    ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
 			    ondisk_cache_entry_size(ce_namelen(ce)))
 
+/* Allow fsck to force verification of the index checksum. */
+int verify_index_checksum;
+
 static int verify_hdr(struct cache_header *hdr, unsigned long size)
 {
 	git_SHA_CTX c;
@@ -1382,6 +1385,10 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size)
 	hdr_version = ntohl(hdr->hdr_version);
 	if (hdr_version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < hdr_version)
 		return error("bad index version %d", hdr_version);
+
+	if (!verify_index_checksum)
+		return 0;
+
 	git_SHA1_Init(&c);
 	git_SHA1_Update(&c, hdr, size - 20);
 	git_SHA1_Final(sha1, &c);

t/t1450-fsck.sh

@@ -689,4 +689,17 @@ test_expect_success 'bogus head does not fallback to all heads' '
 	! grep $blob out
 '
 
+test_expect_success 'detect corrupt index file in fsck' '
+	cp .git/index .git/index.backup &&
+	test_when_finished "mv .git/index.backup .git/index" &&
+	echo zzzzzzzz >zzzzzzzz &&
+	git add zzzzzzzz &&
+	sed -e "s/zzzzzzzz/yyyyyyyy/" .git/index >.git/index.yyy &&
+	mv .git/index.yyy .git/index &&
+	# Confirm that fsck detects invalid checksum
+	test_must_fail git fsck --cache &&
+	# Confirm that status no longer complains about invalid checksum
+	git status
+'
+
 test_done