pack-objects: match prune logic for discarding objects

A recent commit taught git-prune to keep non-recent objects
that are reachable from recent ones. However, pack-objects,
when loosening unreachable objects, tries to optimize out
the write in the case that the object will be immediately
pruned. It now gets this wrong, since its rule does not
reflect the new prune code (and this can be seen by running
t6501 with a strategically placed repack).

Let's teach pack-objects similar logic.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/pack-objects.c

@@ -20,6 +20,8 @@
 #include "streaming.h"
 #include "thread-utils.h"
 #include "pack-bitmap.h"
+#include "reachable.h"
+#include "sha1-array.h"
 
 static const char *pack_usage[] = {
 	N_("git pack-objects --stdout [options...] [< ref-list | < object-list]"),
@@ -2407,6 +2409,15 @@ static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1)
 	return 0;
 }
 
+/*
+ * Store a list of sha1s that are should not be discarded
+ * because they are either written too recently, or are
+ * reachable from another object that was.
+ *
+ * This is filled by get_object_list.
+ */
+static struct sha1_array recent_objects;
+
 static int loosened_object_can_be_discarded(const unsigned char *sha1,
 					    unsigned long mtime)
 {
@@ -2414,6 +2425,8 @@ static int loosened_object_can_be_discarded(const unsigned char *sha1,
 		return 0;
 	if (mtime > unpack_unreachable_expiration)
 		return 0;
+	if (sha1_array_lookup(&recent_objects, sha1) >= 0)
+		return 0;
 	return 1;
 }
 
@@ -2470,6 +2483,19 @@ static int get_object_list_from_bitmap(struct rev_info *revs)
 	return 0;
 }
 
+static void record_recent_object(struct object *obj,
+				 const struct name_path *path,
+				 const char *last,
+				 void *data)
+{
+	sha1_array_append(&recent_objects, obj->sha1);
+}
+
+static void record_recent_commit(struct commit *commit, void *data)
+{
+	sha1_array_append(&recent_objects, commit->object.sha1);
+}
+
 static void get_object_list(int ac, const char **av)
 {
 	struct rev_info revs;
@@ -2517,10 +2543,23 @@ static void get_object_list(int ac, const char **av)
 	mark_edges_uninteresting(&revs, show_edge);
 	traverse_commit_list(&revs, show_commit, show_object, NULL);
 
+	if (unpack_unreachable_expiration) {
+		revs.ignore_missing_links = 1;
+		if (add_unseen_recent_objects_to_traversal(&revs,
+				unpack_unreachable_expiration))
+			die("unable to add recent objects");
+		if (prepare_revision_walk(&revs))
+			die("revision walk setup failed");
+		traverse_commit_list(&revs, record_recent_commit,
+				     record_recent_object, NULL);
+	}
+
 	if (keep_unreachable)
 		add_objects_in_unpacked_packs(&revs);
 	if (unpack_unreachable)
 		loosen_unused_packed_objects(&revs);
+
+	sha1_array_clear(&recent_objects);
 }
 
 static int option_parse_index_version(const struct option *opt,

reachable.c

@@ -183,8 +183,8 @@ static int add_recent_packed(const unsigned char *sha1,
 	return 0;
 }
 
-static int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
+int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
-						  unsigned long timestamp)
+					   unsigned long timestamp)
 {
 	struct recent_data data;
 	int r;

reachable.h

@@ -2,6 +2,8 @@
 #define REACHEABLE_H
 
 struct progress;
+extern int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
+						  unsigned long timestamp);
 extern void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 				   unsigned long mark_recent, struct progress *);
 

t/t6501-freshen-objects.sh

@@ -39,50 +39,67 @@ commit () {
 	git commit -m "$1"
 }
 
-test_expect_success 'disable reflogs' '
+maybe_repack () {
-	git config core.logallrefupdates false &&
+	if test -n "$repack"; then
-	rm -rf .git/logs
+		git repack -ad
-'
+	fi
+}
 
-test_expect_success 'setup basic history' '
+for repack in '' true; do
-	commit base
+	title=${repack:+repack}
-'
+	title=${title:-loose}
 
-test_expect_success 'create and abandon some objects' '
+	test_expect_success "make repo completely empty ($title)" '
-	git checkout -b experiment &&
+		rm -rf .git &&
-	commit abandon &&
+		git init
-	git checkout master &&
+	'
-	git branch -D experiment
-'
 
-test_expect_success 'simulate time passing' '
+	test_expect_success "disable reflogs ($title)" '
-	find .git/objects -type f |
+		git config core.logallrefupdates false &&
-	xargs test-chmtime -v -86400
+		rm -rf .git/logs
-'
+	'
 
-test_expect_success 'start writing new commit with old blob' '
+	test_expect_success "setup basic history ($title)" '
-	tree=$(
+		commit base
-		GIT_INDEX_FILE=index.tmp &&
+	'
-		export GIT_INDEX_FILE &&
-		git read-tree HEAD &&
-		add unrelated &&
-		add abandon &&
-		git write-tree
-	)
-'
 
-test_expect_success 'simultaneous gc' '
+	test_expect_success "create and abandon some objects ($title)" '
-	git gc --prune=12.hours.ago
+		git checkout -b experiment &&
-'
+		commit abandon &&
+		maybe_repack &&
+		git checkout master &&
+		git branch -D experiment
+	'
 
-test_expect_success 'finish writing out commit' '
+	test_expect_success "simulate time passing ($title)" '
-	commit=$(echo foo | git commit-tree -p HEAD $tree) &&
+		find .git/objects -type f |
-	git update-ref HEAD $commit
+		xargs test-chmtime -v -86400
-'
+	'
 
-# "abandon" blob should have been rescued by reference from new tree
+	test_expect_success "start writing new commit with old blob ($title)" '
-test_expect_success 'repository passes fsck' '
+		tree=$(
-	git fsck
+			GIT_INDEX_FILE=index.tmp &&
-'
+			export GIT_INDEX_FILE &&
+			git read-tree HEAD &&
+			add unrelated &&
+			add abandon &&
+			git write-tree
+		)
+	'
+
+	test_expect_success "simultaneous gc ($title)" '
+		git gc --prune=12.hours.ago
+	'
+
+	test_expect_success "finish writing out commit ($title)" '
+		commit=$(echo foo | git commit-tree -p HEAD $tree) &&
+		git update-ref HEAD $commit
+	'
+
+	# "abandon" blob should have been rescued by reference from new tree
+	test_expect_success "repository passes fsck ($title)" '
+		git fsck
+	'
+done
 
 test_done