From ab733daff5398fd07ff051c323f51b70efbc2e57 Mon Sep 17 00:00:00 2001
From: Derrick Stolee <dstolee@microsoft.com>
Date: Wed, 28 Nov 2018 17:50:43 +0000
Subject: [PATCH] pack-objects: add --sparse option

Add a '--sparse' option flag to the pack-objects builtin. This
allows the user to specify that they want to use the new logic
for walking trees. This logic currently does not differ from the
existing output, but will in a later change.

Create a new test script, t5322-pack-objects-sparse.sh, to ensure
the object list that is selected matches what we expect. When we
update the logic to walk in a sparse fashion, the final test will
be updated to show the extra objects that are added.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 Documentation/git-pack-objects.txt |  11 ++-
 builtin/pack-objects.c             |   5 +-
 t/t5322-pack-objects-sparse.sh     | 115 +++++++++++++++++++++++++++++
 3 files changed, 129 insertions(+), 2 deletions(-)
 create mode 100755 t/t5322-pack-objects-sparse.sh

diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt
index 40c825c38197f4..e45f3e680d3632 100644
--- a/Documentation/git-pack-objects.txt
+++ b/Documentation/git-pack-objects.txt
@@ -14,7 +14,7 @@ SYNOPSIS
 	[--local] [--incremental] [--window=<n>] [--depth=<n>]
 	[--revs [--unpacked | --all]] [--keep-pack=<pack-name>]
 	[--stdout [--filter=<filter-spec>] | base-name]
-	[--shallow] [--keep-true-parents] < object-list
+	[--shallow] [--keep-true-parents] [--sparse] < object-list
 
 
 DESCRIPTION
@@ -196,6 +196,15 @@ depth is 4095.
 	Add --no-reuse-object if you want to force a uniform compression
 	level on all data no matter the source.
 
+--sparse::
+	Use the "sparse" algorithm to determine which objects to include in
+	the pack, when combined with the "--revs" option. This algorithm
+	only walks trees that appear in paths that introduce new objects.
+	This can have significant performance benefits when computing
+	a pack to send a small change. However, it is possible that extra
+	objects are added to the pack-file if the included commits contain
+	certain types of direct renames.
+
 --thin::
 	Create a "thin" pack by omitting the common objects between a
 	sender and a receiver in order to reduce network transfer. This
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 5f70d840a707fa..7d5b0735e39698 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -84,6 +84,7 @@ static unsigned long pack_size_limit;
 static int depth = 50;
 static int delta_search_threads;
 static int pack_to_stdout;
+static int sparse;
 static int thin;
 static int num_preferred_base;
 static struct progress *progress_state;
@@ -3135,7 +3136,7 @@ static void get_object_list(int ac, const char **av)
 
 	if (prepare_revision_walk(&revs))
 		die(_("revision walk setup failed"));
-	mark_edges_uninteresting(&revs, show_edge, 0);
+	mark_edges_uninteresting(&revs, show_edge, sparse);
 
 	if (!fn_show_object)
 		fn_show_object = show_object;
@@ -3292,6 +3293,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		{ OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"),
 		  N_("unpack unreachable objects newer than <time>"),
 		  PARSE_OPT_OPTARG, option_parse_unpack_unreachable },
+		OPT_BOOL(0, "sparse", &sparse,
+			 N_("use the sparse reachability algorithm")),
 		OPT_BOOL(0, "thin", &thin,
 			 N_("create thin packs")),
 		OPT_BOOL(0, "shallow", &shallow,
diff --git a/t/t5322-pack-objects-sparse.sh b/t/t5322-pack-objects-sparse.sh
new file mode 100755
index 00000000000000..81f6805bc30559
--- /dev/null
+++ b/t/t5322-pack-objects-sparse.sh
@@ -0,0 +1,115 @@
+#!/bin/sh
+
+test_description='pack-objects object selection using sparse algorithm'
+. ./test-lib.sh
+
+test_expect_success 'setup repo' '
+	test_commit initial &&
+	for i in $(test_seq 1 3)
+	do
+		mkdir f$i &&
+		for j in $(test_seq 1 3)
+		do
+			mkdir f$i/f$j &&
+			echo $j >f$i/f$j/data.txt
+		done
+	done &&
+	git add . &&
+	git commit -m "Initialized trees" &&
+	for i in $(test_seq 1 3)
+	do
+		git checkout -b topic$i master &&
+		echo change-$i >f$i/f$i/data.txt &&
+		git commit -a -m "Changed f$i/f$i/data.txt"
+	done &&
+	cat >packinput.txt <<-EOF &&
+	topic1
+	^topic2
+	^topic3
+	EOF
+	git rev-parse			\
+		topic1			\
+		topic1^{tree}		\
+		topic1:f1		\
+		topic1:f1/f1		\
+		topic1:f1/f1/data.txt | sort >expect_objects.txt
+'
+
+test_expect_success 'non-sparse pack-objects' '
+	git pack-objects --stdout --revs <packinput.txt >nonsparse.pack &&
+	git index-pack -o nonsparse.idx nonsparse.pack &&
+	git show-index <nonsparse.idx | awk "{print \$2}" >nonsparse_objects.txt &&
+	test_cmp expect_objects.txt nonsparse_objects.txt
+'
+
+test_expect_success 'sparse pack-objects' '
+	git pack-objects --stdout --revs --sparse <packinput.txt >sparse.pack &&
+	git index-pack -o sparse.idx sparse.pack &&
+	git show-index <sparse.idx | awk "{print \$2}" >sparse_objects.txt &&
+	test_cmp expect_objects.txt sparse_objects.txt
+'
+
+# Demonstrate that both algorithms send "extra" objects because
+# they are not in the frontier.
+
+test_expect_success 'duplicate a folder from f3 and commit to topic1' '
+	git checkout topic1 &&
+	echo change-3 >f3/f3/data.txt &&
+	git commit -a -m "Changed f3/f3/data.txt" &&
+	git rev-parse			\
+		topic1~1		\
+		topic1~1^{tree}		\
+		topic1^{tree}		\
+		topic1			\
+		topic1:f1		\
+		topic1:f1/f1		\
+		topic1:f1/f1/data.txt	\
+		topic1:f3		\
+		topic1:f3/f3		\
+		topic1:f3/f3/data.txt | sort >expect_objects.txt
+'
+
+test_expect_success 'non-sparse pack-objects' '
+	git pack-objects --stdout --revs <packinput.txt >nonsparse.pack &&
+	git index-pack -o nonsparse.idx nonsparse.pack &&
+	git show-index <nonsparse.idx | awk "{print \$2}" >nonsparse_objects.txt &&
+	test_cmp expect_objects.txt nonsparse_objects.txt
+'
+
+test_expect_success 'sparse pack-objects' '
+	git pack-objects --stdout --revs --sparse <packinput.txt >sparse.pack &&
+	git index-pack -o sparse.idx sparse.pack &&
+	git show-index <sparse.idx | awk "{print \$2}" >sparse_objects.txt &&
+	test_cmp expect_objects.txt sparse_objects.txt
+'
+
+test_expect_success 'duplicate a folder from f1 into f3' '
+	mkdir f3/f4 &&
+	cp -r f1/f1/* f3/f4 &&
+	git add f3/f4 &&
+	git commit -m "Copied f1/f1 to f3/f4" &&
+	cat >packinput.txt <<-EOF &&
+	topic1
+	^topic1~1
+	EOF
+	git rev-parse		\
+		topic1		\
+		topic1^{tree}	\
+		topic1:f3 | sort >expect_objects.txt
+'
+
+test_expect_success 'non-sparse pack-objects' '
+	git pack-objects --stdout --revs <packinput.txt >nonsparse.pack &&
+	git index-pack -o nonsparse.idx nonsparse.pack &&
+	git show-index <nonsparse.idx | awk "{print \$2}" >nonsparse_objects.txt &&
+	test_cmp expect_objects.txt nonsparse_objects.txt
+'
+
+test_expect_success 'sparse pack-objects' '
+	git pack-objects --stdout --revs --sparse <packinput.txt >sparse.pack &&
+	git index-pack -o sparse.idx sparse.pack &&
+	git show-index <sparse.idx | awk "{print \$2}" >sparse_objects.txt &&
+	test_cmp expect_objects.txt sparse_objects.txt
+'
+
+test_done