convert: add "status=delayed" to filter process protocol

Some `clean` / `smudge` filters may require a significant amount of
time to process a single blob (e.g. the Git LFS smudge filter might
perform network requests). During this process the Git checkout
operation is blocked and Git needs to wait until the filter is done to
continue with the checkout.

Teach the filter process protocol, introduced in edcc8581 ("convert: add
filter.<driver>.process option", 2016-10-16), to accept the status
"delayed" as response to a filter request. Upon this response Git
continues with the checkout operation. After the checkout operation Git
calls "finish_delayed_checkout" which queries the filter for remaining
blobs. If the filter is still working on the completion, then the filter
is expected to block. If the filter has completed all remaining blobs
then an empty response is expected.

Git has a multiple code paths that checkout a blob. Support delayed
checkouts only in `clone` (in unpack-trees.c) and `checkout` operations
for now. The optimization is most effective in these code paths as all
files of the tree are processed.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 116 insertions, 0 deletions

diff --git a/t/t0021-conversion.sh b/t/t0021-conversion.sh
index 0c04d346a1..eb3d83744a 100755
--- a/t/t0021-conversion.sh
+++ b/t/t0021-conversion.sh
@@ -701,4 +701,120 @@ test_expect_success PERL 'invalid process filter must fail (and not hang!)' '
 	)
 '
 
+test_expect_success PERL 'delayed checkout in process filter' '
+	test_config_global filter.a.process "rot13-filter.pl a.log clean smudge delay" &&
+	test_config_global filter.a.required true &&
+	test_config_global filter.b.process "rot13-filter.pl b.log clean smudge delay" &&
+	test_config_global filter.b.required true &&
+
+	rm -rf repo &&
+	mkdir repo &&
+	(
+		cd repo &&
+		git init &&
+		echo "*.a filter=a" >.gitattributes &&
+		echo "*.b filter=b" >>.gitattributes &&
+		cp "$TEST_ROOT/test.o" test.a &&
+		cp "$TEST_ROOT/test.o" test-delay10.a &&
+		cp "$TEST_ROOT/test.o" test-delay11.a &&
+		cp "$TEST_ROOT/test.o" test-delay20.a &&
+		cp "$TEST_ROOT/test.o" test-delay10.b &&
+		git add . &&
+		git commit -m "test commit"
+	) &&
+
+	S=$(file_size "$TEST_ROOT/test.o") &&
+	cat >a.exp <<-EOF &&
+		START
+		init handshake complete
+		IN: smudge test.a $S [OK] -- OUT: $S . [OK]
+		IN: smudge test-delay10.a $S [OK] -- [DELAYED]
+		IN: smudge test-delay11.a $S [OK] -- [DELAYED]
+		IN: smudge test-delay20.a $S [OK] -- [DELAYED]
+		IN: list_available_blobs test-delay10.a test-delay11.a [OK]
+		IN: smudge test-delay10.a 0 [OK] -- OUT: $S . [OK]
+		IN: smudge test-delay11.a 0 [OK] -- OUT: $S . [OK]
+		IN: list_available_blobs test-delay20.a [OK]
+		IN: smudge test-delay20.a 0 [OK] -- OUT: $S . [OK]
+		IN: list_available_blobs [OK]
+		STOP
+	EOF
+	cat >b.exp <<-EOF &&
+		START
+		init handshake complete
+		IN: smudge test-delay10.b $S [OK] -- [DELAYED]
+		IN: list_available_blobs test-delay10.b [OK]
+		IN: smudge test-delay10.b 0 [OK] -- OUT: $S . [OK]
+		IN: list_available_blobs [OK]
+		STOP
+	EOF
+
+	rm -rf repo-cloned &&
+	filter_git clone repo repo-cloned &&
+	test_cmp_count a.exp repo-cloned/a.log &&
+	test_cmp_count b.exp repo-cloned/b.log &&
+
+	(
+		cd repo-cloned &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay11.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay20.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.b &&
+
+		rm *.a *.b &&
+		filter_git checkout . &&
+		test_cmp_count ../a.exp a.log &&
+		test_cmp_count ../b.exp b.log &&
+
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay11.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay20.a &&
+		test_cmp_committed_rot13 "$TEST_ROOT/test.o" test-delay10.b
+	)
+'
+
+test_expect_success PERL 'missing file in delayed checkout' '
+	test_config_global filter.bug.process "rot13-filter.pl bug.log clean smudge delay" &&
+	test_config_global filter.bug.required true &&
+
+	rm -rf repo &&
+	mkdir repo &&
+	(
+		cd repo &&
+		git init &&
+		echo "*.a filter=bug" >.gitattributes &&
+		cp "$TEST_ROOT/test.o" missing-delay.a
+		git add . &&
+		git commit -m "test commit"
+	) &&
+
+	rm -rf repo-cloned &&
+	test_must_fail git clone repo repo-cloned 2>git-stderr.log &&
+	cat git-stderr.log &&
+	grep "error: .missing-delay\.a. was not filtered properly" git-stderr.log
+'
+
+test_expect_success PERL 'invalid file in delayed checkout' '
+	test_config_global filter.bug.process "rot13-filter.pl bug.log clean smudge delay" &&
+	test_config_global filter.bug.required true &&
+
+	rm -rf repo &&
+	mkdir repo &&
+	(
+		cd repo &&
+		git init &&
+		echo "*.a filter=bug" >.gitattributes &&
+		cp "$TEST_ROOT/test.o" invalid-delay.a &&
+		cp "$TEST_ROOT/test.o" unfiltered
+		git add . &&
+		git commit -m "test commit"
+	) &&
+
+	rm -rf repo-cloned &&
+	test_must_fail git clone repo repo-cloned 2>git-stderr.log &&
+	grep "error: external filter .* signaled that .unfiltered. is now available although it has not been delayed earlier" git-stderr.log
+'
+
 test_done