[PATCH] diff: batch fetching of missing blobs

From

JTJonathan Tan <jonathantanmy@google.com>

Date

Mar 26, 2019, 22:09 UTC

Message-ID

<20190326220906.111879-1-jonathantanmy@google.com>

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
Here's an improvement for those having partial clones.

I couldn't find a good place to place the test (a place that checks how
diff interfaces with the object store would be ideal), so I created a
new one. Let me know if there's a better place to put it.
---
 diff.c                        | 27 +++++++++++++
 t/t4067-diff-partial-clone.sh | 76 +++++++++++++++++++++++++++++++++++
 2 files changed, 103 insertions(+)
 create mode 100755 t/t4067-diff-partial-clone.sh

diff --git a/diff.c b/diff.c
index ec5c095199..0e08d05b14 100644
--- a/diff.c
+++ b/diff.c
@@ -25,6 +25,7 @@
 #include "packfile.h"
 #include "parse-options.h"
 #include "help.h"
+#include "fetch-object.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -6067,6 +6068,32 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 	if (o->color_moved)
 		o->emitted_symbols = &esm;
 
+	if (repository_format_partial_clone) {
+		/*
+		 * Prefetch the diff pairs that are about to be flushed.
+		 */
+		struct oid_array to_fetch = OID_ARRAY_INIT;
+		int fetch_if_missing_store = fetch_if_missing;
+
+		fetch_if_missing = 0;
+		for (i = 0; i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+			if (!check_pair_status(p))
+				continue;
+			if (p->one && p->one->oid_valid &&
+			    !has_object_file(&p->one->oid))
+				oid_array_append(&to_fetch, &p->one->oid);
+			if (p->two && p->two->oid_valid &&
+			    !has_object_file(&p->two->oid))
+				oid_array_append(&to_fetch, &p->two->oid);
+		}
+		if (to_fetch.nr)
+			fetch_objects(repository_format_partial_clone,
+				      to_fetch.oid, to_fetch.nr);
+		fetch_if_missing = fetch_if_missing_store;
+		oid_array_clear(&to_fetch);
+	}
+
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
 		if (check_pair_status(p))
diff --git a/t/t4067-diff-partial-clone.sh b/t/t4067-diff-partial-clone.sh
new file mode 100755
index 0000000000..38f03be114
--- /dev/null
+++ b/t/t4067-diff-partial-clone.sh
@@ -0,0 +1,76 @@
+#!/bin/sh
+
+test_description='behavior of diff when reading objects in a partial clone'
+
+. ./test-lib.sh
+
+test_expect_success 'git show batches blobs' '
+	test_create_repo server &&
+	echo a >server/a &&
+	echo b >server/b &&
+	git -C server add a b &&
+	git -C server commit -m x &&
+
+	test_config -C server uploadpack.allowfilter 1 &&
+	test_config -C server uploadpack.allowanysha1inwant 1 &&
+	git clone --bare --filter=blob:limit=0 "file://$(pwd)/server" client &&
+
+	# Ensure that there is exactly 1 negotiation by checking that there is
+	# only 1 "done" line sent. ("done" marks the end of negotiation.)
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client show HEAD &&
+	grep "git> done" trace >done_lines &&
+	test_line_count = 1 done_lines
+'
+
+test_expect_success 'diff batches blobs' '
+	rm -rf server client trace &&
+
+	test_create_repo server &&
+	echo a >server/a &&
+	echo b >server/b &&
+	git -C server add a b &&
+	git -C server commit -m x &&
+	echo c >server/c &&
+	echo d >server/d &&
+	git -C server add c d &&
+	git -C server commit -m x &&
+
+	test_config -C server uploadpack.allowfilter 1 &&
+	test_config -C server uploadpack.allowanysha1inwant 1 &&
+	git clone --bare --filter=blob:limit=0 "file://$(pwd)/server" client &&
+
+	# Ensure that there is exactly 1 negotiation by checking that there is
+	# only 1 "done" line sent. ("done" marks the end of negotiation.)
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client diff HEAD^ HEAD &&
+	grep "git> done" trace >done_lines &&
+	test_line_count = 1 done_lines
+'
+
+test_expect_success 'diff skips same-OID blobs' '
+	rm -rf server client trace &&
+
+	test_create_repo server &&
+	echo a >server/a &&
+	echo b >server/b &&
+	git -C server add a b &&
+	git -C server commit -m x &&
+	echo another-a >server/a &&
+	git -C server add a &&
+	git -C server commit -m x &&
+
+	test_config -C server uploadpack.allowfilter 1 &&
+	test_config -C server uploadpack.allowanysha1inwant 1 &&
+	git clone --bare --filter=blob:limit=0 "file://$(pwd)/server" client &&
+
+	echo a | git hash-object --stdin >hash-old-a &&
+	echo another-a | git hash-object --stdin >hash-new-a &&
+	echo b | git hash-object --stdin >hash-b &&
+
+	# Ensure that only a and another-a are fetched.
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client diff HEAD^ HEAD &&
+	grep "want $(cat hash-old-a)" trace &&
+	grep "want $(cat hash-new-a)" trace &&
+	! grep "want $(cat hash-b)" trace
+'
+
+test_done

-- 
2.21.0.155.ge902e9bcae.dirty