Merge branch 'jt/batch-fetch-blobs-in-diff'

While running "git diff" in a lazy clone, we can upfront know which
missing blobs we will need, instead of waiting for the on-demand
machinery to discover them one by one.  Aim to achieve better
performance by batching the request for these promised blobs.

* jt/batch-fetch-blobs-in-diff:
  diff: batch fetching of missing blobs
  sha1-file: support OBJECT_INFO_FOR_PREFETCH

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
@@ -6477,8 +6478,41 @@ void diffcore_fix_diff_index(void)
 	QSORT(q->queue, q->nr, diffnamecmp);
 }
 
+static void add_if_missing(struct repository *r,
+			   struct oid_array *to_fetch,
+			   const struct diff_filespec *filespec)
+{
+	if (filespec && filespec->oid_valid &&
+	    oid_object_info_extended(r, &filespec->oid, NULL,
+				     OBJECT_INFO_FOR_PREFETCH))
+		oid_array_append(to_fetch, &filespec->oid);
+}
+
 void diffcore_std(struct diff_options *options)
 {
+	if (options->repo == the_repository &&
+	    repository_format_partial_clone) {
+		/*
+		 * Prefetch the diff pairs that are about to be flushed.
+		 */
+		int i;
+		struct diff_queue_struct *q = &diff_queued_diff;
+		struct oid_array to_fetch = OID_ARRAY_INIT;
+
+		for (i = 0; i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+			add_if_missing(options->repo, &to_fetch, p->one);
+			add_if_missing(options->repo, &to_fetch, p->two);
+		}
+		if (to_fetch.nr)
+			/*
+			 * NEEDSWORK: Consider deduplicating the OIDs sent.
+			 */
+			fetch_objects(repository_format_partial_clone,
+				      to_fetch.oid, to_fetch.nr);
+		oid_array_clear(&to_fetch);
+	}
+
 	/* NOTE please keep the following in sync with diff_tree_combined() */
 	if (options->skip_stat_unmatch)
 		diffcore_skip_stat_unmatch(options);

object-store.h

@@ -280,6 +280,12 @@ struct object_info {
 #define OBJECT_INFO_QUICK 8
 /* Do not check loose object */
 #define OBJECT_INFO_IGNORE_LOOSE 16
+/*
+ * Do not attempt to fetch the object if missing (even if fetch_is_missing is
+ * nonzero). This is meant for bulk prefetching of missing blobs in a partial
+ * clone. Implies OBJECT_INFO_QUICK.
+ */
+#define OBJECT_INFO_FOR_PREFETCH (32 + OBJECT_INFO_QUICK)
 
 int oid_object_info_extended(struct repository *r,
 			     const struct object_id *,

sha1-file.c

@@ -1378,7 +1378,8 @@ int oid_object_info_extended(struct repository *r, const struct object_id *oid,
 
 		/* Check if it is a missing object */
 		if (fetch_if_missing && repository_format_partial_clone &&
-		    !already_retried && r == the_repository) {
+		    !already_retried && r == the_repository &&
+		    !(flags & OBJECT_INFO_FOR_PREFETCH)) {
 			/*
 			 * TODO Investigate having fetch_object() return
 			 * TODO error/success and stopping the music here.

t/t4067-diff-partial-clone.sh

@@ -0,0 +1,103 @@
+#!/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_when_finished "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 &&
+
+	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' '
+	test_when_finished "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' '
+	test_when_finished "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 $(cat hash-b)" trace
+'
+
+test_expect_success 'diff with rename detection batches blobs' '
+	test_when_finished "rm -rf server client trace" &&
+
+	test_create_repo server &&
+	echo a >server/a &&
+	printf "b\nb\nb\nb\nb\n" >server/b &&
+	git -C server add a b &&
+	git -C server commit -m x &&
+	rm server/b &&
+	printf "b\nb\nb\nb\nbX\n" >server/c &&
+	git -C server add c &&
+	git -C server commit -a -m x &&
+
+	test_config -C server uploadpack.allowfilter 1 &&
+	test_config -C server uploadpack.allowanysha1inwant 1 &&
+	git clone --bare --filter=blob:limit=0 "file://$(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 -M HEAD^ HEAD >out &&
+	grep "similarity index" out &&
+	grep "git> done" trace >done_lines &&
+	test_line_count = 1 done_lines
+'
+
+test_done

unpack-trees.c

@@ -406,20 +406,21 @@ static int check_updates(struct unpack_trees_options *o)
 		 * below.
 		 */
 		struct oid_array to_fetch = OID_ARRAY_INIT;
-		int fetch_if_missing_store = fetch_if_missing;
-		fetch_if_missing = 0;
 		for (i = 0; i < index->cache_nr; i++) {
 			struct cache_entry *ce = index->cache[i];
-			if ((ce->ce_flags & CE_UPDATE) &&
+
-			    !S_ISGITLINK(ce->ce_mode)) {
+			if (!(ce->ce_flags & CE_UPDATE) ||
-				if (!has_object_file(&ce->oid))
+			    S_ISGITLINK(ce->ce_mode))
-					oid_array_append(&to_fetch, &ce->oid);
+				continue;
-			}
+			if (!oid_object_info_extended(the_repository, &ce->oid,
+						      NULL,
+						      OBJECT_INFO_FOR_PREFETCH))
+				continue;
+			oid_array_append(&to_fetch, &ce->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 < index->cache_nr; i++) {