cache-tree: prefetch in partial clone read-tree

jonathantanmy · gitster · commit d3da223f2214 · 2021-07-23T14:22:21.000-07:00
"git read-tree" checks the existence of the blobs referenced by the
given tree, but does not bulk prefetch them. Add a bulk prefetch.

The lack of prefetch here was noticed at $DAYJOB during a merge
involving some specific commits, but I couldn't find a minimal merge
that didn't also trigger the prefetch in check_updates() in
unpack-trees.c (and in all these cases, the lack of prefetch in
cache-tree.c didn't matter because all the relevant blobs would have
already been prefetched by then). This is why I used read-tree here to
exercise this code path.

Signed-off-by: Jonathan Tan &lt;jonathantanmy@google.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/cache-tree.c b/cache-tree.c
@@ -237,6 +237,11 @@ int cache_tree_fully_valid(struct cache_tree *it)
 	return 1;
 }
 
+static int must_check_existence(const struct cache_entry *ce)
+{
+	return !(has_promisor_remote() && ce_skip_worktree(ce));
+}
+
 static int update_one(struct cache_tree *it,
 		      struct cache_entry **cache,
 		      int entries,
@@ -378,8 +383,7 @@ static int update_one(struct cache_tree *it,
 		}
 
 		ce_missing_ok = mode == S_IFGITLINK || missing_ok ||
-			(has_promisor_remote() &&
-			 ce_skip_worktree(ce));
+			!must_check_existence(ce);
 		if (is_null_oid(oid) ||
 		    (!ce_missing_ok && !has_object_file(oid))) {
 			strbuf_release(&buffer);
@@ -466,6 +470,9 @@ int cache_tree_update(struct index_state *istate, int flags)
 	if (!istate->cache_tree)
 		istate->cache_tree = cache_tree();
 
+	if (!(flags & WRITE_TREE_MISSING_OK) && has_promisor_remote())
+		prefetch_cache_entries(istate, must_check_existence);
+
 	trace_performance_enter();
 	trace2_region_enter("cache_tree", "update", the_repository);
 	i = update_one(istate->cache_tree, istate->cache, istate->cache_nr,
diff --git a/t/t1022-read-tree-partial-clone.sh b/t/t1022-read-tree-partial-clone.sh
@@ -0,0 +1,33 @@
+#!/bin/sh
+
+test_description='git read-tree in partial clones'
+
+TEST_NO_CREATE_REPO=1
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+
+test_expect_success 'read-tree in partial clone prefetches in one batch' '
+	test_when_finished "rm -rf server client trace" &&
+
+	git init server &&
+	echo foo >server/one &&
+	echo bar >server/two &&
+	git -C server add one two &&
+	git -C server commit -m "initial commit" &&
+	TREE=$(git -C server rev-parse HEAD^{tree}) &&
+
+	git -C server config uploadpack.allowfilter 1 &&
+	git -C server config uploadpack.allowanysha1inwant 1 &&
+	git clone --bare --filter=blob:none "file://$(pwd)/server" client &&
+	GIT_TRACE_PACKET="$(pwd)/trace" git -C client read-tree $TREE &&
+
+	# "done" marks the end of negotiation (once per fetch). Expect that
+	# only one fetch occurs.
+	grep "fetch> done" trace >donelines &&
+	test_line_count = 1 donelines
+'
+
+test_done
