Merge branch 'jt/bulk-prefetch'

"git read-tree" had a codepath where blobs are fetched one-by-one
from the promisor remote, which has been corrected to fetch in bulk.

* jt/bulk-prefetch:
  cache-tree: prefetch in partial clone read-tree
  unpack-trees: refactor prefetching code

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() &&
+			!must_check_existence(ce);
-			 ce_skip_worktree(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,

cache.h

@@ -410,6 +410,15 @@ struct cache_entry *dup_cache_entry(const struct cache_entry *ce, struct index_s
  */
 void validate_cache_entries(const struct index_state *istate);
 
+/*
+ * Bulk prefetch all missing cache entries that are not GITLINKs and that match
+ * the given predicate. This function should only be called if
+ * has_promisor_remote() returns true.
+ */
+typedef int (*must_prefetch_predicate)(const struct cache_entry *);
+void prefetch_cache_entries(const struct index_state *istate,
+			    must_prefetch_predicate must_prefetch);
+
 #ifdef USE_THE_INDEX_COMPATIBILITY_MACROS
 extern struct index_state the_index;
 

read-cache.c

@@ -27,6 +27,7 @@
 #include "progress.h"
 #include "sparse-index.h"
 #include "csum-file.h"
+#include "promisor-remote.h"
 
 /* Mask for the name length in ce_flags in the on-disk index */
 
@@ -3663,3 +3664,25 @@ static void write_ieot_extension(struct strbuf *sb, struct index_entry_offset_ta
 		strbuf_add(sb, &buffer, sizeof(uint32_t));
 	}
 }
+
+void prefetch_cache_entries(const struct index_state *istate,
+			    must_prefetch_predicate must_prefetch)
+{
+	int i;
+	struct oid_array to_fetch = OID_ARRAY_INIT;
+
+	for (i = 0; i < istate->cache_nr; i++) {
+		struct cache_entry *ce = istate->cache[i];
+
+		if (S_ISGITLINK(ce->ce_mode) || !must_prefetch(ce))
+			continue;
+		if (!oid_object_info_extended(the_repository, &ce->oid,
+					      NULL,
+					      OBJECT_INFO_FOR_PREFETCH))
+			continue;
+		oid_array_append(&to_fetch, &ce->oid);
+	}
+	promisor_remote_get_direct(the_repository,
+				   to_fetch.oid, to_fetch.nr);
+	oid_array_clear(&to_fetch);
+}

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

unpack-trees.c

@@ -392,6 +392,11 @@ static void report_collided_checkout(struct index_state *index)
 	string_list_clear(&list, 0);
 }
 
+static int must_checkout(const struct cache_entry *ce)
+{
+	return ce->ce_flags & CE_UPDATE;
+}
+
 static int check_updates(struct unpack_trees_options *o,
 			 struct index_state *index)
 {
@@ -442,28 +447,12 @@ static int check_updates(struct unpack_trees_options *o,
 	if (should_update_submodules())
 		load_gitmodules_file(index, &state);
 
-	if (has_promisor_remote()) {
+	if (has_promisor_remote())
 		/*
 		 * Prefetch the objects that are to be checked out in the loop
 		 * below.
 		 */
-		struct oid_array to_fetch = OID_ARRAY_INIT;
+		prefetch_cache_entries(index, must_checkout);
-		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))
-				continue;
-			if (!oid_object_info_extended(the_repository, &ce->oid,
-						      NULL,
-						      OBJECT_INFO_FOR_PREFETCH))
-				continue;
-			oid_array_append(&to_fetch, &ce->oid);
-		}
-		promisor_remote_get_direct(the_repository,
-					   to_fetch.oid, to_fetch.nr);
-		oid_array_clear(&to_fetch);
-	}
 
 	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
 
@@ -473,7 +462,7 @@ static int check_updates(struct unpack_trees_options *o,
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
-		if (ce->ce_flags & CE_UPDATE) {
+		if (must_checkout(ce)) {
 			size_t last_pc_queue_size = pc_queue_size();
 
 			if (ce->ce_flags & CE_WT_REMOVE)