Batch prefetching

builtin/log.c

@@ -21,10 +21,12 @@
 #include "color.h"
 #include "commit.h"
 #include "diff.h"
+#include "diffcore.h"
 #include "diff-merges.h"
 #include "revision.h"
 #include "log-tree.h"
 #include "oid-array.h"
+#include "oidset.h"
 #include "tag.h"
 #include "reflog-walk.h"
 #include "patch-ids.h"
@@ -43,9 +45,11 @@
 #include "utf8.h"
 
 #include "commit-reach.h"
+#include "promisor-remote.h"
 #include "range-diff.h"
 #include "tmp-objdir.h"
 #include "tree.h"
+#include "userdiff.h"
 #include "write-or-die.h"
 
 #define MAIL_DEFAULT_WRAP 72
@@ -2602,6 +2606,125 @@ static void print_commit(char sign, struct commit *commit, int verbose,
 	}
 }
 
+/*
+ * Enumerate blob OIDs from a single commit's diff, inserting them into blobs.
+ * Skips files whose userdiff driver explicitly declares binary status
+ * (drv->binary > 0), since patch-ID uses oid_to_hex() for those and
+ * never reads blob content.  Use userdiff_find_by_path() since
+ * diff_filespec_load_driver() is static in diff.c.
+ *
+ * Clean up with diff_queue_clear() (from diffcore.h).
+ */
+static void collect_diff_blob_oids(struct commit *commit,
+				   struct diff_options *opts,
+				   struct oidset *blobs)
+{
+	struct diff_queue_struct *q;
+
+	/*
+	 * Merge commits are filtered out by patch_id_defined() in patch-ids.c,
+	 * so we'll never be called with one.
+	 */
+	assert(!commit->parents || !commit->parents->next);
+
+	if (commit->parents)
+		diff_tree_oid(&commit->parents->item->object.oid,
+			      &commit->object.oid, "", opts);
+	else
+		diff_root_tree_oid(&commit->object.oid, "", opts);
+	diffcore_std(opts);
+
+	q = &diff_queued_diff;
+	for (int i = 0; i < q->nr; i++) {
+		struct diff_filepair *p = q->queue[i];
+		struct userdiff_driver *drv;
+
+		/* Skip binary files */
+		drv = userdiff_find_by_path(opts->repo->index, p->one->path);
+		if (drv && drv->binary > 0)
+			continue;
+
+		if (DIFF_FILE_VALID(p->one))
+			oidset_insert(blobs, &p->one->oid);
+		if (DIFF_FILE_VALID(p->two))
+			oidset_insert(blobs, &p->two->oid);
+	}
+	diff_queue_clear(q);
+}
+
+static int always_match(const void *cmp_data UNUSED,
+			const struct hashmap_entry *entry1 UNUSED,
+			const struct hashmap_entry *entry2 UNUSED,
+			const void *keydata UNUSED)
+{
+	return 0;
+}
+
+/*
+ * Prefetch blobs for git cherry in partial clones.
+ *
+ * Called between the revision walk (which builds the head-side
+ * commit list) and the has_commit_patch_id() comparison loop.
+ *
+ * Uses a cmpfn-swap trick to avoid reading blobs: temporarily
+ * replaces the hashmap's comparison function with a trivial
+ * always-match function, so hashmap_get()/hashmap_get_next() match
+ * any entry with the same oidhash bucket.  These are the set of oids
+ * that would trigger patch_id_neq() during normal lookup and cause
+ * blobs to be read on demand, and we want to prefetch them all at
+ * once instead.
+ */
+static void prefetch_cherry_blobs(struct repository *repo,
+				  struct commit_list *list,
+				  struct patch_ids *ids)
+{
+	struct oidset blobs = OIDSET_INIT;
+	hashmap_cmp_fn original_cmpfn;
+
+	/* Exit if we're not in a partial clone */
+	if (!repo_has_promisor_remote(repo))
+		return;
+
+	/* Save original cmpfn, replace with always_match */
+	original_cmpfn = ids->patches.cmpfn;
+	ids->patches.cmpfn = always_match;
+
+	/* Find header-only collisions, gather blobs from those commits */
+	for (struct commit_list *l = list; l; l = l->next) {
+		struct commit *c = l->item;
+		bool match_found = false;
+		for (struct patch_id *cur = patch_id_iter_first(c, ids);
+		     cur;
+		     cur = patch_id_iter_next(cur, ids)) {
+			match_found = true;
+			collect_diff_blob_oids(cur->commit, &ids->diffopts,
+					       &blobs);
+		}
+		if (match_found)
+			collect_diff_blob_oids(c, &ids->diffopts, &blobs);
+	}
+
+	/* Restore original cmpfn */
+	ids->patches.cmpfn = original_cmpfn;
+
+	/* If we have any blobs to fetch, fetch them */
+	if (oidset_size(&blobs)) {
+		struct oid_array to_fetch = OID_ARRAY_INIT;
+		struct oidset_iter iter;
+		const struct object_id *oid;
+
+		oidset_iter_init(&blobs, &iter);
+		while ((oid = oidset_iter_next(&iter)))
+			oid_array_append(&to_fetch, oid);
+
+		promisor_remote_get_direct(repo, to_fetch.oid, to_fetch.nr);
+
+		oid_array_clear(&to_fetch);
+	}
+
+	oidset_clear(&blobs);
+}
+
 int cmd_cherry(int argc,
 	       const char **argv,
 	       const char *prefix,
@@ -2673,6 +2796,8 @@ int cmd_cherry(int argc,
 		commit_list_insert(commit, &list);
 	}
 
+	prefetch_cherry_blobs(the_repository, list, &ids);
+
 	for (struct commit_list *l = list; l; l = l->next) {
 		char sign = '+';
 

patch-ids.h

@@ -37,7 +37,7 @@ int has_commit_patch_id(struct commit *commit, struct patch_ids *);
  *   struct patch_id *cur;
  *   for (cur = patch_id_iter_first(commit, ids);
  *        cur;
- *        cur = patch_id_iter_next(cur, ids) {
+ *        cur = patch_id_iter_next(cur, ids)) {
  *           ... look at cur->commit
  *   }
  */

t/t3500-cherry.sh

@@ -78,4 +78,22 @@ test_expect_success 'cherry ignores whitespace' '
 	test_cmp expect actual
 '
 
+# Reuse the expect file from the previous test, in a partial clone
+test_expect_success 'cherry in partial clone does bulk prefetch' '
+	test_config uploadpack.allowfilter 1 &&
+	test_config uploadpack.allowanysha1inwant 1 &&
+	test_when_finished "rm -rf copy" &&
+
+	git clone --bare --filter=blob:none file://"$(pwd)" copy &&
+	(
+		cd copy &&
+		GIT_TRACE2_EVENT="$(pwd)/trace.output" git cherry upstream-with-space feature-without-space >actual &&
+		test_cmp ../expect actual &&
+
+		grep "child_start.*fetch.negotiationAlgorithm" trace.output >fetches &&
+		test_line_count = 1 fetches &&
+		test_trace2_data promisor fetch_count 4 <trace.output
+	)
+'
+
 test_done