[PATCH 06/10] sparse-checkout: use oidset to prevent repeat blobs

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: May 7, 2020, 13:17 UTC
Message-ID: <fcf948bda7aebcc5f88c17f5b308b2ce0cc285f5.1588857462.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.627.git.1588857462.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

As we parse the in-tree config files that store the sparse.dir values used to create an in-tree sparse-checkout definition, we can easily avoid parsing the same file multiple times by using an oidset on those blobs. We only parse if the oid is new to the oidset.

This is unlikely to have a major performance benefit right now, but will be extremely important when we introduce the sparse.inherit options to link multiple files in a directed graph. This oidset will prevent infinite loops when cycles exist in that digraph, or exponential blowups even in the case of a directed acyclic graph.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 sparse-checkout.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/sparse-checkout.c b/sparse-checkout.c
index 6c58fda9722..d01f4d7b525 100644
--- a/sparse-checkout.c
+++ b/sparse-checkout.c
@@ -9,6 +9,7 @@
 #include "string-list.h"
 #include "unpack-trees.h"
 #include "object-store.h"
+#include "oidset.h"
 
 char *get_sparse_checkout_filename(void)
 {
@@ -77,9 +78,12 @@ int load_in_tree_pattern_list(struct repository *r,
 			      struct string_list *sl,
 			      struct pattern_list *pl)
 {
+	int result = 0;
 	struct index_state *istate = r->index;
 	struct string_list_item *item;
 	struct strbuf path = STRBUF_INIT;
+	struct oidset set;
+	oidset_init(&set, 16);
 
 	pl->use_cone_patterns = 1;
 
@@ -96,24 +100,34 @@ int load_in_tree_pattern_list(struct repository *r,
 		 * Use -1 return to ensure populate_from_existing_patterns()
 		 * skips the sparse-checkout updates.
 		 */
-		if (pos < 0)
-			return -1;
+		if (pos < 0) {
+			result = -1;
+			goto cleanup;
+		}
 
 		oid = &istate->cache[pos]->oid;
+
+		if (oidset_contains(&set, oid))
+			continue;
+
+		oidset_insert(&set, oid);
+
 		type = oid_object_info(r, oid, NULL);
 
 		if (type != OBJ_BLOB) {
 			warning(_("expected a file at '%s'; not updating sparse-checkout"),
 				oid_to_hex(oid));
-			return 1;
+			result = 1;
+			goto cleanup;
 		}
 
 		load_in_tree_from_blob(pl, oid);
 	}
 
+cleanup:
 	strbuf_release(&path);
-
-	return 0;
+	oidset_clear(&set);
+	return result;
 }
 
 int populate_sparse_checkout_patterns(struct pattern_list *pl)

-- 
gitgitgadget