reftable: a generic binary tree implementation

The reftable format includes support for an (OID => ref) map. This map can speed
up visibility and reachability checks. In particular, various operations along
the fetch/push path within Gerrit have ben sped up by using this structure.

The map is constructed with help of a binary tree. Object IDs are hashes, so
they are uniformly distributed. Hence, the tree does not attempt forced
rebalancing.

Signed-off-by: Han-Wen Nienhuys <hanwen@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 162 insertions, 1 deletions

diff --git a/Makefile b/Makefile
index 65bd39e..2e5a9f4 100644
--- a/Makefile
+++ b/Makefile
@@ -2462,11 +2462,13 @@ REFTABLE_OBJS += reftable/block.o
 REFTABLE_OBJS += reftable/blocksource.o
 REFTABLE_OBJS += reftable/publicbasics.o
 REFTABLE_OBJS += reftable/record.o
+REFTABLE_OBJS += reftable/tree.o
 
+REFTABLE_TEST_OBJS += reftable/basics_test.o
 REFTABLE_TEST_OBJS += reftable/block_test.o
 REFTABLE_TEST_OBJS += reftable/record_test.o
 REFTABLE_TEST_OBJS += reftable/test_framework.o
-REFTABLE_TEST_OBJS += reftable/basics_test.o
+REFTABLE_TEST_OBJS += reftable/tree_test.o
 
 TEST_OBJS := $(patsubst %$X,%.o,$(TEST_PROGRAMS)) $(patsubst %,t/helper/%,$(TEST_BUILTINS_OBJS))
 
diff --git a/reftable/tree.c b/reftable/tree.c
new file mode 100644
index 0000000..82db799
--- /dev/null
+++ b/reftable/tree.c
@@ -0,0 +1,63 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "tree.h"
+
+#include "basics.h"
+#include "system.h"
+
+struct tree_node *tree_search(void *key, struct tree_node **rootp,
+			      int (*compare)(const void *, const void *),
+			      int insert)
+{
+	int res;
+	if (*rootp == NULL) {
+		if (!insert) {
+			return NULL;
+		} else {
+			struct tree_node *n =
+				reftable_calloc(sizeof(struct tree_node));
+			n->key = key;
+			*rootp = n;
+			return *rootp;
+		}
+	}
+
+	res = compare(key, (*rootp)->key);
+	if (res < 0)
+		return tree_search(key, &(*rootp)->left, compare, insert);
+	else if (res > 0)
+		return tree_search(key, &(*rootp)->right, compare, insert);
+	return *rootp;
+}
+
+void infix_walk(struct tree_node *t, void (*action)(void *arg, void *key),
+		void *arg)
+{
+	if (t->left) {
+		infix_walk(t->left, action, arg);
+	}
+	action(arg, t->key);
+	if (t->right) {
+		infix_walk(t->right, action, arg);
+	}
+}
+
+void tree_free(struct tree_node *t)
+{
+	if (t == NULL) {
+		return;
+	}
+	if (t->left) {
+		tree_free(t->left);
+	}
+	if (t->right) {
+		tree_free(t->right);
+	}
+	reftable_free(t);
+}
diff --git a/reftable/tree.h b/reftable/tree.h
new file mode 100644
index 0000000..fbdd002
--- /dev/null
+++ b/reftable/tree.h
@@ -0,0 +1,34 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#ifndef TREE_H
+#define TREE_H
+
+/* tree_node is a generic binary search tree. */
+struct tree_node {
+	void *key;
+	struct tree_node *left, *right;
+};
+
+/* looks for `key` in `rootp` using `compare` as comparison function. If insert
+ * is set, insert the key if it's not found. Else, return NULL.
+ */
+struct tree_node *tree_search(void *key, struct tree_node **rootp,
+			      int (*compare)(const void *, const void *),
+			      int insert);
+
+/* performs an infix walk of the tree. */
+void infix_walk(struct tree_node *t, void (*action)(void *arg, void *key),
+		void *arg);
+
+/*
+ * deallocates the tree nodes recursively. Keys should be deallocated separately
+ * by walking over the tree. */
+void tree_free(struct tree_node *t);
+
+#endif
diff --git a/reftable/tree_test.c b/reftable/tree_test.c
new file mode 100644
index 0000000..cbff125
--- /dev/null
+++ b/reftable/tree_test.c
@@ -0,0 +1,61 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "tree.h"
+
+#include "basics.h"
+#include "record.h"
+#include "test_framework.h"
+#include "reftable-tests.h"
+
+static int test_compare(const void *a, const void *b)
+{
+	return (char *)a - (char *)b;
+}
+
+struct curry {
+	void *last;
+};
+
+static void check_increasing(void *arg, void *key)
+{
+	struct curry *c = arg;
+	if (c->last) {
+		EXPECT(test_compare(c->last, key) < 0);
+	}
+	c->last = key;
+}
+
+static void test_tree(void)
+{
+	struct tree_node *root = NULL;
+
+	void *values[11] = { NULL };
+	struct tree_node *nodes[11] = { NULL };
+	int i = 1;
+	struct curry c = { NULL };
+	do {
+		nodes[i] = tree_search(values + i, &root, &test_compare, 1);
+		i = (i * 7) % 11;
+	} while (i != 1);
+
+	for (i = 1; i < ARRAY_SIZE(nodes); i++) {
+		EXPECT(values + i == nodes[i]->key);
+		EXPECT(nodes[i] ==
+		       tree_search(values + i, &root, &test_compare, 0));
+	}
+
+	infix_walk(root, check_increasing, &c);
+	tree_free(root);
+}
+
+int tree_test_main(int argc, const char *argv[])
+{
+	RUN_TEST(test_tree);
+	return 0;
+}
diff --git a/t/helper/test-reftable.c b/t/helper/test-reftable.c
index c9deeaf..050551f 100644
--- a/t/helper/test-reftable.c
+++ b/t/helper/test-reftable.c
@@ -6,5 +6,6 @@ int cmd__reftable(int argc, const char **argv)
 	basics_test_main(argc, argv);
 	block_test_main(argc, argv);
 	record_test_main(argc, argv);
+	tree_test_main(argc, argv);
 	return 0;
 }