Merge branch 'ew/many-alternate-optim'

Optimization for repositories with many alternate object store.

* ew/many-alternate-optim:
  oidtree: a crit-bit tree for odb_loose_cache
  oidcpy_with_padding: constify `src' arg
  make object_directory.loose_objects_subdir_seen a bitmap
  avoid strlen via strbuf_addstr in link_alt_odb_entry
  speed up alt_odb_usable() with many alternates

Author: gitster

Makefile

@@ -726,6 +726,7 @@ TEST_BUILTINS_OBJS += test-mergesort.o
 TEST_BUILTINS_OBJS += test-mktemp.o
 TEST_BUILTINS_OBJS += test-oid-array.o
 TEST_BUILTINS_OBJS += test-oidmap.o
+TEST_BUILTINS_OBJS += test-oidtree.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-parse-options.o
 TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
@@ -850,6 +851,7 @@ LIB_OBJS += branch.o
 LIB_OBJS += bulk-checkin.o
 LIB_OBJS += bundle.o
 LIB_OBJS += cache-tree.o
+LIB_OBJS += cbtree.o
 LIB_OBJS += chdir-notify.o
 LIB_OBJS += checkout.o
 LIB_OBJS += chunk-format.o
@@ -945,6 +947,7 @@ LIB_OBJS += object.o
 LIB_OBJS += oid-array.o
 LIB_OBJS += oidmap.o
 LIB_OBJS += oidset.o
+LIB_OBJS += oidtree.o
 LIB_OBJS += pack-bitmap-write.o
 LIB_OBJS += pack-bitmap.o
 LIB_OBJS += pack-check.o

cbtree.c

@@ -0,0 +1,167 @@
+/*
+ * crit-bit tree implementation, does no allocations internally
+ * For more information on crit-bit trees: https://cr.yp.to/critbit.html
+ * Based on Adam Langley's adaptation of Dan Bernstein's public domain code
+ * git clone https://github.com/agl/critbit.git
+ */
+#include "cbtree.h"
+
+static struct cb_node *cb_node_of(const void *p)
+{
+	return (struct cb_node *)((uintptr_t)p - 1);
+}
+
+/* locate the best match, does not do a final comparision */
+static struct cb_node *cb_internal_best_match(struct cb_node *p,
+					const uint8_t *k, size_t klen)
+{
+	while (1 & (uintptr_t)p) {
+		struct cb_node *q = cb_node_of(p);
+		uint8_t c = q->byte < klen ? k[q->byte] : 0;
+		size_t direction = (1 + (q->otherbits | c)) >> 8;
+
+		p = q->child[direction];
+	}
+	return p;
+}
+
+/* returns NULL if successful, existing cb_node if duplicate */
+struct cb_node *cb_insert(struct cb_tree *t, struct cb_node *node, size_t klen)
+{
+	size_t newbyte, newotherbits;
+	uint8_t c;
+	int newdirection;
+	struct cb_node **wherep, *p;
+
+	assert(!((uintptr_t)node & 1)); /* allocations must be aligned */
+
+	if (!t->root) {		/* insert into empty tree */
+		t->root = node;
+		return NULL;	/* success */
+	}
+
+	/* see if a node already exists */
+	p = cb_internal_best_match(t->root, node->k, klen);
+
+	/* find first differing byte */
+	for (newbyte = 0; newbyte < klen; newbyte++) {
+		if (p->k[newbyte] != node->k[newbyte])
+			goto different_byte_found;
+	}
+	return p;	/* element exists, let user deal with it */
+
+different_byte_found:
+	newotherbits = p->k[newbyte] ^ node->k[newbyte];
+	newotherbits |= newotherbits >> 1;
+	newotherbits |= newotherbits >> 2;
+	newotherbits |= newotherbits >> 4;
+	newotherbits = (newotherbits & ~(newotherbits >> 1)) ^ 255;
+	c = p->k[newbyte];
+	newdirection = (1 + (newotherbits | c)) >> 8;
+
+	node->byte = newbyte;
+	node->otherbits = newotherbits;
+	node->child[1 - newdirection] = node;
+
+	/* find a place to insert it */
+	wherep = &t->root;
+	for (;;) {
+		struct cb_node *q;
+		size_t direction;
+
+		p = *wherep;
+		if (!(1 & (uintptr_t)p))
+			break;
+		q = cb_node_of(p);
+		if (q->byte > newbyte)
+			break;
+		if (q->byte == newbyte && q->otherbits > newotherbits)
+			break;
+		c = q->byte < klen ? node->k[q->byte] : 0;
+		direction = (1 + (q->otherbits | c)) >> 8;
+		wherep = q->child + direction;
+	}
+
+	node->child[newdirection] = *wherep;
+	*wherep = (struct cb_node *)(1 + (uintptr_t)node);
+
+	return NULL; /* success */
+}
+
+struct cb_node *cb_lookup(struct cb_tree *t, const uint8_t *k, size_t klen)
+{
+	struct cb_node *p = cb_internal_best_match(t->root, k, klen);
+
+	return p && !memcmp(p->k, k, klen) ? p : NULL;
+}
+
+struct cb_node *cb_unlink(struct cb_tree *t, const uint8_t *k, size_t klen)
+{
+	struct cb_node **wherep = &t->root;
+	struct cb_node **whereq = NULL;
+	struct cb_node *q = NULL;
+	size_t direction = 0;
+	uint8_t c;
+	struct cb_node *p = t->root;
+
+	if (!p) return NULL;	/* empty tree, nothing to delete */
+
+	/* traverse to find best match, keeping link to parent */
+	while (1 & (uintptr_t)p) {
+		whereq = wherep;
+		q = cb_node_of(p);
+		c = q->byte < klen ? k[q->byte] : 0;
+		direction = (1 + (q->otherbits | c)) >> 8;
+		wherep = q->child + direction;
+		p = *wherep;
+	}
+
+	if (memcmp(p->k, k, klen))
+		return NULL;		/* no match, nothing unlinked */
+
+	/* found an exact match */
+	if (whereq)	/* update parent */
+		*whereq = q->child[1 - direction];
+	else
+		t->root = NULL;
+	return p;
+}
+
+static enum cb_next cb_descend(struct cb_node *p, cb_iter fn, void *arg)
+{
+	if (1 & (uintptr_t)p) {
+		struct cb_node *q = cb_node_of(p);
+		enum cb_next n = cb_descend(q->child[0], fn, arg);
+
+		return n == CB_BREAK ? n : cb_descend(q->child[1], fn, arg);
+	} else {
+		return fn(p, arg);
+	}
+}
+
+void cb_each(struct cb_tree *t, const uint8_t *kpfx, size_t klen,
+			cb_iter fn, void *arg)
+{
+	struct cb_node *p = t->root;
+	struct cb_node *top = p;
+	size_t i = 0;
+
+	if (!p) return; /* empty tree */
+
+	/* Walk tree, maintaining top pointer */
+	while (1 & (uintptr_t)p) {
+		struct cb_node *q = cb_node_of(p);
+		uint8_t c = q->byte < klen ? kpfx[q->byte] : 0;
+		size_t direction = (1 + (q->otherbits | c)) >> 8;
+
+		p = q->child[direction];
+		if (q->byte < klen)
+			top = p;
+	}
+
+	for (i = 0; i < klen; i++) {
+		if (p->k[i] != kpfx[i])
+			return; /* "best" match failed */
+	}
+	cb_descend(top, fn, arg);
+}

cbtree.h

@@ -0,0 +1,56 @@
+/*
+ * crit-bit tree implementation, does no allocations internally
+ * For more information on crit-bit trees: https://cr.yp.to/critbit.html
+ * Based on Adam Langley's adaptation of Dan Bernstein's public domain code
+ * git clone https://github.com/agl/critbit.git
+ *
+ * This is adapted to store arbitrary data (not just NUL-terminated C strings
+ * and allocates no memory internally.  The user needs to allocate
+ * "struct cb_node" and fill cb_node.k[] with arbitrary match data
+ * for memcmp.
+ * If "klen" is variable, then it should be embedded into "c_node.k[]"
+ * Recursion is bound by the maximum value of "klen" used.
+ */
+#ifndef CBTREE_H
+#define CBTREE_H
+
+#include "git-compat-util.h"
+
+struct cb_node;
+struct cb_node {
+	struct cb_node *child[2];
+	/*
+	 * n.b. uint32_t for `byte' is excessive for OIDs,
+	 * we may consider shorter variants if nothing else gets stored.
+	 */
+	uint32_t byte;
+	uint8_t otherbits;
+	uint8_t k[FLEX_ARRAY]; /* arbitrary data */
+};
+
+struct cb_tree {
+	struct cb_node *root;
+};
+
+enum cb_next {
+	CB_CONTINUE = 0,
+	CB_BREAK = 1
+};
+
+#define CBTREE_INIT { .root = NULL }
+
+static inline void cb_init(struct cb_tree *t)
+{
+	t->root = NULL;
+}
+
+struct cb_node *cb_lookup(struct cb_tree *, const uint8_t *k, size_t klen);
+struct cb_node *cb_insert(struct cb_tree *, struct cb_node *, size_t klen);
+struct cb_node *cb_unlink(struct cb_tree *t, const uint8_t *k, size_t klen);
+
+typedef enum cb_next (*cb_iter)(struct cb_node *, void *arg);
+
+void cb_each(struct cb_tree *, const uint8_t *kpfx, size_t klen,
+		cb_iter, void *arg);
+
+#endif /* CBTREE_H */

dir.c

@@ -78,11 +78,21 @@ int fspathcmp(const char *a, const char *b)
 	return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
 }
 
+int fspatheq(const char *a, const char *b)
+{
+	return !fspathcmp(a, b);
+}
+
 int fspathncmp(const char *a, const char *b, size_t count)
 {
 	return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
 }
 
+unsigned int fspathhash(const char *str)
+{
+	return ignore_case ? strihash(str) : strhash(str);
+}
+
 int git_fnmatch(const struct pathspec_item *item,
 		const char *pattern, const char *string,
 		int prefix)

dir.h

@@ -489,7 +489,9 @@ int remove_dir_recursively(struct strbuf *path, int flag);
 int remove_path(const char *path);
 
 int fspathcmp(const char *a, const char *b);
+int fspatheq(const char *a, const char *b);
 int fspathncmp(const char *a, const char *b, size_t count);
+unsigned int fspathhash(const char *str);
 
 /*
  * The prefix part of pattern must not contains wildcards.

hash.h

@@ -265,7 +265,7 @@ static inline void oidcpy(struct object_id *dst, const struct object_id *src)
 
 /* Like oidcpy() but zero-pads the unused bytes in dst's hash array. */
 static inline void oidcpy_with_padding(struct object_id *dst,
-				       struct object_id *src)
+				       const struct object_id *src)
 {
 	size_t hashsz;