read-cache: speed up add_index_entry during checkout

Teach add_index_entry_with_check() and has_dir_name()
to see if the path of the new item is greater than the
last path in the index array before attempting to search
for it.

This is a performance optimization.

During checkout, merge_working_tree() populates the new
index in sorted order, so this change saves at least 2
lookups per file.

Signed-off-by: Jeff Hostetler <[email protected]>

Author: jeffhostetler

cache.h

@@ -572,6 +572,7 @@ extern int write_locked_index(struct index_state *, struct lock_file *lock, unsi
 extern int discard_index(struct index_state *);
 extern int unmerged_index(const struct index_state *);
 extern int verify_path(const char *path);
+extern int strcmp_offset(const char *s1_in, const char *s2_in, int *first_change);
 extern int index_dir_exists(struct index_state *istate, const char *name, int namelen);
 extern void adjust_dirname_case(struct index_state *istate, char *name);
 extern struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int igncase);

read-cache.c

@@ -894,6 +894,34 @@ static int has_file_name(struct index_state *istate,
 	return retval;
 }
 
+/*
+ * Like strcmp(), but also return the offset of the first change.
+ */
+int strcmp_offset(const char *s1_in, const char *s2_in, int *first_change)
+{
+	const unsigned char *s1 = (const unsigned char *)s1_in;
+	const unsigned char *s2 = (const unsigned char *)s2_in;
+	int diff = 0;
+	int k;
+
+	*first_change = 0;
+	for (k=0; s1[k]; k++)
+		if ((diff = (s1[k] - s2[k])))
+			goto found_it;
+	if (!s2[k])
+		return 0;
+	diff = -1;
+
+found_it:
+	*first_change = k;
+	if (diff > 0)
+		return 1;
+	else if (diff < 0)
+		return -1;
+	else
+		return 0;
+}
+
 /*
  * Do we have another file with a pathname that is a proper
  * subset of the name we're trying to add?
@@ -905,6 +933,21 @@ static int has_dir_name(struct index_state *istate,
 	int stage = ce_stage(ce);
 	const char *name = ce->name;
 	const char *slash = name + ce_namelen(ce);
+	int len_eq_last;
+	int cmp_last = 0;
+
+	if (istate->cache_nr > 0) {
+		/*
+		 * Compare the entry's full path with the last path in the index.
+		 * If it sorts AFTER the last entry in the index and they have no
+		 * common prefix, then there cannot be any F/D name conflicts.
+		 */
+		cmp_last = strcmp_offset(name,
+			istate->cache[istate->cache_nr-1]->name,
+			&len_eq_last);
+		if (cmp_last > 0 && len_eq_last == 0)
+			return retval;
+	}
 
 	for (;;) {
 		int len;
@@ -917,6 +960,24 @@ static int has_dir_name(struct index_state *istate,
 		}
 		len = slash - name;
 
+		if (cmp_last > 0) {
+			/*
+			 * If this part of the directory prefix (including the trailing
+			 * slash) already appears in the path of the last entry in the
+			 * index, then we cannot also have a file with this prefix (or
+			 * any parent directory prefix).
+			 */
+			if (len+1 <= len_eq_last)
+				return retval;
+			/*
+			 * If this part of the directory prefix (excluding the trailing
+			 * slash) is longer than the known equal portions, then this part
+			 * of the prefix cannot collide with a file.  Go on to the parent.
+			 */
+			if (len > len_eq_last)
+				continue;
+		}
+
 		pos = index_name_stage_pos(istate, name, len, stage);
 		if (pos >= 0) {
 			/*
@@ -1008,7 +1069,16 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
 
 	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
 		cache_tree_invalidate_path(istate, ce->name);
-	pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
+
+	/*
+	 * If this entry's path sorts after the last entry in the index,
+	 * we can avoid searching for it.
+	 */
+	if (istate->cache_nr > 0 &&
+		strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0)
+		pos = -istate->cache_nr - 1;
+	else
+		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
 
 	/* existing match? Just replace it. */
 	if (pos >= 0) {