[PATCH 5/5] name-hash: remember previous dir_entry during lazy_init_name_hash

[Johannes Schindelin <johannes.schindelin@gmx.de>]

From: Jeff Hostetler <jeffhost@microsoft.com>

Teach hash_dir_entry() to remember the previously found dir_entry during
lazy_init_name_hash() iteration. This is a performance optimization.
Since items in the index array are sorted by full pathname, adjacent
items are likely to be in the same directory. This can save memihash()
computations and hash map lookups.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
---
 name-hash.c | 50 ++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 36 insertions(+), 14 deletions(-)

diff --git a/name-hash.c b/name-hash.c
index 8f8336cc868..f95054f44cb 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -39,7 +39,8 @@ static struct dir_entry *find_dir_entry(struct index_state *istate,
 }
 
 static struct dir_entry *hash_dir_entry(struct index_state *istate,
-		struct cache_entry *ce, int namelen)
+		struct cache_entry *ce, int namelen,
+		struct dir_entry **previous_dir)
 {
 	/*
 	 * Throw each directory component in the hash for quick lookup
@@ -63,11 +64,24 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate,
 	namelen--;
 
 	/* lookup existing entry for that directory */
-	if (ce->precomputed_hash.initialized && orig_namelen == ce_namelen(ce))
-		hash = ce->precomputed_hash.dir;
-	else
-		hash = memihash(ce->name, namelen);
-	dir = find_dir_entry_1(istate, ce->name, namelen, hash);
+	if (previous_dir && *previous_dir
+	    && namelen == (*previous_dir)->namelen
+	    && memcmp(ce->name, (*previous_dir)->name, namelen) == 0) {
+		/*
+		 * When our caller is sequentially iterating through the index,
+		 * items in the same directory will be sequential, and therefore
+		 * refer to the same dir_entry.
+		 */
+		dir = *previous_dir;
+	} else {
+		if (ce->precomputed_hash.initialized &&
+		    orig_namelen == ce_namelen(ce))
+			hash = ce->precomputed_hash.dir;
+		else
+			hash = memihash(ce->name, namelen);
+		dir = find_dir_entry_1(istate, ce->name, namelen, hash);
+	}
+
 	if (!dir) {
 		/* not found, create it and add to hash table */
 		FLEX_ALLOC_MEM(dir, name, ce->name, namelen);
@@ -76,15 +90,21 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate,
 		hashmap_add(&istate->dir_hash, dir);
 
 		/* recursively add missing parent directories */
-		dir->parent = hash_dir_entry(istate, ce, namelen);
+		dir->parent = hash_dir_entry(istate, ce, namelen, NULL);
 	}
+
+	if (previous_dir)
+		*previous_dir = dir;
+
 	return dir;
 }
 
-static void add_dir_entry(struct index_state *istate, struct cache_entry *ce)
+static void add_dir_entry(struct index_state *istate, struct cache_entry *ce,
+			  struct dir_entry **previous_dir)
 {
 	/* Add reference to the directory entry (and parents if 0). */
-	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
+	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce),
+					       previous_dir);
 	while (dir && !(dir->nr++))
 		dir = dir->parent;
 }
@@ -95,7 +115,7 @@ static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce)
 	 * Release reference to the directory entry. If 0, remove and continue
 	 * with parent directory.
 	 */
-	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
+	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce), NULL);
 	while (dir && !(--dir->nr)) {
 		struct dir_entry *parent = dir->parent;
 		hashmap_remove(&istate->dir_hash, dir, NULL);
@@ -104,7 +124,8 @@ static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce)
 	}
 }
 
-static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
+static void hash_index_entry(struct index_state *istate, struct cache_entry *ce,
+			     struct dir_entry **previous_dir)
 {
 	unsigned int h;
 
@@ -121,7 +142,7 @@ static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
 	hashmap_add(&istate->name_hash, ce);
 
 	if (ignore_case)
-		add_dir_entry(istate, ce);
+		add_dir_entry(istate, ce, previous_dir);
 }
 
 static int cache_entry_cmp(const struct cache_entry *ce1,
@@ -137,6 +158,7 @@ static int cache_entry_cmp(const struct cache_entry *ce1,
 
 static void lazy_init_name_hash(struct index_state *istate)
 {
+	struct dir_entry *previous_dir = NULL;
 	int nr;
 
 	if (istate->name_hash_initialized)
@@ -146,14 +168,14 @@ static void lazy_init_name_hash(struct index_state *istate)
 	hashmap_init(&istate->dir_hash, (hashmap_cmp_fn) dir_entry_cmp,
 			istate->cache_nr);
 	for (nr = 0; nr < istate->cache_nr; nr++)
-		hash_index_entry(istate, istate->cache[nr]);
+		hash_index_entry(istate, istate->cache[nr], &previous_dir);
 	istate->name_hash_initialized = 1;
 }
 
 void add_name_hash(struct index_state *istate, struct cache_entry *ce)
 {
 	if (istate->name_hash_initialized)
-		hash_index_entry(istate, ce);
+		hash_index_entry(istate, ce, NULL);
 }
 
 void remove_name_hash(struct index_state *istate, struct cache_entry *ce)
-- 
2.11.1.windows.1