[PATCH v2 0/1] optimize reading index format v4

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



v2 removes unrelated changes and the dummy_entry. strip_len is also
replaced with copy_len to reduce repeated subtraction calculation.
Diff: 

diff --git a/read-cache.c b/read-cache.c
index 5c04c8f200..8628d0f3a8 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1713,7 +1713,7 @@ int read_index(struct index_state *istate)
 	return read_index_from(istate, get_index_file(), get_git_dir());
 }
 
-static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
+static struct cache_entry *create_from_disk(struct index_state *istate,
 					    struct ondisk_cache_entry *ondisk,
 					    unsigned long *ent_size,
 					    const struct cache_entry *previous_ce)
@@ -1722,7 +1722,15 @@ static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
 	size_t len;
 	const char *name;
 	unsigned int flags;
-	size_t strip_len;
+	size_t copy_len;
+	/*
+	 * Adjacent cache entries tend to share the leading paths, so it makes
+	 * sense to only store the differences in later entries.  In the v4
+	 * on-disk format of the index, each on-disk cache entry stores the
+	 * number of bytes to be stripped from the end of the previous name,
+	 * and the bytes to append to the result, to come up with its name.
+	 */
+	int expand_name_field = istate->version == 4;
 
 	/* On-disk flags are just 16 bits */
 	flags = get_be16(&ondisk->flags);
@@ -1735,37 +1743,37 @@ static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
 		extended_flags = get_be16(&ondisk2->flags2) << 16;
 		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
 		if (extended_flags & ~CE_EXTENDED_FLAGS)
-			die(_("unknown index entry format %08x"), extended_flags);
+			die("Unknown index entry format %08x", extended_flags);
 		flags |= extended_flags;
 		name = ondisk2->name;
 	}
 	else
 		name = ondisk->name;
 
-	/*
-	 * Adjacent cache entries tend to share the leading paths, so it makes
-	 * sense to only store the differences in later entries.  In the v4
-	 * on-disk format of the index, each on-disk cache entry stores the
-	 * number of bytes to be stripped from the end of the previous name,
-	 * and the bytes to append to the result, to come up with its name.
-	 */
-	if (previous_ce) {
+	if (expand_name_field) {
 		const unsigned char *cp = (const unsigned char *)name;
+		size_t strip_len, previous_len;
 
+		previous_len = previous_ce ? previous_ce->ce_namelen : 0;
 		strip_len = decode_varint(&cp);
-		if (previous_ce->ce_namelen < strip_len)
-			die(_("malformed name field in the index, path '%s'"),
-			    previous_ce->name);
+		if (previous_len < strip_len) {
+			if (previous_ce)
+				die(_("malformed name field in the index, near path '%s'"),
+				    previous_ce->name);
+			else
+				die(_("malformed name field in the index in the first path"));
+		}
+		copy_len = previous_len - strip_len;
 		name = (const char *)cp;
 	}
 
 	if (len == CE_NAMEMASK) {
 		len = strlen(name);
-		if (previous_ce)
-			len += previous_ce->ce_namelen - strip_len;
+		if (expand_name_field)
+			len += copy_len;
 	}
 
-	ce = mem_pool__ce_alloc(mem_pool, len);
+	ce = mem_pool__ce_alloc(istate->ce_mem_pool, len);
 
 	ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
 	ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
@@ -1782,9 +1790,9 @@ static struct cache_entry *create_from_disk(struct mem_pool *mem_pool,
 	ce->index = 0;
 	hashcpy(ce->oid.hash, ondisk->sha1);
 
-	if (previous_ce) {
-		size_t copy_len = previous_ce->ce_namelen - strip_len;
-		memcpy(ce->name, previous_ce->name, copy_len);
+	if (expand_name_field) {
+		if (copy_len)
+			memcpy(ce->name, previous_ce->name, copy_len);
 		memcpy(ce->name + copy_len, name, len + 1 - copy_len);
 		*ent_size = (name - ((char *)ondisk)) + len + 1 - copy_len;
 	} else {
@@ -1885,7 +1893,6 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	void *mmap;
 	size_t mmap_size;
 	const struct cache_entry *previous_ce = NULL;
-	struct cache_entry *dummy_entry = NULL;
 
 	if (istate->initialized)
 		return istate->cache_nr;
@@ -1923,7 +1930,6 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	istate->initialized = 1;
 
 	if (istate->version == 4) {
-		previous_ce = dummy_entry = make_empty_transient_cache_entry(0);
 		mem_pool_init(&istate->ce_mem_pool,
 			      estimate_cache_size_from_compressed(istate->cache_nr));
 	} else {
@@ -1938,14 +1944,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 		unsigned long consumed;
 
 		disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
-		ce = create_from_disk(istate->ce_mem_pool, disk_ce, &consumed, previous_ce);
+		ce = create_from_disk(istate, disk_ce, &consumed, previous_ce);
 		set_index_entry(istate, i, ce);
 
 		src_offset += consumed;
-		if (previous_ce)
-			previous_ce = ce;
+		previous_ce = ce;
 	}
-	free(dummy_entry);
 	istate->timestamp.sec = st.st_mtime;
 	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 


Nguyễn Thái Ngọc Duy (1):
  read-cache.c: optimize reading index format v4

 read-cache.c | 128 ++++++++++++++++++++++++---------------------------
 1 file changed, 60 insertions(+), 68 deletions(-)

-- 
2.19.0.rc0.337.ge906d732e7




[Index of Archives]     [Linux Kernel Development]     [Gcc Help]     [IETF Annouce]     [DCCP]     [Netdev]     [Networking]     [Security]     [V4L]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux SCSI]     [Fedora Users]

  Powered by Linux