summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNicolas Pitre <nico@cam.org>2005-05-06 13:48:34 -0400
committerLinus Torvalds <torvalds@ppc970.osdl.org>2005-05-06 11:02:01 -0700
commitbd2c39f58f915af532b488c5bda753314f0db603 (patch)
tree8c1e85a4af5d77cff94fc2703c271bbfc512778e
parentf4f21ce367a5119be1c4396d01271ece6e40ff70 (diff)
downloadgit-bd2c39f58f915af532b488c5bda753314f0db603.tar.gz
[PATCH] don't load and decompress objects twice with parse_object()
It turns out that parse_object() is loading and decompressing given object to free it just before calling the specific object parsing function which does mmap and decompress the same object again. This patch introduces the ability to parse specific objects directly from a memory buffer. Without this patch, running git-fsck-cache on the kernel repositorytake: real 0m13.006s user 0m11.421s sys 0m1.218s With this patch applied: real 0m8.060s user 0m7.071s sys 0m0.710s The performance increase is significant, and this is kind of a prerequisite for sane delta object support with fsck. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--blob.c14
-rw-r--r--blob.h2
-rw-r--r--commit.c40
-rw-r--r--commit.h2
-rw-r--r--object.c30
-rw-r--r--tag.c50
-rw-r--r--tag.h1
-rw-r--r--tree.c44
-rw-r--r--tree.h2
9 files changed, 115 insertions, 70 deletions
diff --git a/blob.c b/blob.c
index 625db43971..280f524157 100644
--- a/blob.c
+++ b/blob.c
@@ -22,21 +22,29 @@ struct blob *lookup_blob(unsigned char *sha1)
return (struct blob *) obj;
}
+int parse_blob_buffer(struct blob *item, void *buffer, unsigned long size)
+{
+ item->object.parsed = 1;
+ return 0;
+}
+
int parse_blob(struct blob *item)
{
char type[20];
void *buffer;
unsigned long size;
+ int ret;
+
if (item->object.parsed)
return 0;
- item->object.parsed = 1;
buffer = read_sha1_file(item->object.sha1, type, &size);
if (!buffer)
return error("Could not read %s",
sha1_to_hex(item->object.sha1));
- free(buffer);
if (strcmp(type, blob_type))
return error("Object %s not a blob",
sha1_to_hex(item->object.sha1));
- return 0;
+ ret = parse_blob_buffer(item, buffer, size);
+ free(buffer);
+ return ret;
}
diff --git a/blob.h b/blob.h
index 4afad0f067..8004c835e7 100644
--- a/blob.h
+++ b/blob.h
@@ -11,6 +11,8 @@ struct blob {
struct blob *lookup_blob(unsigned char *sha1);
+int parse_blob_buffer(struct blob *item, void *buffer, unsigned long size);
+
int parse_blob(struct blob *item);
#endif /* BLOB_H */
diff --git a/commit.c b/commit.c
index b45118a544..706c7cba08 100644
--- a/commit.c
+++ b/commit.c
@@ -41,24 +41,14 @@ static unsigned long parse_commit_date(const char *buf)
return date;
}
-int parse_commit(struct commit *item)
+int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size)
{
- char type[20];
- void * buffer, *bufptr;
- unsigned long size;
+ void *bufptr = buffer;
unsigned char parent[20];
+
if (item->object.parsed)
return 0;
item->object.parsed = 1;
- buffer = bufptr = read_sha1_file(item->object.sha1, type, &size);
- if (!buffer)
- return error("Could not read %s",
- sha1_to_hex(item->object.sha1));
- if (strcmp(type, commit_type)) {
- free(buffer);
- return error("Object %s not a commit",
- sha1_to_hex(item->object.sha1));
- }
get_sha1_hex(bufptr + 5, parent);
item->tree = lookup_tree(parent);
if (item->tree)
@@ -74,10 +64,32 @@ int parse_commit(struct commit *item)
bufptr += 48;
}
item->date = parse_commit_date(bufptr);
- free(buffer);
return 0;
}
+int parse_commit(struct commit *item)
+{
+ char type[20];
+ void *buffer;
+ unsigned long size;
+ int ret;
+
+ if (item->object.parsed)
+ return 0;
+ buffer = read_sha1_file(item->object.sha1, type, &size);
+ if (!buffer)
+ return error("Could not read %s",
+ sha1_to_hex(item->object.sha1));
+ if (strcmp(type, commit_type)) {
+ free(buffer);
+ return error("Object %s not a commit",
+ sha1_to_hex(item->object.sha1));
+ }
+ ret = parse_commit_buffer(item, buffer, size);
+ free(buffer);
+ return ret;
+}
+
void commit_list_insert(struct commit *item, struct commit_list **list_p)
{
struct commit_list *new_list = xmalloc(sizeof(struct commit_list));
diff --git a/commit.h b/commit.h
index d61d084c89..ce0b436711 100644
--- a/commit.h
+++ b/commit.h
@@ -20,6 +20,8 @@ extern const char *commit_type;
struct commit *lookup_commit(unsigned char *sha1);
+int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size);
+
int parse_commit(struct commit *item);
void commit_list_insert(struct commit *item, struct commit_list **list_p);
diff --git a/object.c b/object.c
index c1f22910a2..b5a62e7f87 100644
--- a/object.c
+++ b/object.c
@@ -104,6 +104,7 @@ struct object *parse_object(unsigned char *sha1)
unsigned long mapsize;
void *map = map_sha1_file(sha1, &mapsize);
if (map) {
+ struct object *obj;
char type[100];
unsigned long size;
void *buffer = unpack_sha1_file(map, mapsize, type, &size);
@@ -112,26 +113,27 @@ struct object *parse_object(unsigned char *sha1)
return NULL;
if (check_sha1_signature(sha1, buffer, size, type) < 0)
printf("sha1 mismatch %s\n", sha1_to_hex(sha1));
- free(buffer);
if (!strcmp(type, "blob")) {
- struct blob *ret = lookup_blob(sha1);
- parse_blob(ret);
- return &ret->object;
+ struct blob *blob = lookup_blob(sha1);
+ parse_blob_buffer(blob, buffer, size);
+ obj = &blob->object;
} else if (!strcmp(type, "tree")) {
- struct tree *ret = lookup_tree(sha1);
- parse_tree(ret);
- return &ret->object;
+ struct tree *tree = lookup_tree(sha1);
+ parse_tree_buffer(tree, buffer, size);
+ obj = &tree->object;
} else if (!strcmp(type, "commit")) {
- struct commit *ret = lookup_commit(sha1);
- parse_commit(ret);
- return &ret->object;
+ struct commit *commit = lookup_commit(sha1);
+ parse_commit_buffer(commit, buffer, size);
+ obj = &commit->object;
} else if (!strcmp(type, "tag")) {
- struct tag *ret = lookup_tag(sha1);
- parse_tag(ret);
- return &ret->object;
+ struct tag *tag = lookup_tag(sha1);
+ parse_tag_buffer(tag, buffer, size);
+ obj = &tag->object;
} else {
- return NULL;
+ obj = NULL;
}
+ free(buffer);
+ return obj;
}
return NULL;
}
diff --git a/tag.c b/tag.c
index 3a71dd416a..22deb243ad 100644
--- a/tag.c
+++ b/tag.c
@@ -21,11 +21,8 @@ struct tag *lookup_tag(unsigned char *sha1)
return (struct tag *) obj;
}
-int parse_tag(struct tag *item)
+int parse_tag_buffer(struct tag *item, void *data, unsigned long size)
{
- char type[20];
- void *data, *bufptr;
- unsigned long size;
int typelen, taglen;
unsigned char object[20];
const char *type_line, *tag_line, *sig_line;
@@ -33,20 +30,11 @@ int parse_tag(struct tag *item)
if (item->object.parsed)
return 0;
item->object.parsed = 1;
- data = bufptr = read_sha1_file(item->object.sha1, type, &size);
- if (!data)
- return error("Could not read %s",
- sha1_to_hex(item->object.sha1));
- if (strcmp(type, tag_type)) {
- free(data);
- return error("Object %s not a tag",
- sha1_to_hex(item->object.sha1));
- }
if (size < 64)
- goto err;
+ return -1;
if (memcmp("object ", data, 7) || get_sha1_hex(data + 7, object))
- goto err;
+ return -1;
item->tagged = parse_object(object);
if (item->tagged)
@@ -54,29 +42,47 @@ int parse_tag(struct tag *item)
type_line = data + 48;
if (memcmp("\ntype ", type_line-1, 6))
- goto err;
+ return -1;
tag_line = strchr(type_line, '\n');
if (!tag_line || memcmp("tag ", ++tag_line, 4))
- goto err;
+ return -1;
sig_line = strchr(tag_line, '\n');
if (!sig_line)
- goto err;
+ return -1;
sig_line++;
typelen = tag_line - type_line - strlen("type \n");
if (typelen >= 20)
- goto err;
+ return -1;
taglen = sig_line - tag_line - strlen("tag \n");
item->tag = xmalloc(taglen + 1);
memcpy(item->tag, tag_line + 4, taglen);
item->tag[taglen] = '\0';
- free(data);
return 0;
+}
-err:
+int parse_tag(struct tag *item)
+{
+ char type[20];
+ void *data;
+ unsigned long size;
+ int ret;
+
+ if (item->object.parsed)
+ return 0;
+ data = read_sha1_file(item->object.sha1, type, &size);
+ if (!data)
+ return error("Could not read %s",
+ sha1_to_hex(item->object.sha1));
+ if (strcmp(type, tag_type)) {
+ free(data);
+ return error("Object %s not a tag",
+ sha1_to_hex(item->object.sha1));
+ }
+ ret = parse_tag_buffer(item, data, size);
free(data);
- return -1;
+ return ret;
}
diff --git a/tag.h b/tag.h
index eddfed6bf3..41826870f8 100644
--- a/tag.h
+++ b/tag.h
@@ -13,6 +13,7 @@ struct tag {
};
extern struct tag *lookup_tag(unsigned char *sha1);
+extern int parse_tag_buffer(struct tag *item, void *data, unsigned long size);
extern int parse_tag(struct tag *item);
#endif /* TAG_H */
diff --git a/tree.c b/tree.c
index 468f99e494..d9777bf810 100644
--- a/tree.c
+++ b/tree.c
@@ -88,24 +88,14 @@ struct tree *lookup_tree(unsigned char *sha1)
return (struct tree *) obj;
}
-int parse_tree(struct tree *item)
+int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size)
{
- char type[20];
- void *buffer, *bufptr;
- unsigned long size;
+ void *bufptr = buffer;
struct tree_entry_list **list_p;
+
if (item->object.parsed)
return 0;
item->object.parsed = 1;
- buffer = bufptr = read_sha1_file(item->object.sha1, type, &size);
- if (!buffer)
- return error("Could not read %s",
- sha1_to_hex(item->object.sha1));
- if (strcmp(type, tree_type)) {
- free(buffer);
- return error("Object %s not a tree",
- sha1_to_hex(item->object.sha1));
- }
list_p = &item->entries;
while (size) {
struct object *obj;
@@ -115,10 +105,8 @@ int parse_tree(struct tree *item)
char *path = strchr(bufptr, ' ');
unsigned int mode;
if (size < len + 20 || !path ||
- sscanf(bufptr, "%o", &mode) != 1) {
- free(buffer);
+ sscanf(bufptr, "%o", &mode) != 1)
return -1;
- }
entry = xmalloc(sizeof(struct tree_entry_list));
entry->name = strdup(path + 1);
@@ -144,6 +132,28 @@ int parse_tree(struct tree *item)
*list_p = entry;
list_p = &entry->next;
}
- free(buffer);
return 0;
}
+
+int parse_tree(struct tree *item)
+{
+ char type[20];
+ void *buffer;
+ unsigned long size;
+ int ret;
+
+ if (item->object.parsed)
+ return 0;
+ buffer = read_sha1_file(item->object.sha1, type, &size);
+ if (!buffer)
+ return error("Could not read %s",
+ sha1_to_hex(item->object.sha1));
+ if (strcmp(type, tree_type)) {
+ free(buffer);
+ return error("Object %s not a tree",
+ sha1_to_hex(item->object.sha1));
+ }
+ ret = parse_tree_buffer(item, buffer, size);
+ free(buffer);
+ return ret;
+}
diff --git a/tree.h b/tree.h
index e1c94c090c..1383beb2bf 100644
--- a/tree.h
+++ b/tree.h
@@ -25,6 +25,8 @@ struct tree {
struct tree *lookup_tree(unsigned char *sha1);
+int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size);
+
int parse_tree(struct tree *tree);
#endif /* TREE_H */