git/tree-walk.c
Linus Torvalds 7d65848afd Don't use "sscanf()" for tree mode scanning
Doing an oprofile run on the result of my git rev-list memory leak fixes
and tree parsing cleanups, I was surprised by the third-highest entry
being

	samples  %        image name               app name                 symbol name
	179751    2.7163  libc-2.4.so              libc-2.4.so              _IO_vfscanf@@GLIBC_2.4

where that 2.7% is actually more than 5% of one CPU, because this was run
on a dual CPU setup with the other CPU just being idle.

That seems to all be from the use of 'sscanf(tree, "%o", &mode)' for the
tree buffer parsing.

So do the trivial octal parsing by hand, which also gives us where the
first space in the string is (and thus where the pathname starts) so we
can get rid of the "strchr(tree, ' ')" call too.

This brings the "git rev-list --all --objects" time down from 63 seconds
to 55 seconds on the historical kernel archive for me, so it's quite
noticeable - tree parsing is a lot of what we end up doing when following
all the objects.

[ I also see a 5% speedup on a full "git fsck-objects" on the current
  kernel archive, so that sscanf() really does seem to have hurt our
  performance by a surprising amount ]

Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-28 19:39:49 -07:00

183 lines
3.7 KiB
C

#include "cache.h"
#include "tree-walk.h"
#include "tree.h"
void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1)
{
unsigned long size = 0;
void *buf = NULL;
if (sha1) {
buf = read_object_with_reference(sha1, tree_type, &size, NULL);
if (!buf)
die("unable to read tree %s", sha1_to_hex(sha1));
}
desc->size = size;
desc->buf = buf;
return buf;
}
static int entry_compare(struct name_entry *a, struct name_entry *b)
{
return base_name_compare(
a->path, a->pathlen, a->mode,
b->path, b->pathlen, b->mode);
}
static void entry_clear(struct name_entry *a)
{
memset(a, 0, sizeof(*a));
}
static void entry_extract(struct tree_desc *t, struct name_entry *a)
{
a->sha1 = tree_entry_extract(t, &a->path, &a->mode);
a->pathlen = strlen(a->path);
}
void update_tree_entry(struct tree_desc *desc)
{
void *buf = desc->buf;
unsigned long size = desc->size;
int len = strlen(buf) + 1 + 20;
if (size < len)
die("corrupt tree file");
desc->buf = buf + len;
desc->size = size - len;
}
static const char *get_mode(const char *str, unsigned int *modep)
{
unsigned char c;
unsigned int mode = 0;
while ((c = *str++) != ' ') {
if (c < '0' || c > '7')
return NULL;
mode = (mode << 3) + (c - '0');
}
*modep = mode;
return str;
}
const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep)
{
void *tree = desc->buf;
unsigned long size = desc->size;
int len = strlen(tree)+1;
const unsigned char *sha1 = tree + len;
const char *path;
unsigned int mode;
path = get_mode(tree, &mode);
if (!path || size < len + 20)
die("corrupt tree file");
*pathp = path;
*modep = canon_mode(mode);
return sha1;
}
void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback)
{
struct name_entry *entry = xmalloc(n*sizeof(*entry));
for (;;) {
struct name_entry entry[3];
unsigned long mask = 0;
int i, last;
last = -1;
for (i = 0; i < n; i++) {
if (!t[i].size)
continue;
entry_extract(t+i, entry+i);
if (last >= 0) {
int cmp = entry_compare(entry+i, entry+last);
/*
* Is the new name bigger than the old one?
* Ignore it
*/
if (cmp > 0)
continue;
/*
* Is the new name smaller than the old one?
* Ignore all old ones
*/
if (cmp < 0)
mask = 0;
}
mask |= 1ul << i;
last = i;
}
if (!mask)
break;
/*
* Update the tree entries we've walked, and clear
* all the unused name-entries.
*/
for (i = 0; i < n; i++) {
if (mask & (1ul << i)) {
update_tree_entry(t+i);
continue;
}
entry_clear(entry + i);
}
callback(n, mask, entry, base);
}
free(entry);
}
static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char *result, unsigned *mode)
{
int namelen = strlen(name);
while (t->size) {
const char *entry;
const unsigned char *sha1;
int entrylen, cmp;
sha1 = tree_entry_extract(t, &entry, mode);
update_tree_entry(t);
entrylen = strlen(entry);
if (entrylen > namelen)
continue;
cmp = memcmp(name, entry, entrylen);
if (cmp > 0)
continue;
if (cmp < 0)
break;
if (entrylen == namelen) {
memcpy(result, sha1, 20);
return 0;
}
if (name[entrylen] != '/')
continue;
if (!S_ISDIR(*mode))
break;
if (++entrylen == namelen) {
memcpy(result, sha1, 20);
return 0;
}
return get_tree_entry(sha1, name + entrylen, result, mode);
}
return -1;
}
int get_tree_entry(const unsigned char *tree_sha1, const char *name, unsigned char *sha1, unsigned *mode)
{
int retval;
void *tree;
struct tree_desc t;
tree = read_object_with_reference(tree_sha1, tree_type, &t.size, NULL);
if (!tree)
return -1;
t.buf = tree;
retval = find_tree_entry(&t, name, sha1, mode);
free(tree);
return retval;
}