2006-04-23 23:52:20 +00:00
|
|
|
#include "cache.h"
|
|
|
|
#include "tree.h"
|
2009-04-20 10:58:18 +00:00
|
|
|
#include "tree-walk.h"
|
2006-04-23 23:52:20 +00:00
|
|
|
#include "cache-tree.h"
|
|
|
|
|
2006-10-30 23:29:53 +00:00
|
|
|
#ifndef DEBUG
|
2006-04-23 23:52:20 +00:00
|
|
|
#define DEBUG 0
|
2006-10-30 23:29:53 +00:00
|
|
|
#endif
|
2006-04-23 23:52:20 +00:00
|
|
|
|
|
|
|
struct cache_tree *cache_tree(void)
|
|
|
|
{
|
|
|
|
struct cache_tree *it = xcalloc(1, sizeof(struct cache_tree));
|
|
|
|
it->entry_count = -1;
|
|
|
|
return it;
|
|
|
|
}
|
|
|
|
|
2006-04-25 04:18:58 +00:00
|
|
|
void cache_tree_free(struct cache_tree **it_p)
|
2006-04-23 23:52:20 +00:00
|
|
|
{
|
|
|
|
int i;
|
2006-04-25 04:18:58 +00:00
|
|
|
struct cache_tree *it = *it_p;
|
2006-04-23 23:52:20 +00:00
|
|
|
|
|
|
|
if (!it)
|
|
|
|
return;
|
|
|
|
for (i = 0; i < it->subtree_nr; i++)
|
2010-09-06 21:40:16 +00:00
|
|
|
if (it->down[i]) {
|
2006-04-26 00:40:02 +00:00
|
|
|
cache_tree_free(&it->down[i]->cache_tree);
|
2010-09-06 21:40:16 +00:00
|
|
|
free(it->down[i]);
|
|
|
|
}
|
2006-04-23 23:52:20 +00:00
|
|
|
free(it->down);
|
|
|
|
free(it);
|
2006-04-25 04:18:58 +00:00
|
|
|
*it_p = NULL;
|
2006-04-23 23:52:20 +00:00
|
|
|
}
|
|
|
|
|
2006-04-26 00:40:02 +00:00
|
|
|
static int subtree_name_cmp(const char *one, int onelen,
|
|
|
|
const char *two, int twolen)
|
|
|
|
{
|
|
|
|
if (onelen < twolen)
|
|
|
|
return -1;
|
|
|
|
if (twolen < onelen)
|
|
|
|
return 1;
|
|
|
|
return memcmp(one, two, onelen);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int subtree_pos(struct cache_tree *it, const char *path, int pathlen)
|
|
|
|
{
|
|
|
|
struct cache_tree_sub **down = it->down;
|
|
|
|
int lo, hi;
|
|
|
|
lo = 0;
|
|
|
|
hi = it->subtree_nr;
|
|
|
|
while (lo < hi) {
|
|
|
|
int mi = (lo + hi) / 2;
|
|
|
|
struct cache_tree_sub *mdl = down[mi];
|
|
|
|
int cmp = subtree_name_cmp(path, pathlen,
|
|
|
|
mdl->name, mdl->namelen);
|
|
|
|
if (!cmp)
|
|
|
|
return mi;
|
|
|
|
if (cmp < 0)
|
|
|
|
hi = mi;
|
|
|
|
else
|
|
|
|
lo = mi + 1;
|
|
|
|
}
|
|
|
|
return -lo-1;
|
|
|
|
}
|
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
static struct cache_tree_sub *find_subtree(struct cache_tree *it,
|
|
|
|
const char *path,
|
|
|
|
int pathlen,
|
|
|
|
int create)
|
|
|
|
{
|
|
|
|
struct cache_tree_sub *down;
|
2006-04-26 00:40:02 +00:00
|
|
|
int pos = subtree_pos(it, path, pathlen);
|
|
|
|
if (0 <= pos)
|
|
|
|
return it->down[pos];
|
2006-04-23 23:52:20 +00:00
|
|
|
if (!create)
|
|
|
|
return NULL;
|
2006-04-26 00:40:02 +00:00
|
|
|
|
|
|
|
pos = -pos-1;
|
2006-04-23 23:52:20 +00:00
|
|
|
if (it->subtree_alloc <= it->subtree_nr) {
|
|
|
|
it->subtree_alloc = alloc_nr(it->subtree_alloc);
|
|
|
|
it->down = xrealloc(it->down, it->subtree_alloc *
|
|
|
|
sizeof(*it->down));
|
|
|
|
}
|
2006-04-26 00:40:02 +00:00
|
|
|
it->subtree_nr++;
|
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
down = xmalloc(sizeof(*down) + pathlen + 1);
|
2006-04-26 00:40:02 +00:00
|
|
|
down->cache_tree = NULL;
|
2006-04-23 23:52:20 +00:00
|
|
|
down->namelen = pathlen;
|
|
|
|
memcpy(down->name, path, pathlen);
|
2006-04-26 00:40:02 +00:00
|
|
|
down->name[pathlen] = 0;
|
|
|
|
|
|
|
|
if (pos < it->subtree_nr)
|
|
|
|
memmove(it->down + pos + 1,
|
|
|
|
it->down + pos,
|
|
|
|
sizeof(down) * (it->subtree_nr - pos - 1));
|
|
|
|
it->down[pos] = down;
|
2006-04-23 23:52:20 +00:00
|
|
|
return down;
|
|
|
|
}
|
|
|
|
|
2006-04-27 08:33:07 +00:00
|
|
|
struct cache_tree_sub *cache_tree_sub(struct cache_tree *it, const char *path)
|
|
|
|
{
|
|
|
|
int pathlen = strlen(path);
|
|
|
|
return find_subtree(it, path, pathlen, 1);
|
|
|
|
}
|
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
void cache_tree_invalidate_path(struct cache_tree *it, const char *path)
|
|
|
|
{
|
|
|
|
/* a/b/c
|
|
|
|
* ==> invalidate self
|
|
|
|
* ==> find "a", have it invalidate "b/c"
|
|
|
|
* a
|
|
|
|
* ==> invalidate self
|
|
|
|
* ==> if "a" exists as a subtree, remove it.
|
|
|
|
*/
|
|
|
|
const char *slash;
|
|
|
|
int namelen;
|
|
|
|
struct cache_tree_sub *down;
|
|
|
|
|
2006-05-03 23:10:45 +00:00
|
|
|
#if DEBUG
|
|
|
|
fprintf(stderr, "cache-tree invalidate <%s>\n", path);
|
|
|
|
#endif
|
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
if (!it)
|
|
|
|
return;
|
|
|
|
slash = strchr(path, '/');
|
|
|
|
it->entry_count = -1;
|
|
|
|
if (!slash) {
|
2006-04-26 00:40:02 +00:00
|
|
|
int pos;
|
2006-04-23 23:52:20 +00:00
|
|
|
namelen = strlen(path);
|
2006-04-26 00:40:02 +00:00
|
|
|
pos = subtree_pos(it, path, namelen);
|
|
|
|
if (0 <= pos) {
|
|
|
|
cache_tree_free(&it->down[pos]->cache_tree);
|
|
|
|
free(it->down[pos]);
|
2006-04-23 23:52:20 +00:00
|
|
|
/* 0 1 2 3 4 5
|
|
|
|
* ^ ^subtree_nr = 6
|
2006-04-26 00:40:02 +00:00
|
|
|
* pos
|
2006-04-23 23:52:20 +00:00
|
|
|
* move 4 and 5 up one place (2 entries)
|
2006-04-26 00:40:02 +00:00
|
|
|
* 2 = 6 - 3 - 1 = subtree_nr - pos - 1
|
2006-04-23 23:52:20 +00:00
|
|
|
*/
|
2006-04-26 00:40:02 +00:00
|
|
|
memmove(it->down+pos, it->down+pos+1,
|
2006-04-23 23:52:20 +00:00
|
|
|
sizeof(struct cache_tree_sub *) *
|
2006-04-26 00:40:02 +00:00
|
|
|
(it->subtree_nr - pos - 1));
|
2006-04-23 23:52:20 +00:00
|
|
|
it->subtree_nr--;
|
|
|
|
}
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
namelen = slash - path;
|
|
|
|
down = find_subtree(it, path, namelen, 0);
|
|
|
|
if (down)
|
|
|
|
cache_tree_invalidate_path(down->cache_tree, slash + 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int verify_cache(struct cache_entry **cache,
|
|
|
|
int entries)
|
|
|
|
{
|
|
|
|
int i, funny;
|
|
|
|
|
|
|
|
/* Verify that the tree is merged */
|
|
|
|
funny = 0;
|
|
|
|
for (i = 0; i < entries; i++) {
|
|
|
|
struct cache_entry *ce = cache[i];
|
commit: ignore intent-to-add entries instead of refusing
Originally, "git add -N" was introduced to help users from forgetting to
add new files to the index before they ran "git commit -a". As an attempt
to help them further so that they do not forget to say "-a", "git commit"
to commit the index as-is was taught to error out, reminding the user that
they may have forgotten to add the final contents of the paths before
running the command.
This turned out to be a false "safety" that is useless. If the user made
changes to already tracked paths and paths added with "git add -N", and
then ran "git add" to register the final contents of the paths added with
"git add -N", "git commit" will happily create a commit out of the index,
without including the local changes made to the already tracked paths. It
was not a useful "safety" measure to prevent "forgetful" mistakes from
happening.
It turns out that this behaviour is not just a useless false "safety", but
actively hurts use cases of "git add -N" that were discovered later and
have become popular, namely, to tell Git to be aware of these paths added
by "git add -N", so that commands like "git status" and "git diff" would
include them in their output, even though the user is not interested in
including them in the next commit they are going to make.
Fix this ancient UI mistake, and instead make a commit from the index
ignoring the paths added by "git add -N" without adding real contents.
Based on the work by Nguyễn Thái Ngọc Duy, and helped by injection of
sanity from Jonathan Nieder and others on the Git mailing list.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 19:55:48 +00:00
|
|
|
if (ce_stage(ce)) {
|
2006-04-23 23:52:20 +00:00
|
|
|
if (10 < ++funny) {
|
|
|
|
fprintf(stderr, "...\n");
|
|
|
|
break;
|
|
|
|
}
|
2008-11-29 03:56:34 +00:00
|
|
|
if (ce_stage(ce))
|
|
|
|
fprintf(stderr, "%s: unmerged (%s)\n",
|
|
|
|
ce->name, sha1_to_hex(ce->sha1));
|
|
|
|
else
|
|
|
|
fprintf(stderr, "%s: not added yet\n",
|
|
|
|
ce->name);
|
2006-04-23 23:52:20 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
if (funny)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
/* Also verify that the cache does not have path and path/file
|
|
|
|
* at the same time. At this point we know the cache has only
|
|
|
|
* stage 0 entries.
|
|
|
|
*/
|
|
|
|
funny = 0;
|
|
|
|
for (i = 0; i < entries - 1; i++) {
|
|
|
|
/* path/file always comes after path because of the way
|
|
|
|
* the cache is sorted. Also path can appear only once,
|
|
|
|
* which means conflicting one would immediately follow.
|
|
|
|
*/
|
|
|
|
const char *this_name = cache[i]->name;
|
|
|
|
const char *next_name = cache[i+1]->name;
|
|
|
|
int this_len = strlen(this_name);
|
|
|
|
if (this_len < strlen(next_name) &&
|
|
|
|
strncmp(this_name, next_name, this_len) == 0 &&
|
|
|
|
next_name[this_len] == '/') {
|
|
|
|
if (10 < ++funny) {
|
|
|
|
fprintf(stderr, "...\n");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
fprintf(stderr, "You have both %s and %s\n",
|
|
|
|
this_name, next_name);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (funny)
|
|
|
|
return -1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void discard_unused_subtrees(struct cache_tree *it)
|
|
|
|
{
|
|
|
|
struct cache_tree_sub **down = it->down;
|
|
|
|
int nr = it->subtree_nr;
|
|
|
|
int dst, src;
|
|
|
|
for (dst = src = 0; src < nr; src++) {
|
|
|
|
struct cache_tree_sub *s = down[src];
|
|
|
|
if (s->used)
|
|
|
|
down[dst++] = s;
|
|
|
|
else {
|
2006-04-25 04:18:58 +00:00
|
|
|
cache_tree_free(&s->cache_tree);
|
2006-04-23 23:52:20 +00:00
|
|
|
free(s);
|
|
|
|
it->subtree_nr--;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-04-25 04:18:58 +00:00
|
|
|
int cache_tree_fully_valid(struct cache_tree *it)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
if (!it)
|
|
|
|
return 0;
|
|
|
|
if (it->entry_count < 0 || !has_sha1_file(it->sha1))
|
|
|
|
return 0;
|
|
|
|
for (i = 0; i < it->subtree_nr; i++) {
|
|
|
|
if (!cache_tree_fully_valid(it->down[i]->cache_tree))
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
static int update_one(struct cache_tree *it,
|
|
|
|
struct cache_entry **cache,
|
|
|
|
int entries,
|
|
|
|
const char *base,
|
|
|
|
int baselen,
|
2006-04-27 23:21:54 +00:00
|
|
|
int missing_ok,
|
|
|
|
int dryrun)
|
2006-04-23 23:52:20 +00:00
|
|
|
{
|
2007-09-06 11:20:11 +00:00
|
|
|
struct strbuf buffer;
|
2006-04-23 23:52:20 +00:00
|
|
|
int i;
|
|
|
|
|
2006-04-24 22:12:42 +00:00
|
|
|
if (0 <= it->entry_count && has_sha1_file(it->sha1))
|
2006-04-23 23:52:20 +00:00
|
|
|
return it->entry_count;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We first scan for subtrees and update them; we start by
|
|
|
|
* marking existing subtrees -- the ones that are unmarked
|
|
|
|
* should not be in the result.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < it->subtree_nr; i++)
|
|
|
|
it->down[i]->used = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find the subtrees and update them.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < entries; i++) {
|
|
|
|
struct cache_entry *ce = cache[i];
|
|
|
|
struct cache_tree_sub *sub;
|
|
|
|
const char *path, *slash;
|
|
|
|
int pathlen, sublen, subcnt;
|
|
|
|
|
|
|
|
path = ce->name;
|
|
|
|
pathlen = ce_namelen(ce);
|
|
|
|
if (pathlen <= baselen || memcmp(base, path, baselen))
|
|
|
|
break; /* at the end of this level */
|
|
|
|
|
|
|
|
slash = strchr(path + baselen, '/');
|
|
|
|
if (!slash)
|
|
|
|
continue;
|
|
|
|
/*
|
|
|
|
* a/bbb/c (base = a/, slash = /c)
|
|
|
|
* ==>
|
|
|
|
* path+baselen = bbb/c, sublen = 3
|
|
|
|
*/
|
|
|
|
sublen = slash - (path + baselen);
|
|
|
|
sub = find_subtree(it, path + baselen, sublen, 1);
|
|
|
|
if (!sub->cache_tree)
|
|
|
|
sub->cache_tree = cache_tree();
|
|
|
|
subcnt = update_one(sub->cache_tree,
|
|
|
|
cache + i, entries - i,
|
|
|
|
path,
|
|
|
|
baselen + sublen + 1,
|
2006-04-27 23:21:54 +00:00
|
|
|
missing_ok,
|
|
|
|
dryrun);
|
2006-11-13 13:50:00 +00:00
|
|
|
if (subcnt < 0)
|
|
|
|
return subcnt;
|
2006-04-23 23:52:20 +00:00
|
|
|
i += subcnt - 1;
|
|
|
|
sub->used = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
discard_unused_subtrees(it);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Then write out the tree object for this level.
|
|
|
|
*/
|
2007-09-10 10:35:04 +00:00
|
|
|
strbuf_init(&buffer, 8192);
|
2006-04-23 23:52:20 +00:00
|
|
|
|
|
|
|
for (i = 0; i < entries; i++) {
|
|
|
|
struct cache_entry *ce = cache[i];
|
|
|
|
struct cache_tree_sub *sub;
|
|
|
|
const char *path, *slash;
|
|
|
|
int pathlen, entlen;
|
|
|
|
const unsigned char *sha1;
|
|
|
|
unsigned mode;
|
|
|
|
|
|
|
|
path = ce->name;
|
|
|
|
pathlen = ce_namelen(ce);
|
|
|
|
if (pathlen <= baselen || memcmp(base, path, baselen))
|
|
|
|
break; /* at the end of this level */
|
|
|
|
|
|
|
|
slash = strchr(path + baselen, '/');
|
|
|
|
if (slash) {
|
|
|
|
entlen = slash - (path + baselen);
|
|
|
|
sub = find_subtree(it, path + baselen, entlen, 0);
|
|
|
|
if (!sub)
|
|
|
|
die("cache-tree.c: '%.*s' in '%s' not found",
|
|
|
|
entlen, path + baselen, path);
|
|
|
|
i += sub->cache_tree->entry_count - 1;
|
|
|
|
sha1 = sub->cache_tree->sha1;
|
|
|
|
mode = S_IFDIR;
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
sha1 = ce->sha1;
|
2008-01-15 00:03:17 +00:00
|
|
|
mode = ce->ce_mode;
|
2006-04-23 23:52:20 +00:00
|
|
|
entlen = pathlen - baselen;
|
|
|
|
}
|
2010-08-10 03:32:11 +00:00
|
|
|
if (mode != S_IFGITLINK && !missing_ok && !has_sha1_file(sha1)) {
|
|
|
|
strbuf_release(&buffer);
|
2009-07-14 18:25:17 +00:00
|
|
|
return error("invalid object %06o %s for '%.*s'",
|
|
|
|
mode, sha1_to_hex(sha1), entlen+baselen, path);
|
2010-08-10 03:32:11 +00:00
|
|
|
}
|
2006-04-23 23:52:20 +00:00
|
|
|
|
commit: ignore intent-to-add entries instead of refusing
Originally, "git add -N" was introduced to help users from forgetting to
add new files to the index before they ran "git commit -a". As an attempt
to help them further so that they do not forget to say "-a", "git commit"
to commit the index as-is was taught to error out, reminding the user that
they may have forgotten to add the final contents of the paths before
running the command.
This turned out to be a false "safety" that is useless. If the user made
changes to already tracked paths and paths added with "git add -N", and
then ran "git add" to register the final contents of the paths added with
"git add -N", "git commit" will happily create a commit out of the index,
without including the local changes made to the already tracked paths. It
was not a useful "safety" measure to prevent "forgetful" mistakes from
happening.
It turns out that this behaviour is not just a useless false "safety", but
actively hurts use cases of "git add -N" that were discovered later and
have become popular, namely, to tell Git to be aware of these paths added
by "git add -N", so that commands like "git status" and "git diff" would
include them in their output, even though the user is not interested in
including them in the next commit they are going to make.
Fix this ancient UI mistake, and instead make a commit from the index
ignoring the paths added by "git add -N" without adding real contents.
Based on the work by Nguyễn Thái Ngọc Duy, and helped by injection of
sanity from Jonathan Nieder and others on the Git mailing list.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-07 19:55:48 +00:00
|
|
|
if (ce->ce_flags & (CE_REMOVE | CE_INTENT_TO_ADD))
|
|
|
|
continue; /* entry being removed or placeholder */
|
2006-04-23 23:52:20 +00:00
|
|
|
|
2007-09-06 11:20:11 +00:00
|
|
|
strbuf_grow(&buffer, entlen + 100);
|
|
|
|
strbuf_addf(&buffer, "%o %.*s%c", mode, entlen, path + baselen, '\0');
|
|
|
|
strbuf_add(&buffer, sha1, 20);
|
2006-04-23 23:52:20 +00:00
|
|
|
|
|
|
|
#if DEBUG
|
2006-05-03 23:10:45 +00:00
|
|
|
fprintf(stderr, "cache-tree update-one %o %.*s\n",
|
2006-04-23 23:52:20 +00:00
|
|
|
mode, entlen, path + baselen);
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2006-10-14 10:45:36 +00:00
|
|
|
if (dryrun)
|
2007-09-06 11:20:11 +00:00
|
|
|
hash_sha1_file(buffer.buf, buffer.len, tree_type, it->sha1);
|
2008-04-23 16:47:17 +00:00
|
|
|
else if (write_sha1_file(buffer.buf, buffer.len, tree_type, it->sha1)) {
|
|
|
|
strbuf_release(&buffer);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2007-09-06 11:20:11 +00:00
|
|
|
strbuf_release(&buffer);
|
2006-04-23 23:52:20 +00:00
|
|
|
it->entry_count = i;
|
|
|
|
#if DEBUG
|
2006-05-03 23:10:45 +00:00
|
|
|
fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n",
|
2006-04-23 23:52:20 +00:00
|
|
|
it->entry_count, it->subtree_nr,
|
|
|
|
sha1_to_hex(it->sha1));
|
|
|
|
#endif
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
|
|
|
|
int cache_tree_update(struct cache_tree *it,
|
|
|
|
struct cache_entry **cache,
|
|
|
|
int entries,
|
2006-04-27 23:21:54 +00:00
|
|
|
int missing_ok,
|
|
|
|
int dryrun)
|
2006-04-23 23:52:20 +00:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
i = verify_cache(cache, entries);
|
|
|
|
if (i)
|
|
|
|
return i;
|
2006-04-27 23:21:54 +00:00
|
|
|
i = update_one(it, cache, entries, "", 0, missing_ok, dryrun);
|
2006-04-23 23:52:20 +00:00
|
|
|
if (i < 0)
|
|
|
|
return i;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2007-09-25 08:22:44 +00:00
|
|
|
static void write_one(struct strbuf *buffer, struct cache_tree *it,
|
|
|
|
const char *path, int pathlen)
|
2006-04-23 23:52:20 +00:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
/* One "cache-tree" entry consists of the following:
|
|
|
|
* path (NUL terminated)
|
|
|
|
* entry_count, subtree_nr ("%d %d\n")
|
|
|
|
* tree-sha1 (missing if invalid)
|
|
|
|
* subtree_nr "cache-tree" entries for subtrees.
|
|
|
|
*/
|
2007-09-06 11:20:11 +00:00
|
|
|
strbuf_grow(buffer, pathlen + 100);
|
|
|
|
strbuf_add(buffer, path, pathlen);
|
|
|
|
strbuf_addf(buffer, "%c%d %d\n", 0, it->entry_count, it->subtree_nr);
|
2006-04-23 23:52:20 +00:00
|
|
|
|
|
|
|
#if DEBUG
|
|
|
|
if (0 <= it->entry_count)
|
|
|
|
fprintf(stderr, "cache-tree <%.*s> (%d ent, %d subtree) %s\n",
|
|
|
|
pathlen, path, it->entry_count, it->subtree_nr,
|
|
|
|
sha1_to_hex(it->sha1));
|
|
|
|
else
|
|
|
|
fprintf(stderr, "cache-tree <%.*s> (%d subtree) invalid\n",
|
|
|
|
pathlen, path, it->subtree_nr);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
if (0 <= it->entry_count) {
|
2007-09-06 11:20:11 +00:00
|
|
|
strbuf_add(buffer, it->sha1, 20);
|
2006-04-23 23:52:20 +00:00
|
|
|
}
|
|
|
|
for (i = 0; i < it->subtree_nr; i++) {
|
|
|
|
struct cache_tree_sub *down = it->down[i];
|
2006-04-26 00:40:02 +00:00
|
|
|
if (i) {
|
|
|
|
struct cache_tree_sub *prev = it->down[i-1];
|
|
|
|
if (subtree_name_cmp(down->name, down->namelen,
|
|
|
|
prev->name, prev->namelen) <= 0)
|
|
|
|
die("fatal - unsorted cache subtree");
|
|
|
|
}
|
2007-09-25 08:22:44 +00:00
|
|
|
write_one(buffer, down->cache_tree, down->name, down->namelen);
|
2006-04-23 23:52:20 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-09-25 08:22:44 +00:00
|
|
|
void cache_tree_write(struct strbuf *sb, struct cache_tree *root)
|
2006-04-23 23:52:20 +00:00
|
|
|
{
|
2007-09-25 08:22:44 +00:00
|
|
|
write_one(sb, root, "", 0);
|
2006-04-23 23:52:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct cache_tree *read_one(const char **buffer, unsigned long *size_p)
|
|
|
|
{
|
|
|
|
const char *buf = *buffer;
|
|
|
|
unsigned long size = *size_p;
|
2006-05-02 01:31:02 +00:00
|
|
|
const char *cp;
|
|
|
|
char *ep;
|
2006-04-23 23:52:20 +00:00
|
|
|
struct cache_tree *it;
|
|
|
|
int i, subtree_nr;
|
|
|
|
|
|
|
|
it = NULL;
|
|
|
|
/* skip name, but make sure name exists */
|
|
|
|
while (size && *buf) {
|
|
|
|
size--;
|
|
|
|
buf++;
|
|
|
|
}
|
|
|
|
if (!size)
|
|
|
|
goto free_return;
|
|
|
|
buf++; size--;
|
|
|
|
it = cache_tree();
|
2006-05-02 01:31:02 +00:00
|
|
|
|
|
|
|
cp = buf;
|
|
|
|
it->entry_count = strtol(cp, &ep, 10);
|
|
|
|
if (cp == ep)
|
|
|
|
goto free_return;
|
|
|
|
cp = ep;
|
|
|
|
subtree_nr = strtol(cp, &ep, 10);
|
|
|
|
if (cp == ep)
|
2006-04-23 23:52:20 +00:00
|
|
|
goto free_return;
|
|
|
|
while (size && *buf && *buf != '\n') {
|
|
|
|
size--;
|
|
|
|
buf++;
|
|
|
|
}
|
|
|
|
if (!size)
|
|
|
|
goto free_return;
|
|
|
|
buf++; size--;
|
|
|
|
if (0 <= it->entry_count) {
|
|
|
|
if (size < 20)
|
|
|
|
goto free_return;
|
2007-06-23 06:19:43 +00:00
|
|
|
hashcpy(it->sha1, (const unsigned char*)buf);
|
2006-04-23 23:52:20 +00:00
|
|
|
buf += 20;
|
|
|
|
size -= 20;
|
|
|
|
}
|
|
|
|
|
|
|
|
#if DEBUG
|
|
|
|
if (0 <= it->entry_count)
|
|
|
|
fprintf(stderr, "cache-tree <%s> (%d ent, %d subtree) %s\n",
|
|
|
|
*buffer, it->entry_count, subtree_nr,
|
|
|
|
sha1_to_hex(it->sha1));
|
|
|
|
else
|
|
|
|
fprintf(stderr, "cache-tree <%s> (%d subtrees) invalid\n",
|
|
|
|
*buffer, subtree_nr);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Just a heuristic -- we do not add directories that often but
|
|
|
|
* we do not want to have to extend it immediately when we do,
|
|
|
|
* hence +2.
|
|
|
|
*/
|
|
|
|
it->subtree_alloc = subtree_nr + 2;
|
|
|
|
it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *));
|
|
|
|
for (i = 0; i < subtree_nr; i++) {
|
|
|
|
/* read each subtree */
|
|
|
|
struct cache_tree *sub;
|
2006-04-26 00:40:02 +00:00
|
|
|
struct cache_tree_sub *subtree;
|
2006-04-23 23:52:20 +00:00
|
|
|
const char *name = buf;
|
2006-04-27 08:33:07 +00:00
|
|
|
|
2006-04-23 23:52:20 +00:00
|
|
|
sub = read_one(&buf, &size);
|
|
|
|
if (!sub)
|
|
|
|
goto free_return;
|
2006-04-27 08:33:07 +00:00
|
|
|
subtree = cache_tree_sub(it, name);
|
2006-04-26 00:40:02 +00:00
|
|
|
subtree->cache_tree = sub;
|
2006-04-23 23:52:20 +00:00
|
|
|
}
|
|
|
|
if (subtree_nr != it->subtree_nr)
|
|
|
|
die("cache-tree: internal error");
|
|
|
|
*buffer = buf;
|
|
|
|
*size_p = size;
|
|
|
|
return it;
|
|
|
|
|
|
|
|
free_return:
|
2006-04-25 04:18:58 +00:00
|
|
|
cache_tree_free(&it);
|
2006-04-23 23:52:20 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2006-04-25 04:18:58 +00:00
|
|
|
struct cache_tree *cache_tree_read(const char *buffer, unsigned long size)
|
2006-04-23 23:52:20 +00:00
|
|
|
{
|
2006-04-25 04:18:58 +00:00
|
|
|
if (buffer[0])
|
2006-04-23 23:52:20 +00:00
|
|
|
return NULL; /* not the whole tree */
|
|
|
|
return read_one(&buffer, &size);
|
|
|
|
}
|
2006-04-26 08:20:50 +00:00
|
|
|
|
2008-07-16 10:42:10 +00:00
|
|
|
static struct cache_tree *cache_tree_find(struct cache_tree *it, const char *path)
|
2006-04-26 08:20:50 +00:00
|
|
|
{
|
2009-05-20 22:53:57 +00:00
|
|
|
if (!it)
|
|
|
|
return NULL;
|
2006-04-26 08:20:50 +00:00
|
|
|
while (*path) {
|
|
|
|
const char *slash;
|
|
|
|
struct cache_tree_sub *sub;
|
|
|
|
|
|
|
|
slash = strchr(path, '/');
|
|
|
|
if (!slash)
|
|
|
|
slash = path + strlen(path);
|
|
|
|
/* between path and slash is the name of the
|
|
|
|
* subtree to look for.
|
|
|
|
*/
|
|
|
|
sub = find_subtree(it, path, slash - path, 0);
|
|
|
|
if (!sub)
|
|
|
|
return NULL;
|
|
|
|
it = sub->cache_tree;
|
|
|
|
if (slash)
|
|
|
|
while (*slash && *slash == '/')
|
|
|
|
slash++;
|
|
|
|
if (!slash || !*slash)
|
|
|
|
return it; /* prefix ended with slashes */
|
|
|
|
path = slash;
|
|
|
|
}
|
|
|
|
return it;
|
|
|
|
}
|
2008-01-11 06:49:35 +00:00
|
|
|
|
2009-05-20 18:04:35 +00:00
|
|
|
int write_cache_as_tree(unsigned char *sha1, int flags, const char *prefix)
|
2008-01-11 06:49:35 +00:00
|
|
|
{
|
|
|
|
int entries, was_valid, newfd;
|
2009-05-20 18:04:35 +00:00
|
|
|
struct lock_file *lock_file;
|
2008-01-11 06:49:35 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We can't free this memory, it becomes part of a linked list
|
|
|
|
* parsed atexit()
|
|
|
|
*/
|
2009-05-20 18:04:35 +00:00
|
|
|
lock_file = xcalloc(1, sizeof(struct lock_file));
|
2008-01-11 06:49:35 +00:00
|
|
|
|
|
|
|
newfd = hold_locked_index(lock_file, 1);
|
|
|
|
|
|
|
|
entries = read_cache();
|
|
|
|
if (entries < 0)
|
|
|
|
return WRITE_TREE_UNREADABLE_INDEX;
|
2009-05-20 18:04:35 +00:00
|
|
|
if (flags & WRITE_TREE_IGNORE_CACHE_TREE)
|
|
|
|
cache_tree_free(&(active_cache_tree));
|
2008-01-11 06:49:35 +00:00
|
|
|
|
|
|
|
if (!active_cache_tree)
|
|
|
|
active_cache_tree = cache_tree();
|
|
|
|
|
|
|
|
was_valid = cache_tree_fully_valid(active_cache_tree);
|
|
|
|
if (!was_valid) {
|
2009-05-20 18:04:35 +00:00
|
|
|
int missing_ok = flags & WRITE_TREE_MISSING_OK;
|
|
|
|
|
2008-01-11 06:49:35 +00:00
|
|
|
if (cache_tree_update(active_cache_tree,
|
|
|
|
active_cache, active_nr,
|
|
|
|
missing_ok, 0) < 0)
|
|
|
|
return WRITE_TREE_UNMERGED_INDEX;
|
|
|
|
if (0 <= newfd) {
|
|
|
|
if (!write_cache(newfd, active_cache, active_nr) &&
|
|
|
|
!commit_lock_file(lock_file))
|
|
|
|
newfd = -1;
|
|
|
|
}
|
|
|
|
/* Not being able to write is fine -- we are only interested
|
|
|
|
* in updating the cache-tree part, and if the next caller
|
|
|
|
* ends up using the old index with unupdated cache-tree part
|
|
|
|
* it misses the work we did here, but that is just a
|
|
|
|
* performance penalty and not a big deal.
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
|
|
|
|
if (prefix) {
|
|
|
|
struct cache_tree *subtree =
|
|
|
|
cache_tree_find(active_cache_tree, prefix);
|
|
|
|
if (!subtree)
|
|
|
|
return WRITE_TREE_PREFIX_ERROR;
|
|
|
|
hashcpy(sha1, subtree->sha1);
|
|
|
|
}
|
|
|
|
else
|
|
|
|
hashcpy(sha1, active_cache_tree->sha1);
|
|
|
|
|
|
|
|
if (0 <= newfd)
|
|
|
|
rollback_lock_file(lock_file);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2009-04-20 10:58:18 +00:00
|
|
|
|
|
|
|
static void prime_cache_tree_rec(struct cache_tree *it, struct tree *tree)
|
|
|
|
{
|
|
|
|
struct tree_desc desc;
|
|
|
|
struct name_entry entry;
|
|
|
|
int cnt;
|
|
|
|
|
|
|
|
hashcpy(it->sha1, tree->object.sha1);
|
|
|
|
init_tree_desc(&desc, tree->buffer, tree->size);
|
|
|
|
cnt = 0;
|
|
|
|
while (tree_entry(&desc, &entry)) {
|
|
|
|
if (!S_ISDIR(entry.mode))
|
|
|
|
cnt++;
|
|
|
|
else {
|
|
|
|
struct cache_tree_sub *sub;
|
|
|
|
struct tree *subtree = lookup_tree(entry.sha1);
|
|
|
|
if (!subtree->object.parsed)
|
|
|
|
parse_tree(subtree);
|
|
|
|
sub = cache_tree_sub(it, entry.path);
|
|
|
|
sub->cache_tree = cache_tree();
|
|
|
|
prime_cache_tree_rec(sub->cache_tree, subtree);
|
|
|
|
cnt += sub->cache_tree->entry_count;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
it->entry_count = cnt;
|
|
|
|
}
|
|
|
|
|
|
|
|
void prime_cache_tree(struct cache_tree **it, struct tree *tree)
|
|
|
|
{
|
|
|
|
cache_tree_free(it);
|
|
|
|
*it = cache_tree();
|
|
|
|
prime_cache_tree_rec(*it, tree);
|
|
|
|
}
|
Optimize "diff-index --cached" using cache-tree
When running "diff-index --cached" after making a change to only a small
portion of the index, there is no point unpacking unchanged subtrees into
the index recursively, only to find that all entries match anyway. Tweak
unpack_trees() logic that is used to read in the tree object to catch the
case where the tree entry we are looking at matches the index as a whole
by looking at the cache-tree.
As an exercise, after modifying a few paths in the kernel tree, here are
a few numbers on my Athlon 64X2 3800+:
(without patch, hot cache)
$ /usr/bin/time git diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.07user 0.02system 0:00.09elapsed 102%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+9407minor)pagefaults 0swaps
(with patch, hot cache)
$ /usr/bin/time ../git.git/git-diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.02user 0.00system 0:00.02elapsed 103%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+2446minor)pagefaults 0swaps
Cold cache numbers are very impressive, but it does not matter very much
in practice:
(without patch, cold cache)
$ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches'
$ /usr/bin/time git diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.06user 0.17system 0:10.26elapsed 2%CPU (0avgtext+0avgdata 0maxresident)k
247032inputs+0outputs (1172major+8237minor)pagefaults 0swaps
(with patch, cold cache)
$ su root sh -c 'echo 3 >/proc/sys/vm/drop_caches'
$ /usr/bin/time ../git.git/git-diff --cached --raw
:100644 100644 b57e1f5... e69de29... M Makefile
:100644 000000 8c86b72... 0000000... D arch/x86/Makefile
:000000 100644 0000000... e69de29... A arche
0.02user 0.01system 0:01.01elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k
18440inputs+0outputs (79major+2369minor)pagefaults 0swaps
This of course helps "git status" as well.
(without patch, hot cache)
$ /usr/bin/time ../git.git/git-status >/dev/null
0.17user 0.18system 0:00.35elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+5336outputs (0major+10970minor)pagefaults 0swaps
(with patch, hot cache)
$ /usr/bin/time ../git.git/git-status >/dev/null
0.10user 0.16system 0:00.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+5336outputs (0major+3921minor)pagefaults 0swaps
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-05-20 22:57:22 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* find the cache_tree that corresponds to the current level without
|
|
|
|
* exploding the full path into textual form. The root of the
|
|
|
|
* cache tree is given as "root", and our current level is "info".
|
|
|
|
* (1) When at root level, info->prev is NULL, so it is "root" itself.
|
|
|
|
* (2) Otherwise, find the cache_tree that corresponds to one level
|
|
|
|
* above us, and find ourselves in there.
|
|
|
|
*/
|
|
|
|
static struct cache_tree *find_cache_tree_from_traversal(struct cache_tree *root,
|
|
|
|
struct traverse_info *info)
|
|
|
|
{
|
|
|
|
struct cache_tree *our_parent;
|
|
|
|
|
|
|
|
if (!info->prev)
|
|
|
|
return root;
|
|
|
|
our_parent = find_cache_tree_from_traversal(root, info->prev);
|
|
|
|
return cache_tree_find(our_parent, info->name.path);
|
|
|
|
}
|
|
|
|
|
|
|
|
int cache_tree_matches_traversal(struct cache_tree *root,
|
|
|
|
struct name_entry *ent,
|
|
|
|
struct traverse_info *info)
|
|
|
|
{
|
|
|
|
struct cache_tree *it;
|
|
|
|
|
|
|
|
it = find_cache_tree_from_traversal(root, info);
|
|
|
|
it = cache_tree_find(it, ent->path);
|
|
|
|
if (it && it->entry_count > 0 && !hashcmp(ent->sha1, it->sha1))
|
|
|
|
return it->entry_count;
|
|
|
|
return 0;
|
|
|
|
}
|