git/cache-tree.c

731 строка
17 KiB
C
Исходник Обычный вид История

#include "cache.h"
#include "lockfile.h"
#include "tree.h"
#include "tree-walk.h"
#include "cache-tree.h"
#ifndef DEBUG
#define DEBUG 0
#endif
struct cache_tree *cache_tree(void)
{
struct cache_tree *it = xcalloc(1, sizeof(struct cache_tree));
it->entry_count = -1;
return it;
}
void cache_tree_free(struct cache_tree **it_p)
{
int i;
struct cache_tree *it = *it_p;
if (!it)
return;
for (i = 0; i < it->subtree_nr; i++)
if (it->down[i]) {
cache_tree_free(&it->down[i]->cache_tree);
free(it->down[i]);
}
free(it->down);
free(it);
*it_p = NULL;
}
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 - lo) / 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;
}
static struct cache_tree_sub *find_subtree(struct cache_tree *it,
const char *path,
int pathlen,
int create)
{
struct cache_tree_sub *down;
int pos = subtree_pos(it, path, pathlen);
if (0 <= pos)
return it->down[pos];
if (!create)
return NULL;
pos = -pos-1;
ALLOC_GROW(it->down, it->subtree_nr + 1, it->subtree_alloc);
it->subtree_nr++;
FLEX_ALLOC_MEM(down, name, path, pathlen);
down->cache_tree = NULL;
down->namelen = pathlen;
if (pos < it->subtree_nr)
MOVE_ARRAY(it->down + pos + 1, it->down + pos,
it->subtree_nr - pos - 1);
it->down[pos] = down;
return down;
}
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);
}
static int do_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;
#if DEBUG
fprintf(stderr, "cache-tree invalidate <%s>\n", path);
#endif
if (!it)
return 0;
slash = strchrnul(path, '/');
namelen = slash - path;
it->entry_count = -1;
if (!*slash) {
int pos;
pos = subtree_pos(it, path, namelen);
if (0 <= pos) {
cache_tree_free(&it->down[pos]->cache_tree);
free(it->down[pos]);
/* 0 1 2 3 4 5
* ^ ^subtree_nr = 6
* pos
* move 4 and 5 up one place (2 entries)
* 2 = 6 - 3 - 1 = subtree_nr - pos - 1
*/
MOVE_ARRAY(it->down + pos, it->down + pos + 1,
it->subtree_nr - pos - 1);
it->subtree_nr--;
}
return 1;
}
down = find_subtree(it, path, namelen, 0);
if (down)
do_invalidate_path(down->cache_tree, slash + 1);
return 1;
}
void cache_tree_invalidate_path(struct index_state *istate, const char *path)
{
if (do_invalidate_path(istate->cache_tree, path))
istate->cache_changed |= CACHE_TREE_CHANGED;
}
static int verify_cache(struct cache_entry **cache,
int entries, int flags)
{
int i, funny;
int silent = flags & WRITE_TREE_SILENT;
/* Verify that the tree is merged */
funny = 0;
for (i = 0; i < entries; i++) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 19:29:00 +04:00
const 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 23:55:48 +04:00
if (ce_stage(ce)) {
if (silent)
return -1;
if (10 < ++funny) {
fprintf(stderr, "...\n");
break;
}
fprintf(stderr, "%s: unmerged (%s)\n",
ce->name, oid_to_hex(&ce->oid));
}
}
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 {
cache_tree_free(&s->cache_tree);
free(s);
it->subtree_nr--;
}
}
}
int cache_tree_fully_valid(struct cache_tree *it)
{
int i;
if (!it)
return 0;
if (it->entry_count < 0 || !has_sha1_file(it->oid.hash))
return 0;
for (i = 0; i < it->subtree_nr; i++) {
if (!cache_tree_fully_valid(it->down[i]->cache_tree))
return 0;
}
return 1;
}
static int update_one(struct cache_tree *it,
struct cache_entry **cache,
int entries,
const char *base,
int baselen,
int *skip_count,
int flags)
{
struct strbuf buffer;
int missing_ok = flags & WRITE_TREE_MISSING_OK;
int dryrun = flags & WRITE_TREE_DRY_RUN;
int repair = flags & WRITE_TREE_REPAIR;
int to_invalidate = 0;
int i;
assert(!(dryrun && repair));
*skip_count = 0;
if (0 <= it->entry_count && has_sha1_file(it->oid.hash))
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.
*/
i = 0;
while (i < entries) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 19:29:00 +04:00
const struct cache_entry *ce = cache[i];
struct cache_tree_sub *sub;
const char *path, *slash;
int pathlen, sublen, subcnt, subskip;
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) {
i++;
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,
&subskip,
flags);
if (subcnt < 0)
return subcnt;
cache-tree: avoid infinite loop on zero-entry tree The loop in cache-tree's update_one iterates over all the entries in the index. For each one, we find the cache-tree subtree which represents our path (creating it if necessary), and then recurse into update_one again. The return value we get is the number of index entries that belonged in that subtree. So for example, with entries: a/one a/two b/one We start by processing the first entry, "a/one". We would find the subtree for "a" and recurse into update_one. That would then handle "a/one" and "a/two", and return the value 2. The parent function then skips past the 2 handled entries, and we continue by processing "b/one". If the recursed-into update_one ever returns 0, then we make no forward progress in our loop. We would process "a/one" over and over, infinitely. This should not happen normally. Any subtree we create must have at least one path in it (the one that we are processing!). However, we may also reuse a cache-tree entry we found in the on-disk index. For the same reason, this should also never have zero entries. However, certain buggy versions of libgit2 could produce such bogus cache-tree records. The libgit2 bug has since been fixed, but it does not hurt to protect ourselves against bogus input coming from the on-disk data structures. Note that this is not a die("BUG") or assert, because it is not an internal bug, but rather a corrupted on-disk structure. It's possible that we could even recover from it (by throwing out the bogus cache-tree entry), but it is not worth the effort; the important thing is that we report an error instead of looping infinitely. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-10-29 20:11:58 +03:00
if (!subcnt)
die("index cache-tree records empty sub-tree");
i += subcnt;
sub->count = subcnt; /* to be used in the next loop */
*skip_count += subskip;
sub->used = 1;
}
discard_unused_subtrees(it);
/*
* Then write out the tree object for this level.
*/
strbuf_init(&buffer, 8192);
i = 0;
while (i < entries) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 19:29:00 +04:00
const struct cache_entry *ce = cache[i];
cache-tree.c: fix i-t-a entry skipping directory updates sometimes Commit 3cf773e (cache-tree: fix writing cache-tree when CE_REMOVE is present - 2012-12-16) skips i-t-a entries when building trees objects from the index. Unfortunately it may skip too much. The code in question checks if an entry is an i-t-a one, then no tree entry will be written. But it does not take into account that directories can also be written with the same code. Suppose we have this in the index. a-file subdir/file1 subdir/file2 subdir/file3 the-last-file We write an entry for a-file as normal and move on to subdir/file1, where we realize the entry name for this level is simply just "subdir", write down an entry for "subdir" then jump three items ahead to the-last-file. That is what happens normally when the first file in subdir is not an i-t-a entry. If subdir/file1 is an i-t-a, because of the broken condition in this code, we still think "subdir" is an i-t-a file and not writing "subdir" down and jump to the-last-file. The result tree now only has two items: a-file and the-last-file. subdir should be there too (even though it only records two sub-entries, file2 and file3). If the i-t-a entry is subdir/file2 or subdir/file3, this is not a problem because we jump over them anyway. Which may explain why the bug is hidden for nearly four years. Fix it by making sure we only skip i-t-a entries when the entry in question is actual an index entry, not a directory. Reported-by: Yuri Kanivetsky <yuri.kanivetsky@gmail.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-07-16 08:06:26 +03:00
struct cache_tree_sub *sub = NULL;
const char *path, *slash;
int pathlen, entlen;
const struct object_id *oid;
unsigned mode;
int expected_missing = 0;
int contains_ita = 0;
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->count;
oid = &sub->cache_tree->oid;
mode = S_IFDIR;
contains_ita = sub->cache_tree->entry_count < 0;
if (contains_ita) {
to_invalidate = 1;
expected_missing = 1;
}
}
else {
oid = &ce->oid;
mode = ce->ce_mode;
entlen = pathlen - baselen;
i++;
}
cache-tree: reject entries with null sha1 We generally disallow null sha1s from entering the index, due to 4337b5856 (do not write null sha1s to on-disk index, 2012-07-28). However, we loosened that in 83bd7437c (write_index: optionally allow broken null sha1s, 2013-08-27) so that tools like filter-branch could be used to repair broken history. However, we should make sure that these broken entries do not get propagated into new trees. For most entries, we'd catch them with the missing-object check (since presumably the null sha1 does not exist in our object database). But gitlink entries do not need reachability, so we may blindly copy the entry into a bogus tree. This patch rejects all null sha1s (with the same "invalid entry" message that missing objects get) when building trees from the index. It does so even for non-gitlinks, and even when "write-tree" is given the --missing-ok flag. The null sha1 is a special sentinel value that is already rejected in trees by fsck; whether the object exists or not, it is an error to put it in a tree. Note that for this to work, we must also avoid reusing an existing cache-tree that contains the null sha1. This patch does so by just refusing to write out any cache tree when the index contains a null sha1. This is blunter than we need to be; we could just reject the subtree that contains the offending entry. But it's not worth the complexity. The behavior is unchanged unless you have a broken index entry, and even then we'd refuse the whole index write unless the emergency GIT_ALLOW_NULL_SHA1 is in use. And even then the end result is only a performance drop (any write-tree will have to generate the whole cache-tree from scratch). The tests bear some explanation. The existing test in t7009 doesn't catch this problem, because our index-filter runs "git rm --cached", which will try to rewrite the updated index and barf on the bogus entry. So we never even make it to write-tree. The new test there adds a noop index-filter, which does show the problem. The new tests in t1601 are slightly redundant with what filter-branch is doing under the hood in t7009. But as they're much more direct, they're easier to reason about. And should filter-branch ever change or go away, we'd want to make sure that these plumbing commands behave sanely. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-04-21 21:46:17 +03:00
if (is_null_oid(oid) ||
(mode != S_IFGITLINK && !missing_ok && !has_object_file(oid))) {
strbuf_release(&buffer);
if (expected_missing)
return -1;
return error("invalid object %06o %s for '%.*s'",
mode, oid_to_hex(oid), entlen+baselen, path);
}
/*
* CE_REMOVE entries are removed before the index is
* written to disk. Skip them to remain consistent
* with the future on-disk index.
*/
if (ce->ce_flags & CE_REMOVE) {
*skip_count = *skip_count + 1;
continue;
}
/*
* CE_INTENT_TO_ADD entries exist on on-disk index but
* they are not part of generated trees. Invalidate up
* to root to force cache-tree users to read elsewhere.
*/
cache-tree.c: fix i-t-a entry skipping directory updates sometimes Commit 3cf773e (cache-tree: fix writing cache-tree when CE_REMOVE is present - 2012-12-16) skips i-t-a entries when building trees objects from the index. Unfortunately it may skip too much. The code in question checks if an entry is an i-t-a one, then no tree entry will be written. But it does not take into account that directories can also be written with the same code. Suppose we have this in the index. a-file subdir/file1 subdir/file2 subdir/file3 the-last-file We write an entry for a-file as normal and move on to subdir/file1, where we realize the entry name for this level is simply just "subdir", write down an entry for "subdir" then jump three items ahead to the-last-file. That is what happens normally when the first file in subdir is not an i-t-a entry. If subdir/file1 is an i-t-a, because of the broken condition in this code, we still think "subdir" is an i-t-a file and not writing "subdir" down and jump to the-last-file. The result tree now only has two items: a-file and the-last-file. subdir should be there too (even though it only records two sub-entries, file2 and file3). If the i-t-a entry is subdir/file2 or subdir/file3, this is not a problem because we jump over them anyway. Which may explain why the bug is hidden for nearly four years. Fix it by making sure we only skip i-t-a entries when the entry in question is actual an index entry, not a directory. Reported-by: Yuri Kanivetsky <yuri.kanivetsky@gmail.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-07-16 08:06:26 +03:00
if (!sub && ce_intent_to_add(ce)) {
to_invalidate = 1;
continue;
}
/*
* "sub" can be an empty tree if all subentries are i-t-a.
*/
if (contains_ita && !oidcmp(oid, &empty_tree_oid))
continue;
strbuf_grow(&buffer, entlen + 100);
strbuf_addf(&buffer, "%o %.*s%c", mode, entlen, path + baselen, '\0');
strbuf_add(&buffer, oid->hash, the_hash_algo->rawsz);
#if DEBUG
fprintf(stderr, "cache-tree update-one %o %.*s\n",
mode, entlen, path + baselen);
#endif
}
if (repair) {
struct object_id oid;
hash_object_file(buffer.buf, buffer.len, tree_type, &oid);
if (has_object_file(&oid))
oidcpy(&it->oid, &oid);
else
to_invalidate = 1;
} else if (dryrun) {
hash_object_file(buffer.buf, buffer.len, tree_type, &it->oid);
} else if (write_object_file(buffer.buf, buffer.len, tree_type,
&it->oid)) {
strbuf_release(&buffer);
return -1;
}
strbuf_release(&buffer);
it->entry_count = to_invalidate ? -1 : i - *skip_count;
#if DEBUG
fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n",
it->entry_count, it->subtree_nr,
oid_to_hex(&it->oid));
#endif
return i;
}
int cache_tree_update(struct index_state *istate, int flags)
{
struct cache_tree *it = istate->cache_tree;
struct cache_entry **cache = istate->cache;
int entries = istate->cache_nr;
int skip, i = verify_cache(cache, entries, flags);
if (i)
return i;
i = update_one(it, cache, entries, "", 0, &skip, flags);
if (i < 0)
return i;
istate->cache_changed |= CACHE_TREE_CHANGED;
return 0;
}
static void write_one(struct strbuf *buffer, struct cache_tree *it,
const char *path, int pathlen)
{
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.
*/
strbuf_grow(buffer, pathlen + 100);
strbuf_add(buffer, path, pathlen);
strbuf_addf(buffer, "%c%d %d\n", 0, it->entry_count, it->subtree_nr);
#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,
oid_to_hex(&it->oid));
else
fprintf(stderr, "cache-tree <%.*s> (%d subtree) invalid\n",
pathlen, path, it->subtree_nr);
#endif
if (0 <= it->entry_count) {
strbuf_add(buffer, it->oid.hash, the_hash_algo->rawsz);
}
for (i = 0; i < it->subtree_nr; i++) {
struct cache_tree_sub *down = it->down[i];
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");
}
write_one(buffer, down->cache_tree, down->name, down->namelen);
}
}
void cache_tree_write(struct strbuf *sb, struct cache_tree *root)
{
write_one(sb, root, "", 0);
}
static struct cache_tree *read_one(const char **buffer, unsigned long *size_p)
{
const char *buf = *buffer;
unsigned long size = *size_p;
const char *cp;
char *ep;
struct cache_tree *it;
int i, subtree_nr;
const unsigned rawsz = the_hash_algo->rawsz;
it = NULL;
/* skip name, but make sure name exists */
while (size && *buf) {
size--;
buf++;
}
if (!size)
goto free_return;
buf++; size--;
it = cache_tree();
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)
goto free_return;
while (size && *buf && *buf != '\n') {
size--;
buf++;
}
if (!size)
goto free_return;
buf++; size--;
if (0 <= it->entry_count) {
if (size < rawsz)
goto free_return;
memcpy(it->oid.hash, (const unsigned char*)buf, rawsz);
buf += rawsz;
size -= rawsz;
}
#if DEBUG
if (0 <= it->entry_count)
fprintf(stderr, "cache-tree <%s> (%d ent, %d subtree) %s\n",
*buffer, it->entry_count, subtree_nr,
oid_to_hex(&it->oid));
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;
struct cache_tree_sub *subtree;
const char *name = buf;
sub = read_one(&buf, &size);
if (!sub)
goto free_return;
subtree = cache_tree_sub(it, name);
subtree->cache_tree = sub;
}
if (subtree_nr != it->subtree_nr)
die("cache-tree: internal error");
*buffer = buf;
*size_p = size;
return it;
free_return:
cache_tree_free(&it);
return NULL;
}
struct cache_tree *cache_tree_read(const char *buffer, unsigned long size)
{
if (buffer[0])
return NULL; /* not the whole tree */
return read_one(&buffer, &size);
}
static struct cache_tree *cache_tree_find(struct cache_tree *it, const char *path)
{
if (!it)
return NULL;
while (*path) {
const char *slash;
struct cache_tree_sub *sub;
slash = strchrnul(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;
path = slash;
while (*path == '/')
path++;
}
return it;
}
int write_index_as_tree(struct object_id *oid, struct index_state *index_state, const char *index_path, int flags, const char *prefix)
{
int entries, was_valid;
struct lock_file lock_file = LOCK_INIT;
int ret = 0;
hold_lock_file_for_update(&lock_file, index_path, LOCK_DIE_ON_ERROR);
read-cache: fix reading the shared index for other repos read_index_from() takes a path argument for the location of the index file. For reading the shared index in split index mode however it just ignores that path argument, and reads it from the gitdir of the current repository. This works as long as an index in the_repository is read. Once that changes, such as when we read the index of a submodule, or of a different working tree than the current one, the gitdir of the_repository will no longer contain the appropriate shared index, and git will fail to read it. For example t3007-ls-files-recurse-submodules.sh was broken with GIT_TEST_SPLIT_INDEX set in 188dce131f ("ls-files: use repository object", 2017-06-22), and t7814-grep-recurse-submodules.sh was also broken in a similar manner, probably by introducing struct repository there, although I didn't track down the exact commit for that. be489d02d2 ("revision.c: --indexed-objects add objects from all worktrees", 2017-08-23) breaks with split index mode in a similar manner, not erroring out when it can't read the index, but instead carrying on with pruning, without taking the index of the worktree into account. Fix this by passing an additional gitdir parameter to read_index_from, to indicate where it should look for and read the shared index from. read_cache_from() defaults to using the gitdir of the_repository. As it is mostly a convenience macro, having to pass get_git_dir() for every call seems overkill, and if necessary users can have more control by using read_index_from(). Helped-by: Brandon Williams <bmwill@google.com> Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-08 01:30:13 +03:00
entries = read_index_from(index_state, index_path, get_git_dir());
if (entries < 0) {
ret = WRITE_TREE_UNREADABLE_INDEX;
goto out;
}
if (flags & WRITE_TREE_IGNORE_CACHE_TREE)
cache_tree_free(&index_state->cache_tree);
if (!index_state->cache_tree)
index_state->cache_tree = cache_tree();
was_valid = cache_tree_fully_valid(index_state->cache_tree);
if (!was_valid) {
if (cache_tree_update(index_state, flags) < 0) {
ret = WRITE_TREE_UNMERGED_INDEX;
goto out;
}
write_locked_index(index_state, &lock_file, COMMIT_LOCK);
/* 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;
subtree = cache_tree_find(index_state->cache_tree, prefix);
if (!subtree) {
ret = WRITE_TREE_PREFIX_ERROR;
goto out;
}
oidcpy(oid, &subtree->oid);
}
else
oidcpy(oid, &index_state->cache_tree->oid);
out:
rollback_lock_file(&lock_file);
return ret;
}
int write_cache_as_tree(struct object_id *oid, int flags, const char *prefix)
{
return write_index_as_tree(oid, &the_index, get_index_file(), flags, prefix);
}
static void prime_cache_tree_rec(struct cache_tree *it, struct tree *tree)
{
struct tree_desc desc;
struct name_entry entry;
int cnt;
oidcpy(&it->oid, &tree->object.oid);
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.oid);
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 index_state *istate, struct tree *tree)
{
cache_tree_free(&istate->cache_tree);
istate->cache_tree = cache_tree();
prime_cache_tree_rec(istate->cache_tree, tree);
istate->cache_changed |= CACHE_TREE_CHANGED;
}
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>
2009-05-21 02:57:22 +04:00
/*
* 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 && !oidcmp(ent->oid, &it->oid))
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>
2009-05-21 02:57:22 +04:00
return it->entry_count;
return 0;
}
int update_main_cache_tree(int flags)
{
if (!the_index.cache_tree)
the_index.cache_tree = cache_tree();
return cache_tree_update(&the_index, flags);
}