Staging
v0.7.0
v0.7.0
Revision cb99a34e23e32ca8e94bafaa9699cfd133a17fd3 authored by Derrick Stolee on 24 October 2019, 13:40:42 UTC, committed by Junio C Hamano on 25 October 2019, 02:19:16 UTC
The previous commit includes a failing test for an issue around fetch.writeCommitGraph and fetching in a repo with a submodule. Here, we fix that bug and set the test to "test_expect_success". The problem arises with this set of commands when the remote repo at <url> has a submodule. Note that --recurse-submodules is not needed to demonstrate the bug. $ git clone <url> test $ cd test $ git -c fetch.writeCommitGraph=true fetch origin Computing commit graph generation numbers: 100% (12/12), done. BUG: commit-graph.c:886: missing parent <hash1> for commit <hash2> Aborted (core dumped) As an initial fix, I converted the code in builtin/fetch.c that calls write_commit_graph_reachable() to instead launch a "git commit-graph write --reachable --split" process. That code worked, but is not how we want the feature to work long-term. That test did demonstrate that the issue must be something to do with internal state of the 'git fetch' process. The write_commit_graph() method in commit-graph.c ensures the commits we plan to write are "closed under reachability" using close_reachable(). This method walks from the input commits, and uses the UNINTERESTING flag to mark which commits have already been visited. This allows the walk to take O(N) time, where N is the number of commits, instead of O(P) time, where P is the number of paths. (The number of paths can be exponential in the number of commits.) However, the UNINTERESTING flag is used in lots of places in the codebase. This flag usually means some barrier to stop a commit walk, such as in revision-walking to compare histories. It is not often cleared after the walk completes because the starting points of those walks do not have the UNINTERESTING flag, and clear_commit_marks() would stop immediately. This is happening during a 'git fetch' call with a remote. The fetch negotiation is comparing the remote refs with the local refs and marking some commits as UNINTERESTING. I tested running clear_commit_marks_many() to clear the UNINTERESTING flag inside close_reachable(), but the tips did not have the flag, so that did nothing. It turns out that the calculate_changed_submodule_paths() method is at fault. Thanks, Peff, for pointing out this detail! More specifically, for each submodule, the collect_changed_submodules() runs a revision walk to essentially do file-history on the list of submodules. That revision walk marks commits UNININTERESTING if they are simplified away by not changing the submodule. Instead, I finally arrived on the conclusion that I should use a flag that is not used in any other part of the code. In commit-reach.c, a number of flags were defined for commit walk algorithms. The REACHABLE flag seemed like it made the most sense, and it seems it was not actually used in the file. The REACHABLE flag was used in early versions of commit-reach.c, but was removed by 4fbcca4 (commit-reach: make can_all_from_reach... linear, 2018-07-20). Add the REACHABLE flag to commit-graph.c and use it instead of UNINTERESTING in close_reachable(). This fixes the bug in manual testing. Reported-by: Johannes Schindelin <johannes.schindelin@gmx.de> Helped-by: Jeff King <peff@peff.net> Helped-by: Szeder Gábor <szeder.dev@gmail.com> Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent e88aab9
symlinks.c
#include "cache.h"
static int threaded_check_leading_path(struct cache_def *cache, const char *name, int len);
static int threaded_has_dirs_only_path(struct cache_def *cache, const char *name, int len, int prefix_len);
/*
* Returns the length (on a path component basis) of the longest
* common prefix match of 'name_a' and 'name_b'.
*/
static int longest_path_match(const char *name_a, int len_a,
const char *name_b, int len_b,
int *previous_slash)
{
int max_len, match_len = 0, match_len_prev = 0, i = 0;
max_len = len_a < len_b ? len_a : len_b;
while (i < max_len && name_a[i] == name_b[i]) {
if (name_a[i] == '/') {
match_len_prev = match_len;
match_len = i;
}
i++;
}
/*
* Is 'name_b' a substring of 'name_a', the other way around,
* or is 'name_a' and 'name_b' the exact same string?
*/
if (i >= max_len && ((len_a > len_b && name_a[len_b] == '/') ||
(len_a < len_b && name_b[len_a] == '/') ||
(len_a == len_b))) {
match_len_prev = match_len;
match_len = i;
}
*previous_slash = match_len_prev;
return match_len;
}
static struct cache_def default_cache = CACHE_DEF_INIT;
static inline void reset_lstat_cache(struct cache_def *cache)
{
strbuf_reset(&cache->path);
cache->flags = 0;
/*
* The track_flags and prefix_len_stat_func members is only
* set by the safeguard rule inside lstat_cache()
*/
}
#define FL_DIR (1 << 0)
#define FL_NOENT (1 << 1)
#define FL_SYMLINK (1 << 2)
#define FL_LSTATERR (1 << 3)
#define FL_ERR (1 << 4)
#define FL_FULLPATH (1 << 5)
/*
* Check if name 'name' of length 'len' has a symlink leading
* component, or if the directory exists and is real, or not.
*
* To speed up the check, some information is allowed to be cached.
* This can be indicated by the 'track_flags' argument, which also can
* be used to indicate that we should check the full path.
*
* The 'prefix_len_stat_func' parameter can be used to set the length
* of the prefix, where the cache should use the stat() function
* instead of the lstat() function to test each path component.
*/
static int lstat_cache_matchlen(struct cache_def *cache,
const char *name, int len,
int *ret_flags, int track_flags,
int prefix_len_stat_func)
{
int match_len, last_slash, last_slash_dir, previous_slash;
int save_flags, ret;
struct stat st;
if (cache->track_flags != track_flags ||
cache->prefix_len_stat_func != prefix_len_stat_func) {
/*
* As a safeguard rule we clear the cache if the
* values of track_flags and/or prefix_len_stat_func
* does not match with the last supplied values.
*/
reset_lstat_cache(cache);
cache->track_flags = track_flags;
cache->prefix_len_stat_func = prefix_len_stat_func;
match_len = last_slash = 0;
} else {
/*
* Check to see if we have a match from the cache for
* the 2 "excluding" path types.
*/
match_len = last_slash =
longest_path_match(name, len, cache->path.buf,
cache->path.len, &previous_slash);
*ret_flags = cache->flags & track_flags & (FL_NOENT|FL_SYMLINK);
if (!(track_flags & FL_FULLPATH) && match_len == len)
match_len = last_slash = previous_slash;
if (*ret_flags && match_len == cache->path.len)
return match_len;
/*
* If we now have match_len > 0, we would know that
* the matched part will always be a directory.
*
* Also, if we are tracking directories and 'name' is
* a substring of the cache on a path component basis,
* we can return immediately.
*/
*ret_flags = track_flags & FL_DIR;
if (*ret_flags && len == match_len)
return match_len;
}
/*
* Okay, no match from the cache so far, so now we have to
* check the rest of the path components.
*/
*ret_flags = FL_DIR;
last_slash_dir = last_slash;
if (len > cache->path.len)
strbuf_grow(&cache->path, len - cache->path.len);
while (match_len < len) {
do {
cache->path.buf[match_len] = name[match_len];
match_len++;
} while (match_len < len && name[match_len] != '/');
if (match_len >= len && !(track_flags & FL_FULLPATH))
break;
last_slash = match_len;
cache->path.buf[last_slash] = '\0';
if (last_slash <= prefix_len_stat_func)
ret = stat(cache->path.buf, &st);
else
ret = lstat(cache->path.buf, &st);
if (ret) {
*ret_flags = FL_LSTATERR;
if (errno == ENOENT)
*ret_flags |= FL_NOENT;
} else if (S_ISDIR(st.st_mode)) {
last_slash_dir = last_slash;
continue;
} else if (S_ISLNK(st.st_mode)) {
*ret_flags = FL_SYMLINK;
} else {
*ret_flags = FL_ERR;
}
break;
}
/*
* At the end update the cache. Note that max 3 different
* path types, FL_NOENT, FL_SYMLINK and FL_DIR, can be cached
* for the moment!
*/
save_flags = *ret_flags & track_flags & (FL_NOENT|FL_SYMLINK);
if (save_flags && last_slash > 0) {
cache->path.buf[last_slash] = '\0';
cache->path.len = last_slash;
cache->flags = save_flags;
} else if ((track_flags & FL_DIR) && last_slash_dir > 0) {
/*
* We have a separate test for the directory case,
* since it could be that we have found a symlink or a
* non-existing directory and the track_flags says
* that we cannot cache this fact, so the cache would
* then have been left empty in this case.
*
* But if we are allowed to track real directories, we
* can still cache the path components before the last
* one (the found symlink or non-existing component).
*/
cache->path.buf[last_slash_dir] = '\0';
cache->path.len = last_slash_dir;
cache->flags = FL_DIR;
} else {
reset_lstat_cache(cache);
}
return match_len;
}
static int lstat_cache(struct cache_def *cache, const char *name, int len,
int track_flags, int prefix_len_stat_func)
{
int flags;
(void)lstat_cache_matchlen(cache, name, len, &flags, track_flags,
prefix_len_stat_func);
return flags;
}
#define USE_ONLY_LSTAT 0
/*
* Return non-zero if path 'name' has a leading symlink component
*/
int threaded_has_symlink_leading_path(struct cache_def *cache, const char *name, int len)
{
return lstat_cache(cache, name, len, FL_SYMLINK|FL_DIR, USE_ONLY_LSTAT) & FL_SYMLINK;
}
/*
* Return non-zero if path 'name' has a leading symlink component
*/
int has_symlink_leading_path(const char *name, int len)
{
return threaded_has_symlink_leading_path(&default_cache, name, len);
}
/*
* Return zero if path 'name' has a leading symlink component or
* if some leading path component does not exists.
*
* Return -1 if leading path exists and is a directory.
*
* Return path length if leading path exists and is neither a
* directory nor a symlink.
*/
int check_leading_path(const char *name, int len)
{
return threaded_check_leading_path(&default_cache, name, len);
}
/*
* Return zero if path 'name' has a leading symlink component or
* if some leading path component does not exists.
*
* Return -1 if leading path exists and is a directory.
*
* Return path length if leading path exists and is neither a
* directory nor a symlink.
*/
static int threaded_check_leading_path(struct cache_def *cache, const char *name, int len)
{
int flags;
int match_len = lstat_cache_matchlen(cache, name, len, &flags,
FL_SYMLINK|FL_NOENT|FL_DIR, USE_ONLY_LSTAT);
if (flags & FL_NOENT)
return 0;
else if (flags & FL_DIR)
return -1;
else
return match_len;
}
/*
* Return non-zero if all path components of 'name' exists as a
* directory. If prefix_len > 0, we will test with the stat()
* function instead of the lstat() function for a prefix length of
* 'prefix_len', thus we then allow for symlinks in the prefix part as
* long as those points to real existing directories.
*/
int has_dirs_only_path(const char *name, int len, int prefix_len)
{
return threaded_has_dirs_only_path(&default_cache, name, len, prefix_len);
}
/*
* Return non-zero if all path components of 'name' exists as a
* directory. If prefix_len > 0, we will test with the stat()
* function instead of the lstat() function for a prefix length of
* 'prefix_len', thus we then allow for symlinks in the prefix part as
* long as those points to real existing directories.
*/
static int threaded_has_dirs_only_path(struct cache_def *cache, const char *name, int len, int prefix_len)
{
return lstat_cache(cache, name, len,
FL_DIR|FL_FULLPATH, prefix_len) &
FL_DIR;
}
static struct strbuf removal = STRBUF_INIT;
static void do_remove_scheduled_dirs(int new_len)
{
while (removal.len > new_len) {
removal.buf[removal.len] = '\0';
if (rmdir(removal.buf))
break;
do {
removal.len--;
} while (removal.len > new_len &&
removal.buf[removal.len] != '/');
}
removal.len = new_len;
}
void schedule_dir_for_removal(const char *name, int len)
{
int match_len, last_slash, i, previous_slash;
match_len = last_slash = i =
longest_path_match(name, len, removal.buf, removal.len,
&previous_slash);
/* Find last slash inside 'name' */
while (i < len) {
if (name[i] == '/')
last_slash = i;
i++;
}
/*
* If we are about to go down the directory tree, we check if
* we must first go upwards the tree, such that we then can
* remove possible empty directories as we go upwards.
*/
if (match_len < last_slash && match_len < removal.len)
do_remove_scheduled_dirs(match_len);
/*
* If we go deeper down the directory tree, we only need to
* save the new path components as we go down.
*/
if (match_len < last_slash)
strbuf_add(&removal, &name[match_len], last_slash - match_len);
}
void remove_scheduled_dirs(void)
{
do_remove_scheduled_dirs(0);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...