2023-02-24 00:09:24 +00:00
|
|
|
#include "../git-compat-util.h"
|
|
|
|
#include "../alloc.h"
|
2023-04-22 20:17:20 +00:00
|
|
|
#include "../hash.h"
|
2017-04-16 06:41:31 +00:00
|
|
|
#include "../refs.h"
|
2023-04-22 20:17:20 +00:00
|
|
|
#include "../repository.h"
|
2017-04-16 06:41:31 +00:00
|
|
|
#include "refs-internal.h"
|
|
|
|
#include "ref-cache.h"
|
|
|
|
#include "../iterator.h"
|
|
|
|
|
|
|
|
void add_entry_to_dir(struct ref_dir *dir, struct ref_entry *entry)
|
|
|
|
{
|
|
|
|
ALLOC_GROW(dir->entries, dir->nr + 1, dir->alloc);
|
|
|
|
dir->entries[dir->nr++] = entry;
|
|
|
|
/* optimize for the case that entries are added in order */
|
|
|
|
if (dir->nr == 1 ||
|
|
|
|
(dir->nr == dir->sorted + 1 &&
|
|
|
|
strcmp(dir->entries[dir->nr - 2]->name,
|
|
|
|
dir->entries[dir->nr - 1]->name) < 0))
|
|
|
|
dir->sorted = dir->nr;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct ref_dir *get_ref_dir(struct ref_entry *entry)
|
|
|
|
{
|
|
|
|
struct ref_dir *dir;
|
|
|
|
assert(entry->flag & REF_DIR);
|
|
|
|
dir = &entry->u.subdir;
|
|
|
|
if (entry->flag & REF_INCOMPLETE) {
|
2017-04-16 06:41:34 +00:00
|
|
|
if (!dir->cache->fill_ref_dir)
|
2018-05-02 09:38:39 +00:00
|
|
|
BUG("incomplete ref_store without fill_ref_dir function");
|
2017-04-16 06:41:34 +00:00
|
|
|
|
|
|
|
dir->cache->fill_ref_dir(dir->cache->ref_store, dir, entry->name);
|
2017-04-16 06:41:31 +00:00
|
|
|
entry->flag &= ~REF_INCOMPLETE;
|
|
|
|
}
|
|
|
|
return dir;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct ref_entry *create_ref_entry(const char *refname,
|
2017-05-22 14:17:53 +00:00
|
|
|
const struct object_id *oid, int flag)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
|
|
|
struct ref_entry *ref;
|
|
|
|
|
|
|
|
FLEX_ALLOC_STR(ref, name, refname);
|
2017-05-06 22:10:24 +00:00
|
|
|
oidcpy(&ref->u.value.oid, oid);
|
2017-04-16 06:41:31 +00:00
|
|
|
ref->flag = flag;
|
|
|
|
return ref;
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:34 +00:00
|
|
|
struct ref_cache *create_ref_cache(struct ref_store *refs,
|
|
|
|
fill_ref_dir_fn *fill_ref_dir)
|
2017-04-16 06:41:32 +00:00
|
|
|
{
|
|
|
|
struct ref_cache *ret = xcalloc(1, sizeof(*ret));
|
|
|
|
|
2017-04-16 06:41:33 +00:00
|
|
|
ret->ref_store = refs;
|
2017-04-16 06:41:34 +00:00
|
|
|
ret->fill_ref_dir = fill_ref_dir;
|
2021-09-28 13:02:24 +00:00
|
|
|
ret->root = create_dir_entry(ret, "", 0);
|
2017-04-16 06:41:32 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
static void clear_ref_dir(struct ref_dir *dir);
|
|
|
|
|
2017-04-16 06:41:32 +00:00
|
|
|
static void free_ref_entry(struct ref_entry *entry)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
|
|
|
if (entry->flag & REF_DIR) {
|
|
|
|
/*
|
|
|
|
* Do not use get_ref_dir() here, as that might
|
|
|
|
* trigger the reading of loose refs.
|
|
|
|
*/
|
|
|
|
clear_ref_dir(&entry->u.subdir);
|
|
|
|
}
|
|
|
|
free(entry);
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:32 +00:00
|
|
|
void free_ref_cache(struct ref_cache *cache)
|
|
|
|
{
|
|
|
|
free_ref_entry(cache->root);
|
|
|
|
free(cache);
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
/*
|
|
|
|
* Clear and free all entries in dir, recursively.
|
|
|
|
*/
|
|
|
|
static void clear_ref_dir(struct ref_dir *dir)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
for (i = 0; i < dir->nr; i++)
|
|
|
|
free_ref_entry(dir->entries[i]);
|
2017-06-15 23:15:49 +00:00
|
|
|
FREE_AND_NULL(dir->entries);
|
2017-04-16 06:41:31 +00:00
|
|
|
dir->sorted = dir->nr = dir->alloc = 0;
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:33 +00:00
|
|
|
struct ref_entry *create_dir_entry(struct ref_cache *cache,
|
2021-09-28 13:02:24 +00:00
|
|
|
const char *dirname, size_t len)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
|
|
|
struct ref_entry *direntry;
|
2017-04-16 06:41:33 +00:00
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
FLEX_ALLOC_MEM(direntry, name, dirname, len);
|
2017-04-16 06:41:33 +00:00
|
|
|
direntry->u.subdir.cache = cache;
|
2021-09-28 13:02:24 +00:00
|
|
|
direntry->flag = REF_DIR | REF_INCOMPLETE;
|
2017-04-16 06:41:31 +00:00
|
|
|
return direntry;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int ref_entry_cmp(const void *a, const void *b)
|
|
|
|
{
|
|
|
|
struct ref_entry *one = *(struct ref_entry **)a;
|
|
|
|
struct ref_entry *two = *(struct ref_entry **)b;
|
|
|
|
return strcmp(one->name, two->name);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void sort_ref_dir(struct ref_dir *dir);
|
|
|
|
|
|
|
|
struct string_slice {
|
|
|
|
size_t len;
|
|
|
|
const char *str;
|
|
|
|
};
|
|
|
|
|
|
|
|
static int ref_entry_cmp_sslice(const void *key_, const void *ent_)
|
|
|
|
{
|
|
|
|
const struct string_slice *key = key_;
|
|
|
|
const struct ref_entry *ent = *(const struct ref_entry * const *)ent_;
|
|
|
|
int cmp = strncmp(key->str, ent->name, key->len);
|
|
|
|
if (cmp)
|
|
|
|
return cmp;
|
|
|
|
return '\0' - (unsigned char)ent->name[key->len];
|
|
|
|
}
|
|
|
|
|
|
|
|
int search_ref_dir(struct ref_dir *dir, const char *refname, size_t len)
|
|
|
|
{
|
|
|
|
struct ref_entry **r;
|
|
|
|
struct string_slice key;
|
|
|
|
|
|
|
|
if (refname == NULL || !dir->nr)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
sort_ref_dir(dir);
|
|
|
|
key.len = len;
|
|
|
|
key.str = refname;
|
|
|
|
r = bsearch(&key, dir->entries, dir->nr, sizeof(*dir->entries),
|
|
|
|
ref_entry_cmp_sslice);
|
|
|
|
|
2022-05-02 16:50:37 +00:00
|
|
|
if (!r)
|
2017-04-16 06:41:31 +00:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
return r - dir->entries;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Search for a directory entry directly within dir (without
|
|
|
|
* recursing). Sort dir if necessary. subdirname must be a directory
|
2021-09-28 13:02:23 +00:00
|
|
|
* name (i.e., end in '/'). Returns NULL if the desired
|
2017-04-16 06:41:31 +00:00
|
|
|
* directory cannot be found. dir must already be complete.
|
|
|
|
*/
|
|
|
|
static struct ref_dir *search_for_subdir(struct ref_dir *dir,
|
2021-09-28 13:02:23 +00:00
|
|
|
const char *subdirname, size_t len)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
|
|
|
int entry_index = search_ref_dir(dir, subdirname, len);
|
|
|
|
struct ref_entry *entry;
|
2021-09-28 13:02:23 +00:00
|
|
|
|
|
|
|
if (entry_index == -1)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
entry = dir->entries[entry_index];
|
2017-04-16 06:41:31 +00:00
|
|
|
return get_ref_dir(entry);
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:39 +00:00
|
|
|
/*
|
|
|
|
* If refname is a reference name, find the ref_dir within the dir
|
|
|
|
* tree that should hold refname. If refname is a directory name
|
|
|
|
* (i.e., it ends in '/'), then return that ref_dir itself. dir must
|
|
|
|
* represent the top-level directory and must already be complete.
|
2021-09-28 13:02:23 +00:00
|
|
|
* Sort ref_dirs and recurse into subdirectories as necessary. Will
|
2017-04-16 06:41:39 +00:00
|
|
|
* return NULL if the desired directory cannot be found.
|
|
|
|
*/
|
|
|
|
static struct ref_dir *find_containing_dir(struct ref_dir *dir,
|
2021-09-28 13:02:23 +00:00
|
|
|
const char *refname)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
|
|
|
const char *slash;
|
|
|
|
for (slash = strchr(refname, '/'); slash; slash = strchr(slash + 1, '/')) {
|
|
|
|
size_t dirnamelen = slash - refname + 1;
|
|
|
|
struct ref_dir *subdir;
|
2021-09-28 13:02:23 +00:00
|
|
|
subdir = search_for_subdir(dir, refname, dirnamelen);
|
2017-04-16 06:41:31 +00:00
|
|
|
if (!subdir) {
|
|
|
|
dir = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
dir = subdir;
|
|
|
|
}
|
|
|
|
|
|
|
|
return dir;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct ref_entry *find_ref_entry(struct ref_dir *dir, const char *refname)
|
|
|
|
{
|
|
|
|
int entry_index;
|
|
|
|
struct ref_entry *entry;
|
2021-09-28 13:02:23 +00:00
|
|
|
dir = find_containing_dir(dir, refname);
|
2017-04-16 06:41:31 +00:00
|
|
|
if (!dir)
|
|
|
|
return NULL;
|
|
|
|
entry_index = search_ref_dir(dir, refname, strlen(refname));
|
|
|
|
if (entry_index == -1)
|
|
|
|
return NULL;
|
|
|
|
entry = dir->entries[entry_index];
|
|
|
|
return (entry->flag & REF_DIR) ? NULL : entry;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Emit a warning and return true iff ref1 and ref2 have the same name
|
2017-11-05 08:42:09 +00:00
|
|
|
* and the same oid. Die if they have the same name but different
|
|
|
|
* oids.
|
2017-04-16 06:41:31 +00:00
|
|
|
*/
|
|
|
|
static int is_dup_ref(const struct ref_entry *ref1, const struct ref_entry *ref2)
|
|
|
|
{
|
|
|
|
if (strcmp(ref1->name, ref2->name))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Duplicate name; make sure that they don't conflict: */
|
|
|
|
|
|
|
|
if ((ref1->flag & REF_DIR) || (ref2->flag & REF_DIR))
|
|
|
|
/* This is impossible by construction */
|
|
|
|
die("Reference directory conflict: %s", ref1->name);
|
|
|
|
|
2018-08-28 21:22:48 +00:00
|
|
|
if (!oideq(&ref1->u.value.oid, &ref2->u.value.oid))
|
2017-04-16 06:41:31 +00:00
|
|
|
die("Duplicated ref, and SHA1s don't match: %s", ref1->name);
|
|
|
|
|
|
|
|
warning("Duplicated ref: %s", ref1->name);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Sort the entries in dir non-recursively (if they are not already
|
|
|
|
* sorted) and remove any duplicate entries.
|
|
|
|
*/
|
|
|
|
static void sort_ref_dir(struct ref_dir *dir)
|
|
|
|
{
|
|
|
|
int i, j;
|
|
|
|
struct ref_entry *last = NULL;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This check also prevents passing a zero-length array to qsort(),
|
|
|
|
* which is a problem on some platforms.
|
|
|
|
*/
|
|
|
|
if (dir->sorted == dir->nr)
|
|
|
|
return;
|
|
|
|
|
|
|
|
QSORT(dir->entries, dir->nr, ref_entry_cmp);
|
|
|
|
|
|
|
|
/* Remove any duplicates: */
|
|
|
|
for (i = 0, j = 0; j < dir->nr; j++) {
|
|
|
|
struct ref_entry *entry = dir->entries[j];
|
|
|
|
if (last && is_dup_ref(last, entry))
|
|
|
|
free_ref_entry(entry);
|
|
|
|
else
|
|
|
|
last = dir->entries[i++] = entry;
|
|
|
|
}
|
|
|
|
dir->sorted = dir->nr = i;
|
|
|
|
}
|
|
|
|
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
enum prefix_state {
|
|
|
|
/* All refs within the directory would match prefix: */
|
|
|
|
PREFIX_CONTAINS_DIR,
|
|
|
|
|
|
|
|
/* Some, but not all, refs within the directory might match prefix: */
|
|
|
|
PREFIX_WITHIN_DIR,
|
|
|
|
|
|
|
|
/* No refs within the directory could possibly match prefix: */
|
|
|
|
PREFIX_EXCLUDES_DIR
|
|
|
|
};
|
|
|
|
|
2017-04-16 06:41:39 +00:00
|
|
|
/*
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
* Return a `prefix_state` constant describing the relationship
|
|
|
|
* between the directory with the specified `dirname` and `prefix`.
|
2017-04-16 06:41:39 +00:00
|
|
|
*/
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
static enum prefix_state overlaps_prefix(const char *dirname,
|
|
|
|
const char *prefix)
|
|
|
|
{
|
|
|
|
while (*prefix && *dirname == *prefix) {
|
|
|
|
dirname++;
|
|
|
|
prefix++;
|
|
|
|
}
|
|
|
|
if (!*prefix)
|
|
|
|
return PREFIX_CONTAINS_DIR;
|
|
|
|
else if (!*dirname)
|
|
|
|
return PREFIX_WITHIN_DIR;
|
|
|
|
else
|
|
|
|
return PREFIX_EXCLUDES_DIR;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Load all of the refs from `dir` (recursively) that could possibly
|
|
|
|
* contain references matching `prefix` into our in-memory cache. If
|
|
|
|
* `prefix` is NULL, prime unconditionally.
|
|
|
|
*/
|
|
|
|
static void prime_ref_dir(struct ref_dir *dir, const char *prefix)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The hard work of loading loose refs is done by get_ref_dir(), so we
|
|
|
|
* just need to recurse through all of the sub-directories. We do not
|
|
|
|
* even need to care about sorting, as traversal order does not matter
|
|
|
|
* to us.
|
|
|
|
*/
|
|
|
|
int i;
|
|
|
|
for (i = 0; i < dir->nr; i++) {
|
|
|
|
struct ref_entry *entry = dir->entries[i];
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
if (!(entry->flag & REF_DIR)) {
|
|
|
|
/* Not a directory; no need to recurse. */
|
|
|
|
} else if (!prefix) {
|
|
|
|
/* Recurse in any case: */
|
|
|
|
prime_ref_dir(get_ref_dir(entry), NULL);
|
|
|
|
} else {
|
|
|
|
switch (overlaps_prefix(entry->name, prefix)) {
|
|
|
|
case PREFIX_CONTAINS_DIR:
|
|
|
|
/*
|
|
|
|
* Recurse, and from here down we
|
|
|
|
* don't have to check the prefix
|
|
|
|
* anymore:
|
|
|
|
*/
|
|
|
|
prime_ref_dir(get_ref_dir(entry), NULL);
|
|
|
|
break;
|
|
|
|
case PREFIX_WITHIN_DIR:
|
|
|
|
prime_ref_dir(get_ref_dir(entry), prefix);
|
|
|
|
break;
|
|
|
|
case PREFIX_EXCLUDES_DIR:
|
|
|
|
/* No need to prime this directory. */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2017-04-16 06:41:31 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A level in the reference hierarchy that is currently being iterated
|
|
|
|
* through.
|
|
|
|
*/
|
|
|
|
struct cache_ref_iterator_level {
|
|
|
|
/*
|
|
|
|
* The ref_dir being iterated over at this level. The ref_dir
|
|
|
|
* is sorted before being stored here.
|
|
|
|
*/
|
|
|
|
struct ref_dir *dir;
|
|
|
|
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
enum prefix_state prefix_state;
|
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
/*
|
|
|
|
* The index of the current entry within dir (which might
|
|
|
|
* itself be a directory). If index == -1, then the iteration
|
|
|
|
* hasn't yet begun. If index == dir->nr, then the iteration
|
|
|
|
* through this level is over.
|
|
|
|
*/
|
|
|
|
int index;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Represent an iteration through a ref_dir in the memory cache. The
|
|
|
|
* iteration recurses through subdirectories.
|
|
|
|
*/
|
|
|
|
struct cache_ref_iterator {
|
|
|
|
struct ref_iterator base;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The number of levels currently on the stack. This is always
|
|
|
|
* at least 1, because when it becomes zero the iteration is
|
|
|
|
* ended and this struct is freed.
|
|
|
|
*/
|
|
|
|
size_t levels_nr;
|
|
|
|
|
|
|
|
/* The number of levels that have been allocated on the stack */
|
|
|
|
size_t levels_alloc;
|
|
|
|
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
/*
|
|
|
|
* Only include references with this prefix in the iteration.
|
|
|
|
* The prefix is matched textually, without regard for path
|
|
|
|
* component boundaries.
|
|
|
|
*/
|
|
|
|
const char *prefix;
|
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
/*
|
|
|
|
* A stack of levels. levels[0] is the uppermost level that is
|
|
|
|
* being iterated over in this iteration. (This is not
|
|
|
|
* necessary the top level in the references hierarchy. If we
|
|
|
|
* are iterating through a subtree, then levels[0] will hold
|
|
|
|
* the ref_dir for that subtree, and subsequent levels will go
|
|
|
|
* on from there.)
|
|
|
|
*/
|
|
|
|
struct cache_ref_iterator_level *levels;
|
2021-10-08 21:08:16 +00:00
|
|
|
|
|
|
|
struct repository *repo;
|
2017-04-16 06:41:31 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator)
|
|
|
|
{
|
|
|
|
struct cache_ref_iterator *iter =
|
|
|
|
(struct cache_ref_iterator *)ref_iterator;
|
|
|
|
|
|
|
|
while (1) {
|
|
|
|
struct cache_ref_iterator_level *level =
|
|
|
|
&iter->levels[iter->levels_nr - 1];
|
|
|
|
struct ref_dir *dir = level->dir;
|
|
|
|
struct ref_entry *entry;
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
enum prefix_state entry_prefix_state;
|
2017-04-16 06:41:31 +00:00
|
|
|
|
|
|
|
if (level->index == -1)
|
|
|
|
sort_ref_dir(dir);
|
|
|
|
|
|
|
|
if (++level->index == level->dir->nr) {
|
|
|
|
/* This level is exhausted; pop up a level */
|
|
|
|
if (--iter->levels_nr == 0)
|
|
|
|
return ref_iterator_abort(ref_iterator);
|
|
|
|
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
entry = dir->entries[level->index];
|
|
|
|
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
if (level->prefix_state == PREFIX_WITHIN_DIR) {
|
|
|
|
entry_prefix_state = overlaps_prefix(entry->name, iter->prefix);
|
ref-cache.c: fix prefix matching in ref iteration
Update 'cache_ref_iterator_advance' to skip over refs that are not matched
by the given prefix.
Currently, a ref entry is considered "matched" if the entry name is fully
contained within the prefix:
* prefix: "refs/heads/v1"
* entry: "refs/heads/v1.0"
OR if the prefix is fully contained in the entry name:
* prefix: "refs/heads/v1.0"
* entry: "refs/heads/v1"
The first case is always correct, but the second is only correct if the ref
cache entry is a directory, for example:
* prefix: "refs/heads/example"
* entry: "refs/heads/"
Modify the logic in 'cache_ref_iterator_advance' to reflect these
expectations:
1. If 'overlaps_prefix' returns 'PREFIX_EXCLUDES_DIR', then the prefix and
ref cache entry do not overlap at all. Skip this entry.
2. If 'overlaps_prefix' returns 'PREFIX_WITHIN_DIR', then the prefix matches
inside this entry if it is a directory. Skip if the entry is not a
directory, otherwise iterate over it.
3. Otherwise, 'overlaps_prefix' returned 'PREFIX_CONTAINS_DIR', indicating
that the cache entry (directory or not) is fully contained by or equal to
the prefix. Iterate over this entry.
Note that condition 2 relies on the names of directory entries having the
appropriate trailing slash. The existing function documentation of
'create_dir_entry' explicitly calls out the trailing slash requirement, so
this is a safe assumption to make.
This bug generally doesn't have any user-facing impact, since it requires:
1. using a non-empty prefix without a trailing slash in an iteration like
'for_each_fullref_in',
2. the callback to said iteration not reapplying the original filter (as
for-each-ref does) to ensure unmatched refs are skipped, and
3. the repository having one or more refs that match part of, but not all
of, the prefix.
However, there are some niche scenarios that meet those criteria
(specifically, 'rev-parse --bisect' and '(log|show|shortlog) --bisect'). Add
tests covering those cases to demonstrate the fix in this patch.
Signed-off-by: Victoria Dye <vdye@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-10-09 21:58:53 +00:00
|
|
|
if (entry_prefix_state == PREFIX_EXCLUDES_DIR ||
|
|
|
|
(entry_prefix_state == PREFIX_WITHIN_DIR && !(entry->flag & REF_DIR)))
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
continue;
|
|
|
|
} else {
|
|
|
|
entry_prefix_state = level->prefix_state;
|
|
|
|
}
|
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
if (entry->flag & REF_DIR) {
|
|
|
|
/* push down a level */
|
|
|
|
ALLOC_GROW(iter->levels, iter->levels_nr + 1,
|
|
|
|
iter->levels_alloc);
|
|
|
|
|
|
|
|
level = &iter->levels[iter->levels_nr++];
|
|
|
|
level->dir = get_ref_dir(entry);
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
level->prefix_state = entry_prefix_state;
|
2017-04-16 06:41:31 +00:00
|
|
|
level->index = -1;
|
|
|
|
} else {
|
|
|
|
iter->base.refname = entry->name;
|
|
|
|
iter->base.oid = &entry->u.value.oid;
|
|
|
|
iter->base.flags = entry->flag;
|
|
|
|
return ITER_OK;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cache_ref_iterator_peel(struct ref_iterator *ref_iterator,
|
|
|
|
struct object_id *peeled)
|
|
|
|
{
|
2021-10-08 21:08:16 +00:00
|
|
|
struct cache_ref_iterator *iter =
|
|
|
|
(struct cache_ref_iterator *)ref_iterator;
|
|
|
|
|
|
|
|
if (iter->repo != the_repository)
|
|
|
|
BUG("peeling for non-the_repository is not supported");
|
2021-05-19 15:31:28 +00:00
|
|
|
return peel_object(ref_iterator->oid, peeled) ? -1 : 0;
|
2017-04-16 06:41:31 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int cache_ref_iterator_abort(struct ref_iterator *ref_iterator)
|
|
|
|
{
|
|
|
|
struct cache_ref_iterator *iter =
|
|
|
|
(struct cache_ref_iterator *)ref_iterator;
|
|
|
|
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
free((char *)iter->prefix);
|
2017-04-16 06:41:31 +00:00
|
|
|
free(iter->levels);
|
|
|
|
base_ref_iterator_free(ref_iterator);
|
|
|
|
return ITER_DONE;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct ref_iterator_vtable cache_ref_iterator_vtable = {
|
2022-03-17 17:27:16 +00:00
|
|
|
.advance = cache_ref_iterator_advance,
|
|
|
|
.peel = cache_ref_iterator_peel,
|
|
|
|
.abort = cache_ref_iterator_abort
|
2017-04-16 06:41:31 +00:00
|
|
|
};
|
|
|
|
|
2017-04-16 06:41:39 +00:00
|
|
|
struct ref_iterator *cache_ref_iterator_begin(struct ref_cache *cache,
|
|
|
|
const char *prefix,
|
2021-10-08 21:08:16 +00:00
|
|
|
struct repository *repo,
|
2017-04-16 06:41:39 +00:00
|
|
|
int prime_dir)
|
2017-04-16 06:41:31 +00:00
|
|
|
{
|
2017-04-16 06:41:39 +00:00
|
|
|
struct ref_dir *dir;
|
2017-04-16 06:41:31 +00:00
|
|
|
struct cache_ref_iterator *iter;
|
|
|
|
struct ref_iterator *ref_iterator;
|
|
|
|
struct cache_ref_iterator_level *level;
|
|
|
|
|
2017-04-16 06:41:39 +00:00
|
|
|
dir = get_ref_dir(cache->root);
|
|
|
|
if (prefix && *prefix)
|
2021-09-28 13:02:23 +00:00
|
|
|
dir = find_containing_dir(dir, prefix);
|
2017-04-16 06:41:39 +00:00
|
|
|
if (!dir)
|
|
|
|
/* There's nothing to iterate over. */
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
return empty_ref_iterator_begin();
|
2017-04-16 06:41:39 +00:00
|
|
|
|
|
|
|
if (prime_dir)
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
prime_ref_dir(dir, prefix);
|
2017-04-16 06:41:39 +00:00
|
|
|
|
2021-03-13 16:17:22 +00:00
|
|
|
CALLOC_ARRAY(iter, 1);
|
2017-04-16 06:41:31 +00:00
|
|
|
ref_iterator = &iter->base;
|
2017-09-13 17:15:55 +00:00
|
|
|
base_ref_iterator_init(ref_iterator, &cache_ref_iterator_vtable, 1);
|
2017-04-16 06:41:31 +00:00
|
|
|
ALLOC_GROW(iter->levels, 10, iter->levels_alloc);
|
|
|
|
|
|
|
|
iter->levels_nr = 1;
|
|
|
|
level = &iter->levels[0];
|
|
|
|
level->index = -1;
|
|
|
|
level->dir = dir;
|
|
|
|
|
cache_ref_iterator_begin(): avoid priming unneeded directories
When iterating over references, reference priming is used to make sure
that loose references are read into the ref-cache before packed
references, to avoid races. It used to be that the prefix passed to
reference iterators almost always ended in `/`, for example
`refs/heads/`. In that case, the priming code would read all loose
references under `find_containing_dir("refs/heads/")`, which is
"refs/heads/". That's just what we want.
But now that `ref-filter` knows how to pass refname prefixes to
`for_each_fullref_in()`, the prefix might come from user input; for
example,
git for-each-ref refs/heads
Since the argument doesn't include a trailing slash, the reference
iteration code would prime all of the loose references under
`find_containing_dir("refs/heads")`, which is "refs/". Thus we would
unnecessarily read tags, remote-tracking references, etc., when the
user is only interested in branches.
It is a bit awkward to get around this problem. We can't just append a
slash to the argument, because we don't know ab initio whether an
argument like `refs/tags/release` corresponds to a single tag or to a
directory containing tags.
Moreover, until now a `prefix_ref_iterator` was used to make the final
decision about which references fall within the prefix (the
`cache_ref_iterator` only did a rough cut). This is also inefficient,
because the `prefix_ref_iterator` can't know, for example, that while
you are in a subdirectory that is completely within the prefix, you
don't have to do the prefix check.
So:
* Move the responsibility for doing the prefix check directly to
`cache_ref_iterator`. This means that `cache_ref_iterator_begin()`
never has to wrap its return value in a `prefix_ref_iterator`.
* Teach `cache_ref_iterator_begin()` (and `prime_ref_dir()`) to be
stricter about what they iterate over and what directories they
prime.
* Teach `cache_ref_iterator` to keep track of whether the current
`cache_ref_iterator_level` is fully within the prefix. If so, skip
the prefix checks entirely.
The main benefit of these optimizations is for loose references, since
packed references are always read all at once.
Note that after this change, `prefix_ref_iterator` is only ever used
for its trimming feature and not for its "prefix" feature. But I'm not
ripping out the latter yet, because it might be useful for another
patch series that I'm working on.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-22 14:17:55 +00:00
|
|
|
if (prefix && *prefix) {
|
|
|
|
iter->prefix = xstrdup(prefix);
|
|
|
|
level->prefix_state = PREFIX_WITHIN_DIR;
|
|
|
|
} else {
|
|
|
|
level->prefix_state = PREFIX_CONTAINS_DIR;
|
|
|
|
}
|
2017-04-16 06:41:39 +00:00
|
|
|
|
2021-10-08 21:08:16 +00:00
|
|
|
iter->repo = repo;
|
|
|
|
|
2017-04-16 06:41:31 +00:00
|
|
|
return ref_iterator;
|
|
|
|
}
|