git/tree.c

251 строка
6.3 KiB
C
Исходник Обычный вид История

#include "cache.h"
#include "cache-tree.h"
#include "tree.h"
#include "object-store.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "alloc.h"
#include "tree-walk.h"
#include "repository.h"
const char *tree_type = "tree";
static int read_one_entry_opt(struct index_state *istate,
const struct object_id *oid,
const char *base, int baselen,
const char *pathname,
unsigned mode, int stage, int opt)
{
int len;
struct cache_entry *ce;
if (S_ISDIR(mode))
return READ_TREE_RECURSIVE;
len = strlen(pathname);
block alloc: add lifecycle APIs for cache_entry structs It has been observed that the time spent loading an index with a large number of entries is partly dominated by malloc() calls. This change is in preparation for using memory pools to reduce the number of malloc() calls made to allocate cahce entries when loading an index. Add an API to allocate and discard cache entries, abstracting the details of managing the memory backing the cache entries. This commit does actually change how memory is managed - this will be done in a later commit in the series. This change makes the distinction between cache entries that are associated with an index and cache entries that are not associated with an index. A main use of cache entries is with an index, and we can optimize the memory management around this. We still have other cases where a cache entry is not persisted with an index, and so we need to handle the "transient" use case as well. To keep the congnitive overhead of managing the cache entries, there will only be a single discard function. This means there must be enough information kept with the cache entry so that we know how to discard them. A summary of the main functions in the API is: make_cache_entry: create cache entry for use in an index. Uses specified parameters to populate cache_entry fields. make_empty_cache_entry: Create an empty cache entry for use in an index. Returns cache entry with empty fields. make_transient_cache_entry: create cache entry that is not used in an index. Uses specified parameters to populate cache_entry fields. make_empty_transient_cache_entry: create cache entry that is not used in an index. Returns cache entry with empty fields. discard_cache_entry: A single function that knows how to discard a cache entry regardless of how it was allocated. Signed-off-by: Jameson Miller <jamill@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-07-02 22:49:31 +03:00
ce = make_empty_cache_entry(istate, baselen + len);
ce->ce_mode = create_ce_mode(mode);
ce->ce_flags = create_ce_flags(stage);
ce->ce_namelen = baselen + len;
memcpy(ce->name, base, baselen);
memcpy(ce->name + baselen, pathname, len+1);
oidcpy(&ce->oid, oid);
return add_index_entry(istate, ce, opt);
}
static int read_one_entry(const struct object_id *oid, struct strbuf *base,
const char *pathname, unsigned mode, int stage,
void *context)
{
struct index_state *istate = context;
return read_one_entry_opt(istate, oid, base->buf, base->len, pathname,
mode, stage,
ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK);
}
/*
* This is used when the caller knows there is no existing entries at
* the stage that will conflict with the entry being added.
*/
static int read_one_entry_quick(const struct object_id *oid, struct strbuf *base,
const char *pathname, unsigned mode, int stage,
void *context)
{
struct index_state *istate = context;
return read_one_entry_opt(istate, oid, base->buf, base->len, pathname,
mode, stage,
ADD_CACHE_JUST_APPEND);
}
static int read_tree_1(struct repository *r,
struct tree *tree, struct strbuf *base,
int stage, const struct pathspec *pathspec,
read_tree_fn_t fn, void *context)
{
struct tree_desc desc;
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-30 20:45:45 +04:00
struct name_entry entry;
struct object_id oid;
int len, oldlen = base->len;
enum interesting retval = entry_not_interesting;
if (parse_tree(tree))
return -1;
init_tree_desc(&desc, tree->buffer, tree->size);
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-30 20:45:45 +04:00
while (tree_entry(&desc, &entry)) {
if (retval != all_entries_interesting) {
retval = tree_entry_interesting(r->index, &entry,
base, 0, pathspec);
if (retval == all_entries_not_interesting)
break;
if (retval == entry_not_interesting)
continue;
}
switch (fn(&entry.oid, base,
entry.path, entry.mode, stage, context)) {
case 0:
continue;
case READ_TREE_RECURSIVE:
break;
default:
return -1;
}
if (S_ISDIR(entry.mode))
oidcpy(&oid, &entry.oid);
else if (S_ISGITLINK(entry.mode)) {
struct commit *commit;
commit = lookup_commit(r, &entry.oid);
if (!commit)
die("Commit %s in submodule path %s%s not found",
oid_to_hex(&entry.oid),
base->buf, entry.path);
if (parse_commit(commit))
die("Invalid commit %s in submodule path %s%s",
oid_to_hex(&entry.oid),
base->buf, entry.path);
oidcpy(&oid, get_commit_tree_oid(commit));
}
else
continue;
len = tree_entry_len(&entry);
strbuf_add(base, entry.path, len);
strbuf_addch(base, '/');
retval = read_tree_1(r, lookup_tree(r, &oid),
base, stage, pathspec,
fn, context);
strbuf_setlen(base, oldlen);
if (retval)
return -1;
}
return 0;
}
int read_tree_recursive(struct repository *r,
struct tree *tree,
const char *base, int baselen,
int stage, const struct pathspec *pathspec,
read_tree_fn_t fn, void *context)
{
struct strbuf sb = STRBUF_INIT;
int ret;
strbuf_add(&sb, base, baselen);
ret = read_tree_1(r, tree, &sb, stage, pathspec, fn, context);
strbuf_release(&sb);
return ret;
}
static int cmp_cache_name_compare(const void *a_, const void *b_)
{
const struct cache_entry *ce1, *ce2;
ce1 = *((const struct cache_entry **)a_);
ce2 = *((const struct cache_entry **)b_);
return cache_name_stage_compare(ce1->name, ce1->ce_namelen, ce_stage(ce1),
ce2->name, ce2->ce_namelen, ce_stage(ce2));
}
int read_tree(struct repository *r, struct tree *tree, int stage,
struct pathspec *match, struct index_state *istate)
{
read_tree_fn_t fn = NULL;
int i, err;
/*
* Currently the only existing callers of this function all
* call it with stage=1 and after making sure there is nothing
* at that stage; we could always use read_one_entry_quick().
*
* But when we decide to straighten out git-read-tree not to
* use unpack_trees() in some cases, this will probably start
* to matter.
*/
/*
* See if we have cache entry at the stage. If so,
* do it the original slow way, otherwise, append and then
* sort at the end.
*/
for (i = 0; !fn && i < istate->cache_nr; i++) {
const struct cache_entry *ce = istate->cache[i];
if (ce_stage(ce) == stage)
fn = read_one_entry;
}
if (!fn)
fn = read_one_entry_quick;
err = read_tree_recursive(r, tree, "", 0, stage, match, fn, istate);
if (fn == read_one_entry || err)
return err;
/*
* Sort the cache entry -- we need to nuke the cache tree, though.
*/
cache_tree_free(&istate->cache_tree);
QSORT(istate->cache, istate->cache_nr, cmp_cache_name_compare);
return 0;
}
struct tree *lookup_tree(struct repository *r, const struct object_id *oid)
{
struct object *obj = lookup_object(r, oid);
if (!obj)
return create_object(r, oid, alloc_tree_node(r));
return object_as_type(r, obj, OBJ_TREE, 0);
}
int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size)
{
if (item->object.parsed)
return 0;
item->object.parsed = 1;
item->buffer = buffer;
item->size = size;
return 0;
}
int parse_tree_gently(struct tree *item, int quiet_on_missing)
{
enum object_type type;
void *buffer;
unsigned long size;
if (item->object.parsed)
return 0;
buffer = read_object_file(&item->object.oid, &type, &size);
if (!buffer)
return quiet_on_missing ? -1 :
error("Could not read %s",
oid_to_hex(&item->object.oid));
if (type != OBJ_TREE) {
free(buffer);
return error("Object %s not a tree",
oid_to_hex(&item->object.oid));
}
return parse_tree_buffer(item, buffer, size);
}
void free_tree_buffer(struct tree *tree)
{
FREE_AND_NULL(tree->buffer);
tree->size = 0;
tree->object.parsed = 0;
}
struct tree *parse_tree_indirect(const struct object_id *oid)
{
struct repository *r = the_repository;
struct object *obj = parse_object(r, oid);
return (struct tree *)repo_peel_to_type(r, NULL, 0, obj, OBJ_TREE);
}