git-commit-vandalism/commit.c

672 lines
15 KiB
C
Raw Normal View History

#include "cache.h"
#include "tag.h"
#include "commit.h"
#include "pkt-line.h"
#include "utf8.h"
#include "diff.h"
#include "revision.h"
[PATCH] Avoid wasting memory in git-rev-list As pointed out on the list, git-rev-list can use a lot of memory. One low-hanging fruit is to free the commit buffer for commits that we parse. By default, parse_commit() will save away the buffer, since a lot of cases do want it, and re-reading it continually would be unnecessary. However, in many cases the buffer isn't actually necessary and saving it just wastes memory. We could just free the buffer ourselves, but especially in git-rev-list, we actually end up using the helper functions that automatically add parent commits to the commit lists, so we don't actually control the commit parsing directly. Instead, just make this behaviour of "parse_commit()" a global flag. Maybe this is a bit tasteless, but it's very simple, and it makes a noticable difference in memory usage. Before the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.02system 0:00.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+3714minor)pagefaults 0swaps after the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.00system 0:00.27elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2433minor)pagefaults 0swaps note how the minor faults have decreased from 3714 pages to 2433 pages. That's all due to the fewer anonymous pages allocated to hold the comment buffers and their metadata. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-09-15 23:43:17 +02:00
int save_commit_buffer = 1;
const char *commit_type = "commit";
static struct commit *check_commit(struct object *obj,
const unsigned char *sha1,
int quiet)
{
if (obj->type != OBJ_COMMIT) {
if (!quiet)
error("Object %s is a %s, not a commit",
sha1_to_hex(sha1), typename(obj->type));
return NULL;
}
return (struct commit *) obj;
}
struct commit *lookup_commit_reference_gently(const unsigned char *sha1,
int quiet)
{
struct object *obj = deref_tag(parse_object(sha1), NULL, 0);
if (!obj)
return NULL;
return check_commit(obj, sha1, quiet);
}
struct commit *lookup_commit_reference(const unsigned char *sha1)
{
return lookup_commit_reference_gently(sha1, 0);
}
struct commit *lookup_commit(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
if (!obj)
return create_object(sha1, OBJ_COMMIT, alloc_commit_node());
if (!obj->type)
obj->type = OBJ_COMMIT;
return check_commit(obj, sha1, 0);
}
static unsigned long parse_commit_date(const char *buf, const char *tail)
{
unsigned long date;
const char *dateptr;
if (buf + 6 >= tail)
return 0;
if (memcmp(buf, "author", 6))
return 0;
while (buf < tail && *buf++ != '\n')
/* nada */;
if (buf + 9 >= tail)
return 0;
if (memcmp(buf, "committer", 9))
return 0;
while (buf < tail && *buf++ != '>')
/* nada */;
if (buf >= tail)
return 0;
dateptr = buf;
while (buf < tail && *buf++ != '\n')
/* nada */;
if (buf >= tail)
return 0;
/* dateptr < buf && buf[-1] == '\n', so strtoul will stop at buf-1 */
date = strtoul(dateptr, NULL, 10);
if (date == ULONG_MAX)
date = 0;
return date;
}
static struct commit_graft **commit_graft;
static int commit_graft_alloc, commit_graft_nr;
static int commit_graft_pos(const unsigned char *sha1)
{
int lo, hi;
lo = 0;
hi = commit_graft_nr;
while (lo < hi) {
int mi = (lo + hi) / 2;
struct commit_graft *graft = commit_graft[mi];
int cmp = hashcmp(sha1, graft->sha1);
if (!cmp)
return mi;
if (cmp < 0)
hi = mi;
else
lo = mi + 1;
}
return -lo - 1;
}
int register_commit_graft(struct commit_graft *graft, int ignore_dups)
{
int pos = commit_graft_pos(graft->sha1);
if (0 <= pos) {
if (ignore_dups)
free(graft);
else {
free(commit_graft[pos]);
commit_graft[pos] = graft;
}
return 1;
}
pos = -pos - 1;
if (commit_graft_alloc <= ++commit_graft_nr) {
commit_graft_alloc = alloc_nr(commit_graft_alloc);
commit_graft = xrealloc(commit_graft,
sizeof(*commit_graft) *
commit_graft_alloc);
}
if (pos < commit_graft_nr)
memmove(commit_graft + pos + 1,
commit_graft + pos,
(commit_graft_nr - pos - 1) *
sizeof(*commit_graft));
commit_graft[pos] = graft;
return 0;
}
struct commit_graft *read_graft_line(char *buf, int len)
{
/* The format is just "Commit Parent1 Parent2 ...\n" */
int i;
struct commit_graft *graft = NULL;
if (buf[len-1] == '\n')
buf[--len] = 0;
if (buf[0] == '#' || buf[0] == '\0')
return NULL;
if ((len + 1) % 41) {
bad_graft_data:
error("bad graft data: %s", buf);
free(graft);
return NULL;
}
i = (len + 1) / 41 - 1;
graft = xmalloc(sizeof(*graft) + 20 * i);
graft->nr_parent = i;
if (get_sha1_hex(buf, graft->sha1))
goto bad_graft_data;
for (i = 40; i < len; i += 41) {
if (buf[i] != ' ')
goto bad_graft_data;
if (get_sha1_hex(buf + i + 1, graft->parent[i/41]))
goto bad_graft_data;
}
return graft;
}
int read_graft_file(const char *graft_file)
{
FILE *fp = fopen(graft_file, "r");
char buf[1024];
if (!fp)
return -1;
while (fgets(buf, sizeof(buf), fp)) {
/* The format is just "Commit Parent1 Parent2 ...\n" */
int len = strlen(buf);
struct commit_graft *graft = read_graft_line(buf, len);
if (!graft)
continue;
if (register_commit_graft(graft, 1))
error("duplicate graft data: %s", buf);
}
fclose(fp);
return 0;
}
static void prepare_commit_graft(void)
{
static int commit_graft_prepared;
char *graft_file;
if (commit_graft_prepared)
return;
graft_file = get_graft_file();
read_graft_file(graft_file);
/* make sure shallows are read */
is_repository_shallow();
commit_graft_prepared = 1;
}
struct commit_graft *lookup_commit_graft(const unsigned char *sha1)
{
int pos;
prepare_commit_graft();
pos = commit_graft_pos(sha1);
if (pos < 0)
return NULL;
return commit_graft[pos];
}
int write_shallow_commits(int fd, int use_pack_protocol)
{
int i, count = 0;
for (i = 0; i < commit_graft_nr; i++)
if (commit_graft[i]->nr_parent < 0) {
const char *hex =
sha1_to_hex(commit_graft[i]->sha1);
count++;
if (use_pack_protocol)
packet_write(fd, "shallow %s", hex);
else {
if (write_in_full(fd, hex, 40) != 40)
break;
if (write_in_full(fd, "\n", 1) != 1)
break;
}
}
return count;
}
int unregister_shallow(const unsigned char *sha1)
{
int pos = commit_graft_pos(sha1);
if (pos < 0)
return -1;
if (pos + 1 < commit_graft_nr)
memcpy(commit_graft + pos, commit_graft + pos + 1,
sizeof(struct commit_graft *)
* (commit_graft_nr - pos - 1));
commit_graft_nr--;
return 0;
}
int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size)
{
char *tail = buffer;
char *bufptr = buffer;
unsigned char parent[20];
struct commit_list **pptr;
struct commit_graft *graft;
if (item->object.parsed)
return 0;
item->object.parsed = 1;
tail += size;
if (tail <= bufptr + 46 || memcmp(bufptr, "tree ", 5) || bufptr[45] != '\n')
return error("bogus commit object %s", sha1_to_hex(item->object.sha1));
if (get_sha1_hex(bufptr + 5, parent) < 0)
return error("bad tree pointer in commit %s",
sha1_to_hex(item->object.sha1));
item->tree = lookup_tree(parent);
bufptr += 46; /* "tree " + "hex sha1" + "\n" */
pptr = &item->parents;
graft = lookup_commit_graft(item->object.sha1);
while (bufptr + 48 < tail && !memcmp(bufptr, "parent ", 7)) {
struct commit *new_parent;
if (tail <= bufptr + 48 ||
get_sha1_hex(bufptr + 7, parent) ||
bufptr[47] != '\n')
return error("bad parents in commit %s", sha1_to_hex(item->object.sha1));
bufptr += 48;
if (graft)
continue;
new_parent = lookup_commit(parent);
if (new_parent)
pptr = &commit_list_insert(new_parent, pptr)->next;
}
if (graft) {
int i;
struct commit *new_parent;
for (i = 0; i < graft->nr_parent; i++) {
new_parent = lookup_commit(graft->parent[i]);
if (!new_parent)
continue;
pptr = &commit_list_insert(new_parent, pptr)->next;
}
}
item->date = parse_commit_date(bufptr, tail);
return 0;
}
int parse_commit(struct commit *item)
{
enum object_type type;
void *buffer;
unsigned long size;
int ret;
if (!item)
return -1;
if (item->object.parsed)
return 0;
buffer = read_sha1_file(item->object.sha1, &type, &size);
if (!buffer)
return error("Could not read %s",
sha1_to_hex(item->object.sha1));
if (type != OBJ_COMMIT) {
free(buffer);
return error("Object %s not a commit",
sha1_to_hex(item->object.sha1));
}
ret = parse_commit_buffer(item, buffer, size);
[PATCH] Avoid wasting memory in git-rev-list As pointed out on the list, git-rev-list can use a lot of memory. One low-hanging fruit is to free the commit buffer for commits that we parse. By default, parse_commit() will save away the buffer, since a lot of cases do want it, and re-reading it continually would be unnecessary. However, in many cases the buffer isn't actually necessary and saving it just wastes memory. We could just free the buffer ourselves, but especially in git-rev-list, we actually end up using the helper functions that automatically add parent commits to the commit lists, so we don't actually control the commit parsing directly. Instead, just make this behaviour of "parse_commit()" a global flag. Maybe this is a bit tasteless, but it's very simple, and it makes a noticable difference in memory usage. Before the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.02system 0:00.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+3714minor)pagefaults 0swaps after the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.00system 0:00.27elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2433minor)pagefaults 0swaps note how the minor faults have decreased from 3714 pages to 2433 pages. That's all due to the fewer anonymous pages allocated to hold the comment buffers and their metadata. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-09-15 23:43:17 +02:00
if (save_commit_buffer && !ret) {
item->buffer = buffer;
return 0;
}
free(buffer);
return ret;
}
struct commit_list *commit_list_insert(struct commit *item, struct commit_list **list_p)
{
struct commit_list *new_list = xmalloc(sizeof(struct commit_list));
new_list->item = item;
new_list->next = *list_p;
*list_p = new_list;
return new_list;
}
void free_commit_list(struct commit_list *list)
{
while (list) {
struct commit_list *temp = list;
list = temp->next;
free(temp);
}
}
struct commit_list * insert_by_date(struct commit *item, struct commit_list **list)
{
struct commit_list **pp = list;
struct commit_list *p;
while ((p = *pp) != NULL) {
if (p->item->date < item->date) {
break;
}
pp = &p->next;
}
return commit_list_insert(item, pp);
}
void sort_by_date(struct commit_list **list)
{
struct commit_list *ret = NULL;
while (*list) {
insert_by_date((*list)->item, &ret);
*list = (*list)->next;
}
*list = ret;
}
struct commit *pop_most_recent_commit(struct commit_list **list,
unsigned int mark)
{
struct commit *ret = (*list)->item;
struct commit_list *parents = ret->parents;
struct commit_list *old = *list;
*list = (*list)->next;
free(old);
while (parents) {
struct commit *commit = parents->item;
if (!parse_commit(commit) && !(commit->object.flags & mark)) {
commit->object.flags |= mark;
insert_by_date(commit, list);
}
parents = parents->next;
}
return ret;
}
void clear_commit_marks(struct commit *commit, unsigned int mark)
{
while (commit) {
struct commit_list *parents;
if (!(mark & commit->object.flags))
return;
commit->object.flags &= ~mark;
parents = commit->parents;
if (!parents)
return;
while ((parents = parents->next))
clear_commit_marks(parents->item, mark);
commit = commit->parents->item;
}
}
[PATCH] Modify git-rev-list to linearise the commit history in merge order. This patch linearises the GIT commit history graph into merge order which is defined by invariants specified in Documentation/git-rev-list.txt. The linearisation produced by this patch is superior in an objective sense to that produced by the existing git-rev-list implementation in that the linearisation produced is guaranteed to have the minimum number of discontinuities, where a discontinuity is defined as an adjacent pair of commits in the output list which are not related in a direct child-parent relationship. With this patch a graph like this: a4 --- | \ \ | b4 | |/ | | a3 | | | | | a2 | | | | c3 | | | | | c2 | b3 | | | /| | b2 | | | c1 | | / | b1 a1 | | | a0 | | / root Sorts like this: = a4 | c3 | c2 | c1 ^ b4 | b3 | b2 | b1 ^ a3 | a2 | a1 | a0 = root Instead of this: = a4 | c3 ^ b4 | a3 ^ c2 ^ b3 ^ a2 ^ b2 ^ c1 ^ a1 ^ b1 ^ a0 = root A test script, t/t6000-rev-list.sh, includes a test which demonstrates that the linearisation produced by --merge-order has less discontinuities than the linearisation produced by git-rev-list without the --merge-order flag specified. To see this, do the following: cd t ./t6000-rev-list.sh cd trash cat actual-default-order cat actual-merge-order The existing behaviour of git-rev-list is preserved, by default. To obtain the modified behaviour, specify --merge-order or --merge-order --show-breaks on the command line. This version of the patch has been tested on the git repository and also on the linux-2.6 repository and has reasonable performance on both - ~50-100% slower than the original algorithm. This version of the patch has incorporated a functional equivalent of the Linus' output limiting algorithm into the merge-order algorithm itself. This operates per the notes associated with Linus' commit 337cb3fb8da45f10fe9a0c3cf571600f55ead2ce. This version has incorporated Linus' feedback regarding proposed changes to rev-list.c. (see: [PATCH] Factor out filtering in rev-list.c) This version has improved the way sort_first_epoch marks commits as uninteresting. For more details about this change, refer to Documentation/git-rev-list.txt and http://blackcubes.dyndns.org/epoch/. Signed-off-by: Jon Seymour <jon.seymour@gmail.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-06 17:39:40 +02:00
struct commit *pop_commit(struct commit_list **stack)
{
struct commit_list *top = *stack;
struct commit *item = top ? top->item : NULL;
if (top) {
*stack = top->next;
free(top);
}
return item;
}
/*
* Performs an in-place topological sort on the list supplied.
*/
void sort_in_topological_order(struct commit_list ** list, int lifo)
{
struct commit_list *next, *orig = *list;
struct commit_list *work, **insert;
struct commit_list **pptr;
if (!orig)
return;
*list = NULL;
/* Mark them and clear the indegree */
for (next = orig; next; next = next->next) {
struct commit *commit = next->item;
commit->indegree = 1;
}
/* update the indegree */
for (next = orig; next; next = next->next) {
struct commit_list * parents = next->item->parents;
while (parents) {
struct commit *parent = parents->item;
if (parent->indegree)
parent->indegree++;
parents = parents->next;
}
}
/*
* find the tips
*
* tips are nodes not reachable from any other node in the list
*
* the tips serve as a starting set for the work queue.
*/
work = NULL;
insert = &work;
for (next = orig; next; next = next->next) {
struct commit *commit = next->item;
if (commit->indegree == 1)
insert = &commit_list_insert(commit, insert)->next;
}
/* process the list in topological order */
if (!lifo)
sort_by_date(&work);
pptr = list;
*list = NULL;
while (work) {
struct commit *commit;
struct commit_list *parents, *work_item;
work_item = work;
work = work_item->next;
work_item->next = NULL;
commit = work_item->item;
for (parents = commit->parents; parents ; parents = parents->next) {
struct commit *parent=parents->item;
if (!parent->indegree)
continue;
/*
* parents are only enqueued for emission
* when all their children have been emitted thereby
* guaranteeing topological order.
*/
if (--parent->indegree == 1) {
if (!lifo)
insert_by_date(parent, &work);
else
commit_list_insert(parent, &work);
}
}
/*
* work_item is a commit all of whose children
* have already been emitted. we can emit it now.
*/
commit->indegree = 0;
*pptr = work_item;
pptr = &work_item->next;
}
}
/* merge-base stuff */
/* bits #0..15 in revision.h */
#define PARENT1 (1u<<16)
#define PARENT2 (1u<<17)
#define STALE (1u<<18)
#define RESULT (1u<<19)
static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT);
static struct commit *interesting(struct commit_list *list)
{
while (list) {
struct commit *commit = list->item;
list = list->next;
if (commit->object.flags & STALE)
continue;
return commit;
}
return NULL;
}
static struct commit_list *merge_bases(struct commit *one, struct commit *two)
{
struct commit_list *list = NULL;
struct commit_list *result = NULL;
if (one == two)
/* We do not mark this even with RESULT so we do not
* have to clean it up.
*/
return commit_list_insert(one, &result);
if (parse_commit(one))
return NULL;
if (parse_commit(two))
return NULL;
one->object.flags |= PARENT1;
two->object.flags |= PARENT2;
insert_by_date(one, &list);
insert_by_date(two, &list);
while (interesting(list)) {
struct commit *commit;
struct commit_list *parents;
struct commit_list *n;
int flags;
commit = list->item;
n = list->next;
free(list);
list = n;
flags = commit->object.flags & (PARENT1 | PARENT2 | STALE);
if (flags == (PARENT1 | PARENT2)) {
if (!(commit->object.flags & RESULT)) {
commit->object.flags |= RESULT;
insert_by_date(commit, &result);
}
/* Mark parents of a found merge stale */
flags |= STALE;
}
parents = commit->parents;
while (parents) {
struct commit *p = parents->item;
parents = parents->next;
if ((p->object.flags & flags) == flags)
continue;
if (parse_commit(p))
return NULL;
p->object.flags |= flags;
insert_by_date(p, &list);
}
}
/* Clean up the result to remove stale ones */
free_commit_list(list);
list = result; result = NULL;
while (list) {
struct commit_list *n = list->next;
if (!(list->item->object.flags & STALE))
insert_by_date(list->item, &result);
free(list);
list = n;
}
return result;
}
struct commit_list *get_merge_bases(struct commit *one,
struct commit *two, int cleanup)
{
struct commit_list *list;
struct commit **rslt;
struct commit_list *result;
int cnt, i, j;
result = merge_bases(one, two);
if (one == two)
return result;
if (!result || !result->next) {
if (cleanup) {
clear_commit_marks(one, all_flags);
clear_commit_marks(two, all_flags);
}
return result;
}
/* There are more than one */
cnt = 0;
list = result;
while (list) {
list = list->next;
cnt++;
}
rslt = xcalloc(cnt, sizeof(*rslt));
for (list = result, i = 0; list; list = list->next)
rslt[i++] = list->item;
free_commit_list(result);
clear_commit_marks(one, all_flags);
clear_commit_marks(two, all_flags);
for (i = 0; i < cnt - 1; i++) {
for (j = i+1; j < cnt; j++) {
if (!rslt[i] || !rslt[j])
continue;
result = merge_bases(rslt[i], rslt[j]);
clear_commit_marks(rslt[i], all_flags);
clear_commit_marks(rslt[j], all_flags);
for (list = result; list; list = list->next) {
if (rslt[i] == list->item)
rslt[i] = NULL;
if (rslt[j] == list->item)
rslt[j] = NULL;
}
}
}
/* Surviving ones in rslt[] are the independent results */
result = NULL;
for (i = 0; i < cnt; i++) {
if (rslt[i])
insert_by_date(rslt[i], &result);
}
free(rslt);
return result;
}
int in_merge_bases(struct commit *commit, struct commit **reference, int num)
{
struct commit_list *bases, *b;
int ret = 0;
if (num == 1)
bases = get_merge_bases(commit, *reference, 1);
else
die("not yet");
for (b = bases; b; b = b->next) {
if (!hashcmp(commit->object.sha1, b->item->object.sha1)) {
ret = 1;
break;
}
}
free_commit_list(bases);
return ret;
}