You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

375 lines
8.4 KiB

#include "cache.h"
#include "refs.h"
#include "tag.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
19 years ago
#include "diff.h"
#include "revision.h"
/* bits #0-4 in revision.h */
#define COUNTED (1u<<5)
static const char rev_list_usage[] =
"git-rev-list [OPTION] <commit-id>... [ -- paths... ]\n"
" limiting output:\n"
" --max-count=nr\n"
" --max-age=epoch\n"
" --min-age=epoch\n"
" --sparse\n"
" --no-merges\n"
" --remove-empty\n"
" --all\n"
" ordering output:\n"
" --topo-order\n"
" --date-order\n"
" formatting output:\n"
" --parents\n"
" --objects | --objects-edge\n"
" --unpacked\n"
" --header | --pretty\n"
" --abbrev=nr | --no-abbrev\n"
" special purpose:\n"
" --bisect"
;
struct rev_info revs;
static int bisect_list = 0;
static int verbose_header = 0;
static int abbrev = DEFAULT_ABBREV;
static int show_parents = 0;
static int show_timestamp = 0;
static int hdr_termination = 0;
static const char *commit_prefix = "";
static enum cmit_fmt commit_format = CMIT_FMT_RAW;
static void show_commit(struct commit *commit)
{
if (show_timestamp)
printf("%lu ", commit->date);
if (commit_prefix[0])
fputs(commit_prefix, stdout);
fputs(sha1_to_hex(commit->object.sha1), stdout);
if (show_parents) {
struct commit_list *parents = commit->parents;
while (parents) {
struct object *o = &(parents->item->object);
parents = parents->next;
if (o->flags & TMP_MARK)
continue;
printf(" %s", sha1_to_hex(o->sha1));
o->flags |= TMP_MARK;
}
/* TMP_MARK is a general purpose flag that can
* be used locally, but the user should clean
* things up after it is done with them.
*/
for (parents = commit->parents;
parents;
parents = parents->next)
parents->item->object.flags &= ~TMP_MARK;
}
if (commit_format == CMIT_FMT_ONELINE)
putchar(' ');
else
putchar('\n');
if (verbose_header) {
static char pretty_header[16384];
pretty_print_commit(commit_format, commit, ~0, pretty_header, sizeof(pretty_header), abbrev);
printf("%s%c", pretty_header, hdr_termination);
}
fflush(stdout);
[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>
20 years ago
}
static struct object_list **process_blob(struct blob *blob,
struct object_list **p,
struct name_path *path,
const char *name)
{
struct object *obj = &blob->object;
if (!revs.blob_objects)
return p;
if (obj->flags & (UNINTERESTING | SEEN))
return p;
obj->flags |= SEEN;
return add_object(obj, p, path, name);
}
static struct object_list **process_tree(struct tree *tree,
struct object_list **p,
struct name_path *path,
const char *name)
{
struct object *obj = &tree->object;
struct tree_entry_list *entry;
struct name_path me;
if (!revs.tree_objects)
return p;
if (obj->flags & (UNINTERESTING | SEEN))
return p;
if (parse_tree(tree) < 0)
die("bad tree object %s", sha1_to_hex(obj->sha1));
obj->flags |= SEEN;
p = add_object(obj, p, path, name);
me.up = path;
me.elem = name;
me.elem_len = strlen(name);
entry = tree->entries;
tree->entries = NULL;
while (entry) {
struct tree_entry_list *next = entry->next;
if (entry->directory)
p = process_tree(entry->item.tree, p, &me, entry->name);
else
p = process_blob(entry->item.blob, p, &me, entry->name);
free(entry);
entry = next;
}
return p;
}
static void show_commit_list(struct rev_info *revs)
{
struct commit *commit;
struct object_list *objects = NULL, **p = &objects, *pending;
while ((commit = get_revision(revs)) != NULL) {
p = process_tree(commit->tree, p, NULL, "");
show_commit(commit);
}
for (pending = revs->pending_objects; pending; pending = pending->next) {
struct object *obj = pending->item;
const char *name = pending->name;
if (obj->flags & (UNINTERESTING | SEEN))
continue;
if (obj->type == tag_type) {
obj->flags |= SEEN;
p = add_object(obj, p, NULL, name);
continue;
}
if (obj->type == tree_type) {
p = process_tree((struct tree *)obj, p, NULL, name);
continue;
}
if (obj->type == blob_type) {
p = process_blob((struct blob *)obj, p, NULL, name);
continue;
}
die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name);
}
while (objects) {
/* An object with name "foo\n0000000..." can be used to
* confuse downstream git-pack-objects very badly.
*/
const char *ep = strchr(objects->name, '\n');
if (ep) {
printf("%s %.*s\n", sha1_to_hex(objects->item->sha1),
(int) (ep - objects->name),
objects->name);
}
else
printf("%s %s\n", sha1_to_hex(objects->item->sha1), objects->name);
objects = objects->next;
}
}
/*
* This is a truly stupid algorithm, but it's only
* used for bisection, and we just don't care enough.
*
* We care just barely enough to avoid recursing for
* non-merge entries.
*/
static int count_distance(struct commit_list *entry)
{
int nr = 0;
while (entry) {
struct commit *commit = entry->item;
struct commit_list *p;
if (commit->object.flags & (UNINTERESTING | COUNTED))
break;
if (!revs.prune_fn || (commit->object.flags & TREECHANGE))
nr++;
commit->object.flags |= COUNTED;
p = commit->parents;
entry = p;
if (p) {
p = p->next;
while (p) {
nr += count_distance(p);
p = p->next;
}
}
}
return nr;
}
static void clear_distance(struct commit_list *list)
{
while (list) {
struct commit *commit = list->item;
commit->object.flags &= ~COUNTED;
list = list->next;
}
}
static struct commit_list *find_bisection(struct commit_list *list)
{
int nr, closest;
struct commit_list *p, *best;
nr = 0;
p = list;
while (p) {
if (!revs.prune_fn || (p->item->object.flags & TREECHANGE))
nr++;
p = p->next;
}
closest = 0;
best = list;
for (p = list; p; p = p->next) {
int distance;
if (revs.prune_fn && !(p->item->object.flags & TREECHANGE))
continue;
distance = count_distance(p);
clear_distance(list);
if (nr - distance < distance)
distance = nr - distance;
if (distance > closest) {
best = p;
closest = distance;
}
}
if (best)
best->next = NULL;
return best;
}
static void mark_edge_parents_uninteresting(struct commit *commit)
{
struct commit_list *parents;
for (parents = commit->parents; parents; parents = parents->next) {
struct commit *parent = parents->item;
if (!(parent->object.flags & UNINTERESTING))
continue;
mark_tree_uninteresting(parent->tree);
if (revs.edge_hint && !(parent->object.flags & SHOWN)) {
parent->object.flags |= SHOWN;
printf("-%s\n", sha1_to_hex(parent->object.sha1));
}
}
}
static void mark_edges_uninteresting(struct commit_list *list)
{
for ( ; list; list = list->next) {
struct commit *commit = list->item;
if (commit->object.flags & UNINTERESTING) {
mark_tree_uninteresting(commit->tree);
continue;
}
mark_edge_parents_uninteresting(commit);
}
}
19 years ago
int main(int argc, const char **argv)
{
struct commit_list *list;
int i;
argc = setup_revisions(argc, argv, &revs, NULL);
for (i = 1 ; i < argc; i++) {
19 years ago
const char *arg = argv[i];
/* accept -<digit>, like traditilnal "head" */
if ((*arg == '-') && isdigit(arg[1])) {
revs.max_count = atoi(arg + 1);
continue;
}
if (!strcmp(arg, "-n")) {
if (++i >= argc)
die("-n requires an argument");
revs.max_count = atoi(argv[i]);
continue;
}
if (!strncmp(arg,"-n",2)) {
revs.max_count = atoi(arg + 2);
continue;
}
if (!strcmp(arg, "--header")) {
verbose_header = 1;
continue;
}
if (!strcmp(arg, "--no-abbrev")) {
abbrev = 0;
continue;
}
if (!strncmp(arg, "--abbrev=", 9)) {
abbrev = strtoul(arg + 9, NULL, 10);
if (abbrev && abbrev < MINIMUM_ABBREV)
abbrev = MINIMUM_ABBREV;
else if (40 < abbrev)
abbrev = 40;
continue;
}
if (!strncmp(arg, "--pretty", 8)) {
commit_format = get_commit_format(arg+8);
verbose_header = 1;
hdr_termination = '\n';
if (commit_format == CMIT_FMT_ONELINE)
commit_prefix = "";
else
commit_prefix = "commit ";
continue;
}
if (!strcmp(arg, "--parents")) {
show_parents = 1;
continue;
}
if (!strcmp(arg, "--timestamp")) {
show_timestamp = 1;
continue;
}
if (!strcmp(arg, "--bisect")) {
bisect_list = 1;
continue;
}
usage(rev_list_usage);
}
list = revs.commits;
if (!list &&
(!(revs.tag_objects||revs.tree_objects||revs.blob_objects) && !revs.pending_objects))
usage(rev_list_usage);
prepare_revision_walk(&revs);
if (revs.tree_objects)
mark_edges_uninteresting(revs.commits);
if (bisect_list)
revs.commits = find_bisection(revs.commits);
[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>
19 years ago
save_commit_buffer = verbose_header;
track_object_refs = 0;
[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>
19 years ago
show_commit_list(&revs);
return 0;
}