@matheusbsbs / matheus-bagliano / commits / 39410bf0bf

Speed up log -L... -M

So far log -L only used the implicit diff filtering by pathspec. If the user specifies -M, we cannot do that, and so we simply handed the whole diff queue (which is approximately 'git show --raw') to diffcore_std(). Unfortunately this is very slow. We can optimize a lot if we throw out files that we know cannot possibly be interesting, in the same spirit that the pathspec filtering reduces the number of files. However, in this case, we have to be more careful. Because we want to look out for renames, we need to keep all filepairs where something was deleted. This is a bit hacky and should really be replaced by equivalent support in --follow, and just using that. However, in the meantime it speeds up 'log -M -L' by an order of magnitude. Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Thomas Rast committed Mar 28, 2013 at 17:47 UTC 39410bf0bf81cb3f76fb9bfa8308cd672bc1442c

1 file changed +52 -4

line-log.c

+52 -4

@@ -750,7 +750,50 @@ static void move_diff_queue(struct diff_queue_struct *dst,

750 DIFF_QUEUE_CLEAR(src);

751 }

752

753 -static void queue_diffs(struct diff_options *opt,

753 +static void filter_diffs_for_paths(struct line_log_data *range, int keep_deletions)

754 +{

755 + int i;

756 + struct diff_queue_struct outq;

757 + DIFF_QUEUE_CLEAR(&outq);

758 +

759 + for (i = 0; i < diff_queued_diff.nr; i++) {

760 + struct diff_filepair *p = diff_queued_diff.queue[i];

761 + struct line_log_data *rg = NULL;

762 +

763 + if (!DIFF_FILE_VALID(p->two)) {

764 + if (keep_deletions)

765 + diff_q(&outq, p);

766 + else

767 + diff_free_filepair(p);

768 + continue;

769 + }

770 + for (rg = range; rg; rg = rg->next) {

771 + if (!strcmp(rg->spec->path, p->two->path))

772 + break;

773 + }

774 + if (rg)

775 + diff_q(&outq, p);

776 + else

777 + diff_free_filepair(p);

778 + }

779 + free(diff_queued_diff.queue);

780 + diff_queued_diff = outq;

781 +}

782 +

783 +static inline int diff_might_be_rename(void)

784 +{

785 + int i;

786 + for (i = 0; i < diff_queued_diff.nr; i++)

787 + if (!DIFF_FILE_VALID(diff_queued_diff.queue[i]->one)) {

788 + /* fprintf(stderr, "diff_might_be_rename found creation of: %s\n", */

789 + /* diff_queued_diff.queue[i]->two->path); */

790 + return 1;

791 + }

792 + return 0;

793 +}

794 +

795 +static void queue_diffs(struct line_log_data *range,

796 + struct diff_options *opt,

797 struct diff_queue_struct *queue,

798 struct commit *commit, struct commit *parent)

799 {

@@ -766,7 +809,12 @@ static void queue_diffs(struct diff_options *opt,

809

810 DIFF_QUEUE_CLEAR(&diff_queued_diff);

811 diff_tree(&desc1, &desc2, "", opt);

769 - diffcore_std(opt);

812 + if (opt->detect_rename) {

813 + filter_diffs_for_paths(range, 1);

814 + if (diff_might_be_rename())

815 + diffcore_std(opt);

816 + filter_diffs_for_paths(range, 0);

817 + }

818 move_diff_queue(queue, &diff_queued_diff);

819

820 if (tree1)

@@ -1050,7 +1098,7 @@ static int process_ranges_ordinary_commit(struct rev_info *rev, struct commit *c

1098 if (commit->parents)

1099 parent = commit->parents->item;

1100

1053 - queue_diffs(&rev->diffopt, &queue, commit, parent);

1101 + queue_diffs(range, &rev->diffopt, &queue, commit, parent);

1102 changed = process_all_files(&parent_range, rev, &queue, range);

1103 if (parent)

1104 add_line_range(rev, parent, parent_range);

@@ -1075,7 +1123,7 @@ static int process_ranges_merge_commit(struct rev_info *rev, struct commit *comm

1123 for (i = 0; i < nparents; i++) {

1124 parents[i] = p->item;

1125 p = p->next;

1078 - queue_diffs(&rev->diffopt, &diffqueues[i], commit, parents[i]);

1126 + queue_diffs(range, &rev->diffopt, &diffqueues[i], commit, parents[i]);

1127 }

1128

1129 for (i = 0; i < nparents; i++) {