When we perform a diff to get the set of changed paths for a commit,
we initialize a full "struct rev_info" with setup_revisions(). But the
only part of it we use is the diff_options struct. Besides being overly
complex, this also leaks memory, as we use the fake argv to
setup_revisions() create a pending array which is never cleared.
Let's just use diff_options directly. This reduces the peak heap usage
of "git commit-graph write --changed-paths" on linux.git from ~4GB to
~1.2GB.
Signed-off-by: Jeff King <peff@xxxxxxxx>
---
bloom.c | 16 +++++++---------
1 file changed, 7 insertions(+), 9 deletions(-)
diff --git a/bloom.c b/bloom.c
index d1d3796e11..ea77631cc2 100644
--- a/bloom.c
+++ b/bloom.c
@@ -154,8 +154,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
struct bloom_filter *filter;
struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
int i;
- struct rev_info revs;
- const char *revs_argv[] = {NULL, "HEAD", NULL};
+ struct diff_options diffopt;
filter = bloom_filter_slab_at(&bloom_filters, c);
@@ -170,16 +169,15 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
if (filter->data || !compute_if_null)
return filter;
- init_revisions(&revs, NULL);
- revs.diffopt.flags.recursive = 1;
-
- setup_revisions(2, revs_argv, &revs, NULL);
+ repo_diff_setup(r, &diffopt);
+ diffopt.flags.recursive = 1;
+ diff_setup_done(&diffopt);
if (c->parents)
- diff_tree_oid(&c->parents->item->object.oid, &c->object.oid, "", &revs.diffopt);
+ diff_tree_oid(&c->parents->item->object.oid, &c->object.oid, "", &diffopt);
else
- diff_tree_oid(NULL, &c->object.oid, "", &revs.diffopt);
- diffcore_std(&revs.diffopt);
+ diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
+ diffcore_std(&diffopt);
if (diff_queued_diff.nr <= 512) {
struct hashmap pathmap;
--
2.24.1.1152.gda0b849012
