log: clean unneeded objects during `log --remerge-diff`

The --remerge-diff option will need to create new blobs and trees
representing the "automatic merge" state.  If one is traversing a
long project history, one can easily get hundreds of thousands of
loose objects generated during `log --remerge-diff`.  However, none of
those loose objects are needed after we have completed our diff
operation; they can be summarily deleted.

Add a new helper function to tmp_objdir to discard all the contained
objects, and call it after each merge is handled.

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 28 insertions, 7 deletions

diff --git a/builtin/log.c b/builtin/log.c
index a7d624f4a7..63d480b37b 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -422,13 +422,12 @@ static int cmd_log_walk(struct rev_info *rev)
 	struct commit *commit;
 	int saved_nrl = 0;
 	int saved_dcctc = 0;
-	struct tmp_objdir *remerge_objdir = NULL;
 
 	if (rev->remerge_diff) {
-		remerge_objdir = tmp_objdir_create("remerge-diff");
-		if (!remerge_objdir)
+		rev->remerge_objdir = tmp_objdir_create("remerge-diff");
+		if (!rev->remerge_objdir)
 			die(_("unable to create temporary object directory"));
-		tmp_objdir_replace_primary_odb(remerge_objdir, 1);
+		tmp_objdir_replace_primary_odb(rev->remerge_objdir, 1);
 	}
 
 	if (rev->early_output)
@@ -473,8 +472,10 @@ static int cmd_log_walk(struct rev_info *rev)
 	rev->diffopt.no_free = 0;
 	diff_free(&rev->diffopt);
 
-	if (rev->remerge_diff)
-		tmp_objdir_destroy(remerge_objdir);
+	if (rev->remerge_diff) {
+		tmp_objdir_destroy(rev->remerge_objdir);
+		rev->remerge_objdir = NULL;
+	}
 
 	if (rev->diffopt.output_format & DIFF_FORMAT_CHECKDIFF &&
 	    rev->diffopt.flags.check_failed) {
diff --git a/log-tree.c b/log-tree.c
index 8f762fb373..6b62ae1a6b 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -4,6 +4,7 @@
 #include "diff.h"
 #include "object-store.h"
 #include "repository.h"
+#include "tmp-objdir.h"
 #include "commit.h"
 #include "tag.h"
 #include "graph.h"
@@ -946,7 +947,12 @@ static int do_remerge_diff(struct rev_info *opt,
 	strbuf_release(&parent1_desc);
 	strbuf_release(&parent2_desc);
 	merge_finalize(&o, &res);
-	/* TODO: clean up the temporary object directory */
+
+	/* Clean up the contents of the temporary object directory */
+	if (opt->remerge_objdir)
+		tmp_objdir_discard_objects(opt->remerge_objdir);
+	else
+		BUG("did a remerge diff without remerge_objdir?!?");
 
 	return !opt->loginfo;
 }
diff --git a/revision.h b/revision.h
index 13178e6b8f..44efce3f41 100644
--- a/revision.h
+++ b/revision.h
@@ -318,6 +318,9 @@ struct rev_info {
 
 	/* misc. flags related to '--no-kept-objects' */
 	unsigned keep_pack_cache_flags;
+
+	/* Location where temporary objects for remerge-diff are written. */
+	struct tmp_objdir *remerge_objdir;
 };
 
 int ref_excluded(struct string_list *, const char *path);
diff --git a/tmp-objdir.c b/tmp-objdir.c
index 3d38eeab66..adf6033549 100644
--- a/tmp-objdir.c
+++ b/tmp-objdir.c
@@ -79,6 +79,11 @@ static void remove_tmp_objdir_on_signal(int signo)
 	raise(signo);
 }
 
+void tmp_objdir_discard_objects(struct tmp_objdir *t)
+{
+	remove_dir_recursively(&t->path, REMOVE_DIR_KEEP_TOPLEVEL);
+}
+
 /*
  * These env_* functions are for setting up the child environment; the
  * "replace" variant overrides the value of any existing variable with that
diff --git a/tmp-objdir.h b/tmp-objdir.h
index cda5ec7677..76efc7edee 100644
--- a/tmp-objdir.h
+++ b/tmp-objdir.h
@@ -47,6 +47,12 @@ int tmp_objdir_migrate(struct tmp_objdir *);
 int tmp_objdir_destroy(struct tmp_objdir *);
 
 /*
+ * Remove all objects from the temporary object directory, while leaving it
+ * around so more objects can be added.
+ */
+void tmp_objdir_discard_objects(struct tmp_objdir *);
+
+/*
  * Add the temporary object directory as an alternate object store in the
  * current process.
  */