Re: git annotate runs out of memory

From: Junio C Hamano <gitster@pobox.com>
Date: Dec 11, 2007, 21:54 UTC
Message-ID: <7vprxcdhis.fsf@gitster.siamese.dyndns.org>
In-Reply-To: <alpine.LFD.0.9999.0712111300440.25032@woody.linux-foundation.org>

Linus Torvalds <torvalds@linux-foundation.org> writes:

Show 23 quoted lines

>  builtin-blame.c |   10 ++++++++++
>  1 files changed, 10 insertions(+), 0 deletions(-)
>
> diff --git a/builtin-blame.c b/builtin-blame.c
> index c158d31..18f9924 100644
> --- a/builtin-blame.c
> +++ b/builtin-blame.c
> @@ -87,6 +87,14 @@ struct origin {
>  	char path[FLEX_ARRAY];
>  };
>  
>  /*
>   * Given an origin, prepare mmfile_t structure to be used by the
>   * diff machinery
> @@ -558,6 +566,8 @@ static struct patch *get_patch(struct origin *parent, struct origin *origin)
>  	if (!file_p.ptr || !file_o.ptr)
>  		return NULL;
>  	patch = compare_buffer(&file_p, &file_o, 0);
> +	drop_origin_blob(parent);
> +	drop_origin_blob(origin);
>  	num_get_patch++;
>  	return patch;
>  }

While this should be safe (because the user of blob lazily re-fetches), it feels a bit too aggressive, especially when -C or other "retry and try harder to assign blame elsewhere" option is used.

Instead, how about discarding after we are done with each origin, like this?

---
 builtin-blame.c |   17 +++++++++++++++--
 1 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/builtin-blame.c b/builtin-blame.c
index c158d31..eda79d0 100644
--- a/builtin-blame.c
+++ b/builtin-blame.c
@@ -130,6 +130,14 @@ static void origin_decref(struct origin *o)
 	}
 }
 
+static void drop_origin_blob(struct origin *o)
+{
+	if (o->file.ptr) {
+		free(o->file.ptr);
+		o->file.ptr = NULL;
+	}
+}
+
 /*
  * Each group of lines is described by a blame_entry; it can be split
  * as we pass blame to the parents.  They form a linked list in the
@@ -1274,8 +1282,13 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt)
 		}
 
  finish:
-	for (i = 0; i < MAXPARENT; i++)
-		origin_decref(parent_origin[i]);
+	for (i = 0; i < MAXPARENT; i++) {
+		if (parent_origin[i]) {
+			drop_origin_blob(parent_origin[i]);
+			origin_decref(parent_origin[i]);
+		}
+	}
+	drop_origin_blob(origin);
 }
 
 /*