core: log offset pack data accesses happened

In a workload other than "git log" (without pathspec nor any option that
causes us to inspect trees and blobs), the recency pack order is said to
cause the access jump around quite a bit. Add a hook to allow us observe
how bad it is.

"git config core.logpackaccess /var/tmp/pal.txt" will give you the log
in the specified file.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 21 insertions, 0 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 064a330408..baf5da1823 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1839,6 +1839,24 @@ static void *unpack_delta_entry(struct packed_git *p,
 	return result;
 }
 
+static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
+{
+	static FILE *log_file;
+
+	if (!log_file) {
+		log_file = fopen(log_pack_access, "w");
+		if (!log_file) {
+			error("cannot open pack access log '%s' for writing: %s",
+			      log_pack_access, strerror(errno));
+			log_pack_access = NULL;
+			return;
+		}
+	}
+	fprintf(log_file, "%s %"PRIuMAX"\n",
+		p->pack_name, (uintmax_t)obj_offset);
+	fflush(log_file);
+}
+
 int do_check_packed_object_crc;
 
 void *unpack_entry(struct packed_git *p, off_t obj_offset,
@@ -1848,6 +1866,9 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
 	off_t curpos = obj_offset;
 	void *data;
 
+	if (log_pack_access)
+		write_pack_access_log(p, obj_offset);
+
 	if (do_check_packed_object_crc && p->index_version > 1) {
 		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
 		unsigned long len = revidx[1].offset - obj_offset;