Re: [PATCH 11/14] commit: integrate packed graph with commit parsing

> Teach Git to inspect a packed graph to supply the contents of a
> struct commit when calling parse_commit_gently(). This implementation
> satisfies all post-conditions on the struct commit, including loading
> parents, the root tree, and the commit date. The only loosely-expected
> condition is that the commit buffer is loaded into the cache. This
> was checked in log-tree.c:show_log(), but the "return;" on failure
> produced unexpected results (i.e. the message line was never terminated).
> The new behavior of loading the buffer when needed prevents the
> unexpected behavior.
>
> If core.graph is false, then do not load the graph and behave as usual.
>
> In test script t5319-graph.sh, add output-matching conditions on read-
> only graph operations.
>
> By loading commits from the graph instead of parsing commit buffers, we
> save a lot of time on long commits walks. Here are some performance
> results for a copy of the Linux repository where 'master' has 704,766
> reachable commits and is behind 'origin/master' by 19,610 commits.
>
> | Command                          | Before | After  | Rel % |
> |----------------------------------|--------|--------|-------|
> | log --oneline --topo-order -1000 |  5.9s  |  0.7s  | -88%  |
> | branch -vv                       |  0.42s |  0.27s | -35%  |
> | rev-list --all                   |  6.4s  |  1.0s  | -84%  |
> | rev-list --all --objects         | 32.6s  | 27.6s  | -15%  |

> @@ -383,19 +384,27 @@ int parse_commit_gently(struct commit *item, int quiet_on_missing)
>
>         if (!item)
>                 return -1;
> +
> +       // If we already parsed, but got it from the graph, then keep going!

>         if (item->object.parsed)
>                 return 0;
> +
> +       if (check_packed && parse_packed_commit(item))
> +               return 0;
> +
>         buffer = read_sha1_file(item->object.oid.hash, &type, &size);
>         if (!buffer)
>                 return quiet_on_missing ? -1 :
>                         error("Could not read %s",
> -                            oid_to_hex(&item->object.oid));
> +                       oid_to_hex(&item->object.oid));
>         if (type != OBJ_COMMIT) {
>                 free(buffer);
>                 return error("Object %s not a commit",
> -                            oid_to_hex(&item->object.oid));
> +                       oid_to_hex(&item->object.oid));
>         }
> +
>         ret = parse_commit_buffer(item, buffer, size);
> +

> @@ -34,6 +34,8 @@
>  #define GRAPH_CHUNKLOOKUP_SIZE (5 * 12)
>  #define GRAPH_MIN_SIZE (GRAPH_CHUNKLOOKUP_SIZE + GRAPH_FANOUT_SIZE + \
>                         GRAPH_OID_LEN + sizeof(struct packed_graph_header))
> +/* global storage */
> +struct packed_graph *packed_graph = 0;
>
>  struct object_id *get_graph_head_oid(const char *pack_dir, struct object_id *oid)
>  {
> @@ -209,6 +211,225 @@ struct packed_graph *load_packed_graph_one(const char *graph_file, const char *p
>         return graph;
>  }
>
> +static void prepare_packed_graph_one(const char *obj_dir)
> +{
> +       char *graph_file;
> +       struct object_id oid;
> +       struct strbuf pack_dir = STRBUF_INIT;
> +       strbuf_addstr(&pack_dir, obj_dir);
> +       strbuf_add(&pack_dir, "/pack", 5);
> +
> +       if (!get_graph_head_oid(pack_dir.buf, &oid))
> +               return;
> +
> +       graph_file = get_graph_filename_oid(pack_dir.buf, &oid);
> +
> +       packed_graph = load_packed_graph_one(graph_file, pack_dir.buf);
> +       strbuf_release(&pack_dir);
> +}
> +
> +static int prepare_packed_graph_run_once = 0;