2018-04-02 22:34:19 +02:00
|
|
|
#ifndef COMMIT_GRAPH_H
|
|
|
|
#define COMMIT_GRAPH_H
|
|
|
|
|
2018-04-10 14:56:02 +02:00
|
|
|
#include "git-compat-util.h"
|
2018-06-27 15:24:32 +02:00
|
|
|
#include "repository.h"
|
2018-06-27 15:24:44 +02:00
|
|
|
#include "string-list.h"
|
2018-08-15 19:54:05 +02:00
|
|
|
#include "cache.h"
|
2018-04-10 14:56:02 +02:00
|
|
|
|
2018-08-29 14:49:04 +02:00
|
|
|
#define GIT_TEST_COMMIT_GRAPH "GIT_TEST_COMMIT_GRAPH"
|
|
|
|
|
2018-07-12 00:42:39 +02:00
|
|
|
struct commit;
|
|
|
|
|
2018-04-10 14:56:02 +02:00
|
|
|
char *get_commit_graph_filename(const char *obj_dir);
|
|
|
|
|
2018-04-10 14:56:05 +02:00
|
|
|
/*
|
|
|
|
* Given a commit struct, try to fill the commit struct info, including:
|
|
|
|
* 1. tree object
|
|
|
|
* 2. date
|
|
|
|
* 3. parents.
|
|
|
|
*
|
|
|
|
* Returns 1 if and only if the commit was found in the packed graph.
|
|
|
|
*
|
|
|
|
* See parse_commit_buffer() for the fallback after this call.
|
|
|
|
*/
|
2018-07-12 00:42:42 +02:00
|
|
|
int parse_commit_in_graph(struct repository *r, struct commit *item);
|
2018-04-10 14:56:05 +02:00
|
|
|
|
2018-05-01 14:47:13 +02:00
|
|
|
/*
|
|
|
|
* It is possible that we loaded commit contents from the commit buffer,
|
|
|
|
* but we also want to ensure the commit-graph content is correctly
|
|
|
|
* checked and filled. Fill the graph_pos and generation members of
|
|
|
|
* the given commit.
|
|
|
|
*/
|
2018-07-12 00:42:42 +02:00
|
|
|
void load_commit_graph_info(struct repository *r, struct commit *item);
|
2018-05-01 14:47:13 +02:00
|
|
|
|
2018-07-12 00:42:42 +02:00
|
|
|
struct tree *get_commit_tree_in_graph(struct repository *r,
|
|
|
|
const struct commit *c);
|
2018-04-06 21:09:46 +02:00
|
|
|
|
2018-04-10 14:56:02 +02:00
|
|
|
struct commit_graph {
|
|
|
|
int graph_fd;
|
|
|
|
|
|
|
|
const unsigned char *data;
|
|
|
|
size_t data_len;
|
|
|
|
|
|
|
|
unsigned char hash_len;
|
|
|
|
unsigned char num_chunks;
|
|
|
|
uint32_t num_commits;
|
|
|
|
struct object_id oid;
|
|
|
|
|
|
|
|
const uint32_t *chunk_oid_fanout;
|
|
|
|
const unsigned char *chunk_oid_lookup;
|
|
|
|
const unsigned char *chunk_commit_data;
|
|
|
|
const unsigned char *chunk_large_edges;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct commit_graph *load_commit_graph_one(const char *graph_file);
|
|
|
|
|
commit-reach: use can_all_from_reach
The is_descendant_of method previously used in_merge_bases() to check if
the commit can reach any of the commits in the provided list. This had
two performance problems:
1. The performance is quadratic in worst-case.
2. A single in_merge_bases() call requires walking beyond the target
commit in order to find the full set of boundary commits that may be
merge-bases.
The can_all_from_reach method avoids this quadratic behavior and can
limit the search beyond the target commits using generation numbers. It
requires a small prototype adjustment to stop using commit-date as a
cutoff, as that optimization is no longer appropriate here.
Since in_merge_bases() uses paint_down_to_common(), is_descendant_of()
naturally found cutoffs to avoid walking the entire commit graph. Since
we want to always return the correct result, we cannot use the
min_commit_date cutoff in can_all_from_reach. We then rely on generation
numbers to provide the cutoff.
Since not all repos will have a commit-graph file, nor will we always
have generation numbers computed for a commit-graph file, create a new
method, generation_numbers_enabled(), that checks for a commit-graph
file and sees if the first commit in the file has a non-zero generation
number. In the case that we do not have generation numbers, use the old
logic for is_descendant_of().
Performance was meausured on a copy of the Linux repository using the
'test-tool reach is_descendant_of' command using this input:
A:v4.9
X:v4.10
X:v4.11
X:v4.12
X:v4.13
X:v4.14
X:v4.15
X:v4.16
X:v4.17
X.v3.0
Note that this input is tailored to demonstrate the quadratic nature of
the previous method, as it will compute merge-bases for v4.9 versus all
of the later versions before checking against v4.1.
Before: 0.26 s
After: 0.21 s
Since we previously used the is_descendant_of method in the ref_newer
method, we also measured performance there using
'test-tool reach ref_newer' with this input:
A:v4.9
B:v3.19
Before: 0.10 s
After: 0.08 s
By adding a new commit with parent v3.19, we test the non-reachable case
of ref_newer:
Before: 0.09 s
After: 0.08 s
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-07-20 18:33:30 +02:00
|
|
|
/*
|
|
|
|
* Return 1 if and only if the repository has a commit-graph
|
|
|
|
* file and generation numbers are computed in that file.
|
|
|
|
*/
|
|
|
|
int generation_numbers_enabled(struct repository *r);
|
|
|
|
|
2018-06-27 15:24:45 +02:00
|
|
|
void write_commit_graph_reachable(const char *obj_dir, int append);
|
2018-04-10 14:56:06 +02:00
|
|
|
void write_commit_graph(const char *obj_dir,
|
2018-06-27 15:24:44 +02:00
|
|
|
struct string_list *pack_indexes,
|
|
|
|
struct string_list *commit_hex,
|
2018-04-10 14:56:08 +02:00
|
|
|
int append);
|
2018-04-02 22:34:19 +02:00
|
|
|
|
2018-06-27 15:24:32 +02:00
|
|
|
int verify_commit_graph(struct repository *r, struct commit_graph *g);
|
|
|
|
|
2018-07-12 00:42:40 +02:00
|
|
|
void free_commit_graph(struct commit_graph *);
|
|
|
|
|
2018-04-02 22:34:19 +02:00
|
|
|
#endif
|