From f2af9f5e02380ba3868df7daa34368945d500206 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:14 -0400 Subject: [PATCH 01/18] csum-file: rename hashclose() to finalize_hashfile() The hashclose() method behaves very differently depending on the flags parameter. In particular, the file descriptor is not always closed. Perform a simple rename of "hashclose()" to "finalize_hashfile()" in preparation for functional changes. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- builtin/index-pack.c | 2 +- builtin/pack-objects.c | 6 +++--- bulk-checkin.c | 4 ++-- csum-file.c | 2 +- csum-file.h | 4 ++-- fast-import.c | 2 +- pack-bitmap-write.c | 2 +- pack-write.c | 4 ++-- 8 files changed, 13 insertions(+), 13 deletions(-) diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 7e3e1a461c4469..ca5a3d02488462 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1269,7 +1269,7 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha nr_objects - nr_objects_initial); stop_progress_msg(&progress, msg.buf); strbuf_release(&msg); - hashclose(f, tail_hash, 0); + finalize_hashfile(f, tail_hash, 0); hashcpy(read_hash, pack_hash); fixup_pack_header_footer(output_fd, pack_hash, curr_pack, nr_objects, diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 5c674b2843ccad..5126623e0348c9 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -837,11 +837,11 @@ static void write_pack_file(void) * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - hashclose(f, oid.hash, CSUM_CLOSE); + finalize_hashfile(f, oid.hash, CSUM_CLOSE); } else if (nr_written == nr_remaining) { - hashclose(f, oid.hash, CSUM_FSYNC); + finalize_hashfile(f, oid.hash, CSUM_FSYNC); } else { - int fd = hashclose(f, oid.hash, 0); + int fd = finalize_hashfile(f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, pack_tmp_name, nr_written, oid.hash, offset); close(fd); diff --git a/bulk-checkin.c b/bulk-checkin.c index 8bcd1c8665d028..e8094f5f61052a 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -35,9 +35,9 @@ static void finish_bulk_checkin(struct bulk_checkin_state *state) unlink(state->pack_tmp_name); goto clear_exit; } else if (state->nr_written == 1) { - hashclose(state->f, oid.hash, CSUM_FSYNC); + finalize_hashfile(state->f, oid.hash, CSUM_FSYNC); } else { - int fd = hashclose(state->f, oid.hash, 0); + int fd = finalize_hashfile(state->f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, state->pack_tmp_name, state->nr_written, oid.hash, state->offset); diff --git a/csum-file.c b/csum-file.c index 5eda7fb6af673a..e6c95a6915cbba 100644 --- a/csum-file.c +++ b/csum-file.c @@ -53,7 +53,7 @@ void hashflush(struct hashfile *f) } } -int hashclose(struct hashfile *f, unsigned char *result, unsigned int flags) +int finalize_hashfile(struct hashfile *f, unsigned char *result, unsigned int flags) { int fd; diff --git a/csum-file.h b/csum-file.h index 992e5c014122d8..9ba87f0a6c98fa 100644 --- a/csum-file.h +++ b/csum-file.h @@ -26,14 +26,14 @@ struct hashfile_checkpoint { extern void hashfile_checkpoint(struct hashfile *, struct hashfile_checkpoint *); extern int hashfile_truncate(struct hashfile *, struct hashfile_checkpoint *); -/* hashclose flags */ +/* finalize_hashfile flags */ #define CSUM_CLOSE 1 #define CSUM_FSYNC 2 extern struct hashfile *hashfd(int fd, const char *name); extern struct hashfile *hashfd_check(const char *name); extern struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp); -extern int hashclose(struct hashfile *, unsigned char *, unsigned int); +extern int finalize_hashfile(struct hashfile *, unsigned char *, unsigned int); extern void hashwrite(struct hashfile *, const void *, unsigned int); extern void hashflush(struct hashfile *f); extern void crc32_begin(struct hashfile *); diff --git a/fast-import.c b/fast-import.c index 0f818cd9328d18..1b58fca9f0ee21 100644 --- a/fast-import.c +++ b/fast-import.c @@ -1016,7 +1016,7 @@ static void end_packfile(void) struct tag *t; close_pack_windows(pack_data); - hashclose(pack_file, cur_pack_oid.hash, 0); + finalize_hashfile(pack_file, cur_pack_oid.hash, 0); fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1, pack_data->pack_name, object_count, cur_pack_oid.hash, pack_size); diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index e01f9928840488..662b44f97d9a94 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -535,7 +535,7 @@ void bitmap_writer_finish(struct pack_idx_entry **index, if (options & BITMAP_OPT_HASH_CACHE) write_hash_cache(f, index, index_nr); - hashclose(f, NULL, CSUM_FSYNC); + finalize_hashfile(f, NULL, CSUM_FSYNC); if (adjust_shared_perm(tmp_file.buf)) die_errno("unable to make temporary bitmap file readable"); diff --git a/pack-write.c b/pack-write.c index d775c7406dd5a8..044f427392a7f6 100644 --- a/pack-write.c +++ b/pack-write.c @@ -170,8 +170,8 @@ const char *write_idx_file(const char *index_name, struct pack_idx_entry **objec } hashwrite(f, sha1, the_hash_algo->rawsz); - hashclose(f, NULL, ((opts->flags & WRITE_IDX_VERIFY) - ? CSUM_CLOSE : CSUM_FSYNC)); + finalize_hashfile(f, NULL, ((opts->flags & WRITE_IDX_VERIFY) + ? CSUM_CLOSE : CSUM_FSYNC)); return index_name; } From cfe83216e404223ce8c5f6ef79c4ba9a27ff872e Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:15 -0400 Subject: [PATCH 02/18] csum-file: refactor finalize_hashfile() method If we want to use a hashfile on the temporary file for a lockfile, then we need finalize_hashfile() to fully write the trailing hash but also keep the file descriptor open. Do this by adding a new CSUM_HASH_IN_STREAM flag along with a functional change that checks this flag before writing the checksum to the stream. This differs from previous behavior since it would be written if either CSUM_CLOSE or CSUM_FSYNC is provided. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- builtin/pack-objects.c | 4 ++-- bulk-checkin.c | 2 +- csum-file.c | 8 ++++---- csum-file.h | 5 +++-- pack-bitmap-write.c | 2 +- pack-write.c | 5 +++-- 6 files changed, 14 insertions(+), 12 deletions(-) diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 5126623e0348c9..c4a5a9572a1828 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -837,9 +837,9 @@ static void write_pack_file(void) * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - finalize_hashfile(f, oid.hash, CSUM_CLOSE); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); } else if (nr_written == nr_remaining) { - finalize_hashfile(f, oid.hash, CSUM_FSYNC); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { int fd = finalize_hashfile(f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, pack_tmp_name, diff --git a/bulk-checkin.c b/bulk-checkin.c index e8094f5f61052a..a3e1b59d0e2c6d 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -35,7 +35,7 @@ static void finish_bulk_checkin(struct bulk_checkin_state *state) unlink(state->pack_tmp_name); goto clear_exit; } else if (state->nr_written == 1) { - finalize_hashfile(state->f, oid.hash, CSUM_FSYNC); + finalize_hashfile(state->f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { int fd = finalize_hashfile(state->f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, state->pack_tmp_name, diff --git a/csum-file.c b/csum-file.c index e6c95a6915cbba..53ce37f7ca4299 100644 --- a/csum-file.c +++ b/csum-file.c @@ -61,11 +61,11 @@ int finalize_hashfile(struct hashfile *f, unsigned char *result, unsigned int fl the_hash_algo->final_fn(f->buffer, &f->ctx); if (result) hashcpy(result, f->buffer); - if (flags & (CSUM_CLOSE | CSUM_FSYNC)) { - /* write checksum and close fd */ + if (flags & CSUM_HASH_IN_STREAM) flush(f, f->buffer, the_hash_algo->rawsz); - if (flags & CSUM_FSYNC) - fsync_or_die(f->fd, f->name); + if (flags & CSUM_FSYNC) + fsync_or_die(f->fd, f->name); + if (flags & CSUM_CLOSE) { if (close(f->fd)) die_errno("%s: sha1 file error on close", f->name); fd = 0; diff --git a/csum-file.h b/csum-file.h index 9ba87f0a6c98fa..c5a2e335e7e063 100644 --- a/csum-file.h +++ b/csum-file.h @@ -27,8 +27,9 @@ extern void hashfile_checkpoint(struct hashfile *, struct hashfile_checkpoint *) extern int hashfile_truncate(struct hashfile *, struct hashfile_checkpoint *); /* finalize_hashfile flags */ -#define CSUM_CLOSE 1 -#define CSUM_FSYNC 2 +#define CSUM_CLOSE 1 +#define CSUM_FSYNC 2 +#define CSUM_HASH_IN_STREAM 4 extern struct hashfile *hashfd(int fd, const char *name); extern struct hashfile *hashfd_check(const char *name); diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 662b44f97d9a94..db4c832428b469 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -535,7 +535,7 @@ void bitmap_writer_finish(struct pack_idx_entry **index, if (options & BITMAP_OPT_HASH_CACHE) write_hash_cache(f, index, index_nr); - finalize_hashfile(f, NULL, CSUM_FSYNC); + finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); if (adjust_shared_perm(tmp_file.buf)) die_errno("unable to make temporary bitmap file readable"); diff --git a/pack-write.c b/pack-write.c index 044f427392a7f6..a9d46bc03f63b2 100644 --- a/pack-write.c +++ b/pack-write.c @@ -170,8 +170,9 @@ const char *write_idx_file(const char *index_name, struct pack_idx_entry **objec } hashwrite(f, sha1, the_hash_algo->rawsz); - finalize_hashfile(f, NULL, ((opts->flags & WRITE_IDX_VERIFY) - ? CSUM_CLOSE : CSUM_FSYNC)); + finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_CLOSE | + ((opts->flags & WRITE_IDX_VERIFY) + ? 0 : CSUM_FSYNC)); return index_name; } From b84f767c8a9bcf69b4cfa7fbe44441201a12541e Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:16 -0400 Subject: [PATCH 03/18] commit-graph: add format document Add document specifying the binary format for commit graphs. This format allows for: * New versions. * New hash functions and hash lengths. * Optional extensions. Basic header information is followed by a binary table of contents into "chunks" that include: * An ordered list of commit object IDs. * A 256-entry fanout into that list of OIDs. * A list of metadata for the commits. * A list of "large edges" to enable octopus merges. The format automatically includes two parent positions for every commit. This favors speed over space, since using only one position per commit would cause an extra level of indirection for every merge commit. (Octopus merges suffer from this indirection, but they are very rare.) Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- .../technical/commit-graph-format.txt | 97 +++++++++++++++++++ 1 file changed, 97 insertions(+) create mode 100644 Documentation/technical/commit-graph-format.txt diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt new file mode 100644 index 00000000000000..ad6af8105cf68e --- /dev/null +++ b/Documentation/technical/commit-graph-format.txt @@ -0,0 +1,97 @@ +Git commit graph format +======================= + +The Git commit graph stores a list of commit OIDs and some associated +metadata, including: + +- The generation number of the commit. Commits with no parents have + generation number 1; commits with parents have generation number + one more than the maximum generation number of its parents. We + reserve zero as special, and can be used to mark a generation + number invalid or as "not computed". + +- The root tree OID. + +- The commit date. + +- The parents of the commit, stored using positional references within + the graph file. + +These positional references are stored as unsigned 32-bit integers +corresponding to the array position withing the list of commit OIDs. We +use the most-significant bit for special purposes, so we can store at most +(1 << 31) - 1 (around 2 billion) commits. + +== Commit graph files have the following format: + +In order to allow extensions that add extra data to the graph, we organize +the body into "chunks" and provide a binary lookup table at the beginning +of the body. The header includes certain values, such as number of chunks +and hash type. + +All 4-byte numbers are in network order. + +HEADER: + + 4-byte signature: + The signature is: {'C', 'G', 'P', 'H'} + + 1-byte version number: + Currently, the only valid version is 1. + + 1-byte Hash Version (1 = SHA-1) + We infer the hash length (H) from this value. + + 1-byte number (C) of "chunks" + + 1-byte (reserved for later use) + Current clients should ignore this value. + +CHUNK LOOKUP: + + (C + 1) * 12 bytes listing the table of contents for the chunks: + First 4 bytes describe the chunk id. Value 0 is a terminating label. + Other 8 bytes provide the byte-offset in current file for chunk to + start. (Chunks are ordered contiguously in the file, so you can infer + the length using the next chunk position if necessary.) Each chunk + ID appears at most once. + + The remaining data in the body is described one chunk at a time, and + these chunks may be given in any order. Chunks are required unless + otherwise specified. + +CHUNK DATA: + + OID Fanout (ID: {'O', 'I', 'D', 'F'}) (256 * 4 bytes) + The ith entry, F[i], stores the number of OIDs with first + byte at most i. Thus F[255] stores the total + number of commits (N). + + OID Lookup (ID: {'O', 'I', 'D', 'L'}) (N * H bytes) + The OIDs for all commits in the graph, sorted in ascending order. + + Commit Data (ID: {'C', 'G', 'E', 'T' }) (N * (H + 16) bytes) + * The first H bytes are for the OID of the root tree. + * The next 8 bytes are for the positions of the first two parents + of the ith commit. Stores value 0xffffffff if no parent in that + position. If there are more than two parents, the second value + has its most-significant bit on and the other bits store an array + position into the Large Edge List chunk. + * The next 8 bytes store the generation number of the commit and + the commit time in seconds since EPOCH. The generation number + uses the higher 30 bits of the first 4 bytes, while the commit + time uses the 32 bits of the second 4 bytes, along with the lowest + 2 bits of the lowest byte, storing the 33rd and 34th bit of the + commit time. + + Large Edge List (ID: {'E', 'D', 'G', 'E'}) [Optional] + This list of 4-byte values store the second through nth parents for + all octopus merges. The second parent value in the commit data stores + an array position within this list along with the most-significant bit + on. Starting at that array position, iterate through this list of commit + positions for the parents until reaching a value with the most-significant + bit on. The other bits correspond to the position of the last parent. + +TRAILER: + + H-byte HASH-checksum of all of the above. From ae30d7b1151348068a24ac241cb4f6ad7f5e661b Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:17 -0400 Subject: [PATCH 04/18] graph: add commit graph design document Add Documentation/technical/commit-graph.txt with details of the planned commit graph feature, including future plans. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/technical/commit-graph.txt | 163 +++++++++++++++++++++++ 1 file changed, 163 insertions(+) create mode 100644 Documentation/technical/commit-graph.txt diff --git a/Documentation/technical/commit-graph.txt b/Documentation/technical/commit-graph.txt new file mode 100644 index 00000000000000..0550c6d0dc3173 --- /dev/null +++ b/Documentation/technical/commit-graph.txt @@ -0,0 +1,163 @@ +Git Commit Graph Design Notes +============================= + +Git walks the commit graph for many reasons, including: + +1. Listing and filtering commit history. +2. Computing merge bases. + +These operations can become slow as the commit count grows. The merge +base calculation shows up in many user-facing commands, such as 'merge-base' +or 'status' and can take minutes to compute depending on history shape. + +There are two main costs here: + +1. Decompressing and parsing commits. +2. Walking the entire graph to satisfy topological order constraints. + +The commit graph file is a supplemental data structure that accelerates +commit graph walks. If a user downgrades or disables the 'core.commitGraph' +config setting, then the existing ODB is sufficient. The file is stored +as "commit-graph" either in the .git/objects/info directory or in the info +directory of an alternate. + +The commit graph file stores the commit graph structure along with some +extra metadata to speed up graph walks. By listing commit OIDs in lexi- +cographic order, we can identify an integer position for each commit and +refer to the parents of a commit using those integer positions. We use +binary search to find initial commits and then use the integer positions +for fast lookups during the walk. + +A consumer may load the following info for a commit from the graph: + +1. The commit OID. +2. The list of parents, along with their integer position. +3. The commit date. +4. The root tree OID. +5. The generation number (see definition below). + +Values 1-4 satisfy the requirements of parse_commit_gently(). + +Define the "generation number" of a commit recursively as follows: + + * A commit with no parents (a root commit) has generation number one. + + * A commit with at least one parent has generation number one more than + the largest generation number among its parents. + +Equivalently, the generation number of a commit A is one more than the +length of a longest path from A to a root commit. The recursive definition +is easier to use for computation and observing the following property: + + If A and B are commits with generation numbers N and M, respectively, + and N <= M, then A cannot reach B. That is, we know without searching + that B is not an ancestor of A because it is further from a root commit + than A. + + Conversely, when checking if A is an ancestor of B, then we only need + to walk commits until all commits on the walk boundary have generation + number at most N. If we walk commits using a priority queue seeded by + generation numbers, then we always expand the boundary commit with highest + generation number and can easily detect the stopping condition. + +This property can be used to significantly reduce the time it takes to +walk commits and determine topological relationships. Without generation +numbers, the general heuristic is the following: + + If A and B are commits with commit time X and Y, respectively, and + X < Y, then A _probably_ cannot reach B. + +This heuristic is currently used whenever the computation is allowed to +violate topological relationships due to clock skew (such as "git log" +with default order), but is not used when the topological order is +required (such as merge base calculations, "git log --graph"). + +In practice, we expect some commits to be created recently and not stored +in the commit graph. We can treat these commits as having "infinite" +generation number and walk until reaching commits with known generation +number. + +Design Details +-------------- + +- The commit graph file is stored in a file named 'commit-graph' in the + .git/objects/info directory. This could be stored in the info directory + of an alternate. + +- The core.commitGraph config setting must be on to consume graph files. + +- The file format includes parameters for the object ID hash function, + so a future change of hash algorithm does not require a change in format. + +Future Work +----------- + +- The commit graph feature currently does not honor commit grafts. This can + be remedied by duplicating or refactoring the current graft logic. + +- The 'commit-graph' subcommand does not have a "verify" mode that is + necessary for integration with fsck. + +- The file format includes room for precomputed generation numbers. These + are not currently computed, so all generation numbers will be marked as + 0 (or "uncomputed"). A later patch will include this calculation. + +- After computing and storing generation numbers, we must make graph + walks aware of generation numbers to gain the performance benefits they + enable. This will mostly be accomplished by swapping a commit-date-ordered + priority queue with one ordered by generation number. The following + operations are important candidates: + + - paint_down_to_common() + - 'log --topo-order' + +- Currently, parse_commit_gently() requires filling in the root tree + object for a commit. This passes through lookup_tree() and consequently + lookup_object(). Also, it calls lookup_commit() when loading the parents. + These method calls check the ODB for object existence, even if the + consumer does not need the content. For example, we do not need the + tree contents when computing merge bases. Now that commit parsing is + removed from the computation time, these lookup operations are the + slowest operations keeping graph walks from being fast. Consider + loading these objects without verifying their existence in the ODB and + only loading them fully when consumers need them. Consider a method + such as "ensure_tree_loaded(commit)" that fully loads a tree before + using commit->tree. + +- The current design uses the 'commit-graph' subcommand to generate the graph. + When this feature stabilizes enough to recommend to most users, we should + add automatic graph writes to common operations that create many commits. + For example, one could compute a graph on 'clone', 'fetch', or 'repack' + commands. + +- A server could provide a commit graph file as part of the network protocol + to avoid extra calculations by clients. This feature is only of benefit if + the user is willing to trust the file, because verifying the file is correct + is as hard as computing it from scratch. + +Related Links +------------- +[0] https://bugs.chromium.org/p/git/issues/detail?id=8 + Chromium work item for: Serialized Commit Graph + +[1] https://public-inbox.org/git/20110713070517.GC18566@sigill.intra.peff.net/ + An abandoned patch that introduced generation numbers. + +[2] https://public-inbox.org/git/20170908033403.q7e6dj7benasrjes@sigill.intra.peff.net/ + Discussion about generation numbers on commits and how they interact + with fsck. + +[3] https://public-inbox.org/git/20170908034739.4op3w4f2ma5s65ku@sigill.intra.peff.net/ + More discussion about generation numbers and not storing them inside + commit objects. A valuable quote: + + "I think we should be moving more in the direction of keeping + repo-local caches for optimizations. Reachability bitmaps have been + a big performance win. I think we should be doing the same with our + properties of commits. Not just generation numbers, but making it + cheap to access the graph structure without zlib-inflating whole + commit objects (i.e., packv4 or something like the "metapacks" I + proposed a few years ago)." + +[4] https://public-inbox.org/git/20180108154822.54829-1-git@jeffhostetler.com/T/#u + A patch to remove the ahead-behind calculation from 'status'. From 4ce58ee38de3ab0955b94946bfc339f387227223 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:18 -0400 Subject: [PATCH 05/18] commit-graph: create git-commit-graph builtin Teach git the 'commit-graph' builtin that will be used for writing and reading packed graph files. The current implementation is mostly empty, except for an '--object-dir' option. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- .gitignore | 1 + Documentation/git-commit-graph.txt | 10 +++++++ Makefile | 1 + builtin.h | 1 + builtin/commit-graph.c | 36 ++++++++++++++++++++++++++ command-list.txt | 1 + contrib/completion/git-completion.bash | 2 ++ git.c | 1 + 8 files changed, 53 insertions(+) create mode 100644 Documentation/git-commit-graph.txt create mode 100644 builtin/commit-graph.c diff --git a/.gitignore b/.gitignore index 833ef3b0b783b8..e82f90184d6e8f 100644 --- a/.gitignore +++ b/.gitignore @@ -34,6 +34,7 @@ /git-clone /git-column /git-commit +/git-commit-graph /git-commit-tree /git-config /git-count-objects diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt new file mode 100644 index 00000000000000..f3b34622a888df --- /dev/null +++ b/Documentation/git-commit-graph.txt @@ -0,0 +1,10 @@ +git-commit-graph(1) +=================== + +NAME +---- +git-commit-graph - Write and verify Git commit graph files + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/Makefile b/Makefile index c56fdc14ca154b..2e4956f0a37bbb 100644 --- a/Makefile +++ b/Makefile @@ -946,6 +946,7 @@ BUILTIN_OBJS += builtin/clone.o BUILTIN_OBJS += builtin/column.o BUILTIN_OBJS += builtin/commit-tree.o BUILTIN_OBJS += builtin/commit.o +BUILTIN_OBJS += builtin/commit-graph.o BUILTIN_OBJS += builtin/config.o BUILTIN_OBJS += builtin/count-objects.o BUILTIN_OBJS += builtin/credential.o diff --git a/builtin.h b/builtin.h index 42378f3aa471eb..079855b6d44d77 100644 --- a/builtin.h +++ b/builtin.h @@ -149,6 +149,7 @@ extern int cmd_clone(int argc, const char **argv, const char *prefix); extern int cmd_clean(int argc, const char **argv, const char *prefix); extern int cmd_column(int argc, const char **argv, const char *prefix); extern int cmd_commit(int argc, const char **argv, const char *prefix); +extern int cmd_commit_graph(int argc, const char **argv, const char *prefix); extern int cmd_commit_tree(int argc, const char **argv, const char *prefix); extern int cmd_config(int argc, const char **argv, const char *prefix); extern int cmd_count_objects(int argc, const char **argv, const char *prefix); diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c new file mode 100644 index 00000000000000..b466ecd781f288 --- /dev/null +++ b/builtin/commit-graph.c @@ -0,0 +1,36 @@ +#include "builtin.h" +#include "config.h" +#include "parse-options.h" + +static char const * const builtin_commit_graph_usage[] = { + N_("git commit-graph [--object-dir ]"), + NULL +}; + +static struct opts_commit_graph { + const char *obj_dir; +} opts; + + +int cmd_commit_graph(int argc, const char **argv, const char *prefix) +{ + static struct option builtin_commit_graph_options[] = { + OPT_STRING(0, "object-dir", &opts.obj_dir, + N_("dir"), + N_("The object directory to store the graph")), + OPT_END(), + }; + + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(builtin_commit_graph_usage, + builtin_commit_graph_options); + + git_config(git_default_config, NULL); + argc = parse_options(argc, argv, prefix, + builtin_commit_graph_options, + builtin_commit_graph_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + usage_with_options(builtin_commit_graph_usage, + builtin_commit_graph_options); +} diff --git a/command-list.txt b/command-list.txt index a1fad28fd82da1..835c5890be93ab 100644 --- a/command-list.txt +++ b/command-list.txt @@ -34,6 +34,7 @@ git-clean mainporcelain git-clone mainporcelain init git-column purehelpers git-commit mainporcelain history +git-commit-graph plumbingmanipulators git-commit-tree plumbingmanipulators git-config ancillarymanipulators git-count-objects ancillaryinterrogators diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index 88813e91244d82..b060b6ff6ebb59 100644 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -841,6 +841,7 @@ __git_list_porcelain_commands () check-ref-format) : plumbing;; checkout-index) : plumbing;; column) : internal helper;; + commit-graph) : plumbing;; commit-tree) : plumbing;; count-objects) : infrequent;; credential) : credentials;; @@ -2419,6 +2420,7 @@ _git_config () core.bigFileThreshold core.checkStat core.commentChar + core.commitGraph core.compression core.createObject core.deltaBaseCacheLimit diff --git a/git.c b/git.c index c870b9719c21b2..c7b5adae7b86cc 100644 --- a/git.c +++ b/git.c @@ -388,6 +388,7 @@ static struct cmd_struct commands[] = { { "clone", cmd_clone }, { "column", cmd_column, RUN_SETUP_GENTLY }, { "commit", cmd_commit, RUN_SETUP | NEED_WORK_TREE }, + { "commit-graph", cmd_commit_graph, RUN_SETUP }, { "commit-tree", cmd_commit_tree, RUN_SETUP }, { "config", cmd_config, RUN_SETUP_GENTLY }, { "count-objects", cmd_count_objects, RUN_SETUP }, From 08fd81c9b6495a395a527985d18aa51c4ae66cdc Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:19 -0400 Subject: [PATCH 06/18] commit-graph: implement write_commit_graph() Teach Git to write a commit graph file by checking all packed objects to see if they are commits, then store the file in the given object directory. Helped-by: Jeff King Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Makefile | 1 + commit-graph.c | 359 +++++++++++++++++++++++++++++++++++++++++++++++++ commit-graph.h | 6 + 3 files changed, 366 insertions(+) create mode 100644 commit-graph.c create mode 100644 commit-graph.h diff --git a/Makefile b/Makefile index 2e4956f0a37bbb..bf91b2dfae1dfb 100644 --- a/Makefile +++ b/Makefile @@ -771,6 +771,7 @@ LIB_OBJS += color.o LIB_OBJS += column.o LIB_OBJS += combine-diff.o LIB_OBJS += commit.o +LIB_OBJS += commit-graph.o LIB_OBJS += compat/obstack.o LIB_OBJS += compat/terminal.o LIB_OBJS += config.o diff --git a/commit-graph.c b/commit-graph.c new file mode 100644 index 00000000000000..f3f7c4f1899635 --- /dev/null +++ b/commit-graph.c @@ -0,0 +1,359 @@ +#include "cache.h" +#include "config.h" +#include "git-compat-util.h" +#include "lockfile.h" +#include "pack.h" +#include "packfile.h" +#include "commit.h" +#include "object.h" +#include "revision.h" +#include "sha1-lookup.h" +#include "commit-graph.h" + +#define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */ +#define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */ +#define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */ +#define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */ +#define GRAPH_CHUNKID_LARGEEDGES 0x45444745 /* "EDGE" */ + +#define GRAPH_DATA_WIDTH 36 + +#define GRAPH_VERSION_1 0x1 +#define GRAPH_VERSION GRAPH_VERSION_1 + +#define GRAPH_OID_VERSION_SHA1 1 +#define GRAPH_OID_LEN_SHA1 GIT_SHA1_RAWSZ +#define GRAPH_OID_VERSION GRAPH_OID_VERSION_SHA1 +#define GRAPH_OID_LEN GRAPH_OID_LEN_SHA1 + +#define GRAPH_OCTOPUS_EDGES_NEEDED 0x80000000 +#define GRAPH_PARENT_MISSING 0x7fffffff +#define GRAPH_EDGE_LAST_MASK 0x7fffffff +#define GRAPH_PARENT_NONE 0x70000000 + +#define GRAPH_LAST_EDGE 0x80000000 + +#define GRAPH_FANOUT_SIZE (4 * 256) +#define GRAPH_CHUNKLOOKUP_WIDTH 12 +#define GRAPH_MIN_SIZE (5 * GRAPH_CHUNKLOOKUP_WIDTH + GRAPH_FANOUT_SIZE + \ + GRAPH_OID_LEN + 8) + + +static char *get_commit_graph_filename(const char *obj_dir) +{ + return xstrfmt("%s/info/commit-graph", obj_dir); +} + +static void write_graph_chunk_fanout(struct hashfile *f, + struct commit **commits, + int nr_commits) +{ + int i, count = 0; + struct commit **list = commits; + + /* + * Write the first-level table (the list is sorted, + * but we use a 256-entry lookup to be able to avoid + * having to do eight extra binary search iterations). + */ + for (i = 0; i < 256; i++) { + while (count < nr_commits) { + if ((*list)->object.oid.hash[0] != i) + break; + count++; + list++; + } + + hashwrite_be32(f, count); + } +} + +static void write_graph_chunk_oids(struct hashfile *f, int hash_len, + struct commit **commits, int nr_commits) +{ + struct commit **list = commits; + int count; + for (count = 0; count < nr_commits; count++, list++) + hashwrite(f, (*list)->object.oid.hash, (int)hash_len); +} + +static const unsigned char *commit_to_sha1(size_t index, void *table) +{ + struct commit **commits = table; + return commits[index]->object.oid.hash; +} + +static void write_graph_chunk_data(struct hashfile *f, int hash_len, + struct commit **commits, int nr_commits) +{ + struct commit **list = commits; + struct commit **last = commits + nr_commits; + uint32_t num_extra_edges = 0; + + while (list < last) { + struct commit_list *parent; + int edge_value; + uint32_t packedDate[2]; + + parse_commit(*list); + hashwrite(f, (*list)->tree->object.oid.hash, hash_len); + + parent = (*list)->parents; + + if (!parent) + edge_value = GRAPH_PARENT_NONE; + else { + edge_value = sha1_pos(parent->item->object.oid.hash, + commits, + nr_commits, + commit_to_sha1); + + if (edge_value < 0) + edge_value = GRAPH_PARENT_MISSING; + } + + hashwrite_be32(f, edge_value); + + if (parent) + parent = parent->next; + + if (!parent) + edge_value = GRAPH_PARENT_NONE; + else if (parent->next) + edge_value = GRAPH_OCTOPUS_EDGES_NEEDED | num_extra_edges; + else { + edge_value = sha1_pos(parent->item->object.oid.hash, + commits, + nr_commits, + commit_to_sha1); + if (edge_value < 0) + edge_value = GRAPH_PARENT_MISSING; + } + + hashwrite_be32(f, edge_value); + + if (edge_value & GRAPH_OCTOPUS_EDGES_NEEDED) { + do { + num_extra_edges++; + parent = parent->next; + } while (parent); + } + + if (sizeof((*list)->date) > 4) + packedDate[0] = htonl(((*list)->date >> 32) & 0x3); + else + packedDate[0] = 0; + + packedDate[1] = htonl((*list)->date); + hashwrite(f, packedDate, 8); + + list++; + } +} + +static void write_graph_chunk_large_edges(struct hashfile *f, + struct commit **commits, + int nr_commits) +{ + struct commit **list = commits; + struct commit **last = commits + nr_commits; + struct commit_list *parent; + + while (list < last) { + int num_parents = 0; + for (parent = (*list)->parents; num_parents < 3 && parent; + parent = parent->next) + num_parents++; + + if (num_parents <= 2) { + list++; + continue; + } + + /* Since num_parents > 2, this initializer is safe. */ + for (parent = (*list)->parents->next; parent; parent = parent->next) { + int edge_value = sha1_pos(parent->item->object.oid.hash, + commits, + nr_commits, + commit_to_sha1); + + if (edge_value < 0) + edge_value = GRAPH_PARENT_MISSING; + else if (!parent->next) + edge_value |= GRAPH_LAST_EDGE; + + hashwrite_be32(f, edge_value); + } + + list++; + } +} + +static int commit_compare(const void *_a, const void *_b) +{ + const struct object_id *a = (const struct object_id *)_a; + const struct object_id *b = (const struct object_id *)_b; + return oidcmp(a, b); +} + +struct packed_commit_list { + struct commit **list; + int nr; + int alloc; +}; + +struct packed_oid_list { + struct object_id *list; + int nr; + int alloc; +}; + +static int add_packed_commits(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *data) +{ + struct packed_oid_list *list = (struct packed_oid_list*)data; + enum object_type type; + off_t offset = nth_packed_object_offset(pack, pos); + struct object_info oi = OBJECT_INFO_INIT; + + oi.typep = &type; + if (packed_object_info(pack, offset, &oi) < 0) + die("unable to get type of object %s", oid_to_hex(oid)); + + if (type != OBJ_COMMIT) + return 0; + + ALLOC_GROW(list->list, list->nr + 1, list->alloc); + oidcpy(&(list->list[list->nr]), oid); + list->nr++; + + return 0; +} + +void write_commit_graph(const char *obj_dir) +{ + struct packed_oid_list oids; + struct packed_commit_list commits; + struct hashfile *f; + uint32_t i, count_distinct = 0; + char *graph_name; + int fd; + struct lock_file lk = LOCK_INIT; + uint32_t chunk_ids[5]; + uint64_t chunk_offsets[5]; + int num_chunks; + int num_extra_edges; + struct commit_list *parent; + + oids.nr = 0; + oids.alloc = approximate_object_count() / 4; + + if (oids.alloc < 1024) + oids.alloc = 1024; + ALLOC_ARRAY(oids.list, oids.alloc); + + for_each_packed_object(add_packed_commits, &oids, 0); + + QSORT(oids.list, oids.nr, commit_compare); + + count_distinct = 1; + for (i = 1; i < oids.nr; i++) { + if (oidcmp(&oids.list[i-1], &oids.list[i])) + count_distinct++; + } + + if (count_distinct >= GRAPH_PARENT_MISSING) + die(_("the commit graph format cannot write %d commits"), count_distinct); + + commits.nr = 0; + commits.alloc = count_distinct; + ALLOC_ARRAY(commits.list, commits.alloc); + + num_extra_edges = 0; + for (i = 0; i < oids.nr; i++) { + int num_parents = 0; + if (i > 0 && !oidcmp(&oids.list[i-1], &oids.list[i])) + continue; + + commits.list[commits.nr] = lookup_commit(&oids.list[i]); + parse_commit(commits.list[commits.nr]); + + for (parent = commits.list[commits.nr]->parents; + parent; parent = parent->next) + num_parents++; + + if (num_parents > 2) + num_extra_edges += num_parents - 1; + + commits.nr++; + } + num_chunks = num_extra_edges ? 4 : 3; + + if (commits.nr >= GRAPH_PARENT_MISSING) + die(_("too many commits to write graph")); + + graph_name = get_commit_graph_filename(obj_dir); + fd = hold_lock_file_for_update(&lk, graph_name, 0); + + if (fd < 0) { + struct strbuf folder = STRBUF_INIT; + strbuf_addstr(&folder, graph_name); + strbuf_setlen(&folder, strrchr(folder.buf, '/') - folder.buf); + + if (mkdir(folder.buf, 0777) < 0) + die_errno(_("cannot mkdir %s"), folder.buf); + strbuf_release(&folder); + + fd = hold_lock_file_for_update(&lk, graph_name, LOCK_DIE_ON_ERROR); + + if (fd < 0) + die_errno("unable to create '%s'", graph_name); + } + + f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf); + + hashwrite_be32(f, GRAPH_SIGNATURE); + + hashwrite_u8(f, GRAPH_VERSION); + hashwrite_u8(f, GRAPH_OID_VERSION); + hashwrite_u8(f, num_chunks); + hashwrite_u8(f, 0); /* unused padding byte */ + + chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT; + chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP; + chunk_ids[2] = GRAPH_CHUNKID_DATA; + if (num_extra_edges) + chunk_ids[3] = GRAPH_CHUNKID_LARGEEDGES; + else + chunk_ids[3] = 0; + chunk_ids[4] = 0; + + chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH; + chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE; + chunk_offsets[2] = chunk_offsets[1] + GRAPH_OID_LEN * commits.nr; + chunk_offsets[3] = chunk_offsets[2] + (GRAPH_OID_LEN + 16) * commits.nr; + chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges; + + for (i = 0; i <= num_chunks; i++) { + uint32_t chunk_write[3]; + + chunk_write[0] = htonl(chunk_ids[i]); + chunk_write[1] = htonl(chunk_offsets[i] >> 32); + chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff); + hashwrite(f, chunk_write, 12); + } + + write_graph_chunk_fanout(f, commits.list, commits.nr); + write_graph_chunk_oids(f, GRAPH_OID_LEN, commits.list, commits.nr); + write_graph_chunk_data(f, GRAPH_OID_LEN, commits.list, commits.nr); + write_graph_chunk_large_edges(f, commits.list, commits.nr); + + finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC); + commit_lock_file(&lk); + + free(oids.list); + oids.alloc = 0; + oids.nr = 0; +} diff --git a/commit-graph.h b/commit-graph.h new file mode 100644 index 00000000000000..16fea993ab6f73 --- /dev/null +++ b/commit-graph.h @@ -0,0 +1,6 @@ +#ifndef COMMIT_GRAPH_H +#define COMMIT_GRAPH_H + +void write_commit_graph(const char *obj_dir); + +#endif From f237c8b6feaa3bad352bd27c14f0d83d0a1c061a Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 2 Apr 2018 16:34:20 -0400 Subject: [PATCH 07/18] commit-graph: implement git-commit-graph write Teach git-commit-graph to write graph files. Create new test script to verify this command succeeds without failure. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/git-commit-graph.txt | 41 ++++++++++ builtin/commit-graph.c | 33 ++++++++ t/t5318-commit-graph.sh | 124 +++++++++++++++++++++++++++++ 3 files changed, 198 insertions(+) create mode 100755 t/t5318-commit-graph.sh diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index f3b34622a888df..47996e8f89b99b 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -5,6 +5,47 @@ NAME ---- git-commit-graph - Write and verify Git commit graph files + +SYNOPSIS +-------- +[verse] +'git commit-graph write' [--object-dir ] + + +DESCRIPTION +----------- + +Manage the serialized commit graph file. + + +OPTIONS +------- +--object-dir:: + Use given directory for the location of packfiles and commit graph + file. This parameter exists to specify the location of an alternate + that only has the objects directory, not a full .git directory. The + commit graph file is expected to be at /info/commit-graph and + the packfiles are expected to be in /pack. + + +COMMANDS +-------- +'write':: + +Write a commit graph file based on the commits found in packfiles. +Includes all commits from the existing commit graph file. + + +EXAMPLES +-------- + +* Write a commit graph file for the packed commits in your local .git folder. ++ +------------------------------------------------ +$ git commit-graph write +------------------------------------------------ + + GIT --- Part of the linkgit:git[1] suite diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index b466ecd781f288..26b63602893897 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -1,9 +1,18 @@ #include "builtin.h" #include "config.h" +#include "dir.h" +#include "lockfile.h" #include "parse-options.h" +#include "commit-graph.h" static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph [--object-dir ]"), + N_("git commit-graph write [--object-dir ]"), + NULL +}; + +static const char * const builtin_commit_graph_write_usage[] = { + N_("git commit-graph write [--object-dir ]"), NULL }; @@ -11,6 +20,25 @@ static struct opts_commit_graph { const char *obj_dir; } opts; +static int graph_write(int argc, const char **argv) +{ + static struct option builtin_commit_graph_write_options[] = { + OPT_STRING(0, "object-dir", &opts.obj_dir, + N_("dir"), + N_("The object directory to store the graph")), + OPT_END(), + }; + + argc = parse_options(argc, argv, NULL, + builtin_commit_graph_write_options, + builtin_commit_graph_write_usage, 0); + + if (!opts.obj_dir) + opts.obj_dir = get_object_directory(); + + write_commit_graph(opts.obj_dir); + return 0; +} int cmd_commit_graph(int argc, const char **argv, const char *prefix) { @@ -31,6 +59,11 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix) builtin_commit_graph_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if (argc > 0) { + if (!strcmp(argv[0], "write")) + return graph_write(argc, argv); + } + usage_with_options(builtin_commit_graph_usage, builtin_commit_graph_options); } diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh new file mode 100755 index 00000000000000..d7b635bd689217 --- /dev/null +++ b/t/t5318-commit-graph.sh @@ -0,0 +1,124 @@ +#!/bin/sh + +test_description='commit graph' +. ./test-lib.sh + +test_expect_success 'setup full repo' ' + mkdir full && + cd "$TRASH_DIRECTORY/full" && + git init && + objdir=".git/objects" +' + +test_expect_success 'write graph with no packs' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write --object-dir . && + test_path_is_file info/commit-graph +' + +test_expect_success 'create commits and repack' ' + cd "$TRASH_DIRECTORY/full" && + for i in $(test_seq 3) + do + test_commit $i && + git branch commits/$i + done && + git repack +' + +test_expect_success 'write graph' ' + cd "$TRASH_DIRECTORY/full" && + graph1=$(git commit-graph write) && + test_path_is_file $objdir/info/commit-graph +' + +test_expect_success 'Add more commits' ' + cd "$TRASH_DIRECTORY/full" && + git reset --hard commits/1 && + for i in $(test_seq 4 5) + do + test_commit $i && + git branch commits/$i + done && + git reset --hard commits/2 && + for i in $(test_seq 6 7) + do + test_commit $i && + git branch commits/$i + done && + git reset --hard commits/2 && + git merge commits/4 && + git branch merge/1 && + git reset --hard commits/4 && + git merge commits/6 && + git branch merge/2 && + git reset --hard commits/3 && + git merge commits/5 commits/7 && + git branch merge/3 && + git repack +' + +# Current graph structure: +# +# __M3___ +# / | \ +# 3 M1 5 M2 7 +# |/ \|/ \| +# 2 4 6 +# |___/____/ +# 1 + + +test_expect_success 'write graph with merges' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write && + test_path_is_file $objdir/info/commit-graph +' + +test_expect_success 'Add one more commit' ' + cd "$TRASH_DIRECTORY/full" && + test_commit 8 && + git branch commits/8 && + ls $objdir/pack | grep idx >existing-idx && + git repack && + ls $objdir/pack| grep idx | grep -v --file=existing-idx >new-idx +' + +# Current graph structure: +# +# 8 +# | +# __M3___ +# / | \ +# 3 M1 5 M2 7 +# |/ \|/ \| +# 2 4 6 +# |___/____/ +# 1 + +test_expect_success 'write graph with new commit' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write && + test_path_is_file $objdir/info/commit-graph +' + +test_expect_success 'write graph with nothing new' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write && + test_path_is_file $objdir/info/commit-graph +' + +test_expect_success 'setup bare repo' ' + cd "$TRASH_DIRECTORY" && + git clone --bare --no-local full bare && + cd bare && + baredir="./objects" +' + +test_expect_success 'write graph in bare repo' ' + cd "$TRASH_DIRECTORY/bare" && + git commit-graph write && + test_path_is_file $baredir/info/commit-graph +' + +test_done From 2a2e32bdc5a80221981939e77643cec3462b4793 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:02 -0400 Subject: [PATCH 08/18] commit-graph: implement git commit-graph read Teach git-commit-graph to read commit graph files and summarize their contents. Use the read subcommand to verify the contents of a commit graph file in the tests. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/git-commit-graph.txt | 12 +++ builtin/commit-graph.c | 56 ++++++++++++ commit-graph.c | 137 ++++++++++++++++++++++++++++- commit-graph.h | 23 +++++ t/t5318-commit-graph.sh | 32 +++++-- 5 files changed, 254 insertions(+), 6 deletions(-) diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index 47996e8f89b99b..8aad8303f59caf 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -9,6 +9,7 @@ git-commit-graph - Write and verify Git commit graph files SYNOPSIS -------- [verse] +'git commit-graph read' [--object-dir ] 'git commit-graph write' [--object-dir ] @@ -35,6 +36,11 @@ COMMANDS Write a commit graph file based on the commits found in packfiles. Includes all commits from the existing commit graph file. +'read':: + +Read a graph file given by the commit-graph file and output basic +details about the graph file. Used for debugging purposes. + EXAMPLES -------- @@ -45,6 +51,12 @@ EXAMPLES $ git commit-graph write ------------------------------------------------ +* Read basic information from the commit-graph file. ++ +------------------------------------------------ +$ git commit-graph read +------------------------------------------------ + GIT --- diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index 26b63602893897..efd39331d7c54b 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -7,10 +7,16 @@ static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph [--object-dir ]"), + N_("git commit-graph read [--object-dir ]"), N_("git commit-graph write [--object-dir ]"), NULL }; +static const char * const builtin_commit_graph_read_usage[] = { + N_("git commit-graph read [--object-dir ]"), + NULL +}; + static const char * const builtin_commit_graph_write_usage[] = { N_("git commit-graph write [--object-dir ]"), NULL @@ -20,6 +26,54 @@ static struct opts_commit_graph { const char *obj_dir; } opts; +static int graph_read(int argc, const char **argv) +{ + struct commit_graph *graph = NULL; + char *graph_name; + + static struct option builtin_commit_graph_read_options[] = { + OPT_STRING(0, "object-dir", &opts.obj_dir, + N_("dir"), + N_("The object directory to store the graph")), + OPT_END(), + }; + + argc = parse_options(argc, argv, NULL, + builtin_commit_graph_read_options, + builtin_commit_graph_read_usage, 0); + + if (!opts.obj_dir) + opts.obj_dir = get_object_directory(); + + graph_name = get_commit_graph_filename(opts.obj_dir); + graph = load_commit_graph_one(graph_name); + + if (!graph) + die("graph file %s does not exist", graph_name); + FREE_AND_NULL(graph_name); + + printf("header: %08x %d %d %d %d\n", + ntohl(*(uint32_t*)graph->data), + *(unsigned char*)(graph->data + 4), + *(unsigned char*)(graph->data + 5), + *(unsigned char*)(graph->data + 6), + *(unsigned char*)(graph->data + 7)); + printf("num_commits: %u\n", graph->num_commits); + printf("chunks:"); + + if (graph->chunk_oid_fanout) + printf(" oid_fanout"); + if (graph->chunk_oid_lookup) + printf(" oid_lookup"); + if (graph->chunk_commit_data) + printf(" commit_metadata"); + if (graph->chunk_large_edges) + printf(" large_edges"); + printf("\n"); + + return 0; +} + static int graph_write(int argc, const char **argv) { static struct option builtin_commit_graph_write_options[] = { @@ -60,6 +114,8 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix) PARSE_OPT_STOP_AT_NON_OPTION); if (argc > 0) { + if (!strcmp(argv[0], "read")) + return graph_read(argc, argv); if (!strcmp(argv[0], "write")) return graph_write(argc, argv); } diff --git a/commit-graph.c b/commit-graph.c index f3f7c4f1899635..b1bd3a892d8992 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -39,11 +39,146 @@ GRAPH_OID_LEN + 8) -static char *get_commit_graph_filename(const char *obj_dir) +char *get_commit_graph_filename(const char *obj_dir) { return xstrfmt("%s/info/commit-graph", obj_dir); } +static struct commit_graph *alloc_commit_graph(void) +{ + struct commit_graph *g = xcalloc(1, sizeof(*g)); + g->graph_fd = -1; + + return g; +} + +struct commit_graph *load_commit_graph_one(const char *graph_file) +{ + void *graph_map; + const unsigned char *data, *chunk_lookup; + size_t graph_size; + struct stat st; + uint32_t i; + struct commit_graph *graph; + int fd = git_open(graph_file); + uint64_t last_chunk_offset; + uint32_t last_chunk_id; + uint32_t graph_signature; + unsigned char graph_version, hash_version; + + if (fd < 0) + return NULL; + if (fstat(fd, &st)) { + close(fd); + return NULL; + } + graph_size = xsize_t(st.st_size); + + if (graph_size < GRAPH_MIN_SIZE) { + close(fd); + die("graph file %s is too small", graph_file); + } + graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0); + data = (const unsigned char *)graph_map; + + graph_signature = get_be32(data); + if (graph_signature != GRAPH_SIGNATURE) { + error("graph signature %X does not match signature %X", + graph_signature, GRAPH_SIGNATURE); + goto cleanup_fail; + } + + graph_version = *(unsigned char*)(data + 4); + if (graph_version != GRAPH_VERSION) { + error("graph version %X does not match version %X", + graph_version, GRAPH_VERSION); + goto cleanup_fail; + } + + hash_version = *(unsigned char*)(data + 5); + if (hash_version != GRAPH_OID_VERSION) { + error("hash version %X does not match version %X", + hash_version, GRAPH_OID_VERSION); + goto cleanup_fail; + } + + graph = alloc_commit_graph(); + + graph->hash_len = GRAPH_OID_LEN; + graph->num_chunks = *(unsigned char*)(data + 6); + graph->graph_fd = fd; + graph->data = graph_map; + graph->data_len = graph_size; + + last_chunk_id = 0; + last_chunk_offset = 8; + chunk_lookup = data + 8; + for (i = 0; i < graph->num_chunks; i++) { + uint32_t chunk_id = get_be32(chunk_lookup + 0); + uint64_t chunk_offset = get_be64(chunk_lookup + 4); + int chunk_repeated = 0; + + chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH; + + if (chunk_offset > graph_size - GIT_MAX_RAWSZ) { + error("improper chunk offset %08x%08x", (uint32_t)(chunk_offset >> 32), + (uint32_t)chunk_offset); + goto cleanup_fail; + } + + switch (chunk_id) { + case GRAPH_CHUNKID_OIDFANOUT: + if (graph->chunk_oid_fanout) + chunk_repeated = 1; + else + graph->chunk_oid_fanout = (uint32_t*)(data + chunk_offset); + break; + + case GRAPH_CHUNKID_OIDLOOKUP: + if (graph->chunk_oid_lookup) + chunk_repeated = 1; + else + graph->chunk_oid_lookup = data + chunk_offset; + break; + + case GRAPH_CHUNKID_DATA: + if (graph->chunk_commit_data) + chunk_repeated = 1; + else + graph->chunk_commit_data = data + chunk_offset; + break; + + case GRAPH_CHUNKID_LARGEEDGES: + if (graph->chunk_large_edges) + chunk_repeated = 1; + else + graph->chunk_large_edges = data + chunk_offset; + break; + } + + if (chunk_repeated) { + error("chunk id %08x appears multiple times", chunk_id); + goto cleanup_fail; + } + + if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP) + { + graph->num_commits = (chunk_offset - last_chunk_offset) + / graph->hash_len; + } + + last_chunk_id = chunk_id; + last_chunk_offset = chunk_offset; + } + + return graph; + +cleanup_fail: + munmap(graph_map, graph_size); + close(fd); + exit(1); +} + static void write_graph_chunk_fanout(struct hashfile *f, struct commit **commits, int nr_commits) diff --git a/commit-graph.h b/commit-graph.h index 16fea993ab6f73..2528478f06db26 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -1,6 +1,29 @@ #ifndef COMMIT_GRAPH_H #define COMMIT_GRAPH_H +#include "git-compat-util.h" + +char *get_commit_graph_filename(const char *obj_dir); + +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); + void write_commit_graph(const char *obj_dir); #endif diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index d7b635bd689217..2f44f91193324c 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -26,10 +26,28 @@ test_expect_success 'create commits and repack' ' git repack ' +graph_read_expect() { + OPTIONAL="" + NUM_CHUNKS=3 + if test ! -z $2 + then + OPTIONAL=" $2" + NUM_CHUNKS=$((3 + $(echo "$2" | wc -w))) + fi + cat >expect <<- EOF + header: 43475048 1 1 $NUM_CHUNKS 0 + num_commits: $1 + chunks: oid_fanout oid_lookup commit_metadata$OPTIONAL + EOF + git commit-graph read >output && + test_cmp expect output +} + test_expect_success 'write graph' ' cd "$TRASH_DIRECTORY/full" && graph1=$(git commit-graph write) && - test_path_is_file $objdir/info/commit-graph + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "3" ' test_expect_success 'Add more commits' ' @@ -72,7 +90,8 @@ test_expect_success 'Add more commits' ' test_expect_success 'write graph with merges' ' cd "$TRASH_DIRECTORY/full" && git commit-graph write && - test_path_is_file $objdir/info/commit-graph + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "10" "large_edges" ' test_expect_success 'Add one more commit' ' @@ -99,13 +118,15 @@ test_expect_success 'Add one more commit' ' test_expect_success 'write graph with new commit' ' cd "$TRASH_DIRECTORY/full" && git commit-graph write && - test_path_is_file $objdir/info/commit-graph + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "11" "large_edges" ' test_expect_success 'write graph with nothing new' ' cd "$TRASH_DIRECTORY/full" && git commit-graph write && - test_path_is_file $objdir/info/commit-graph + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "11" "large_edges" ' test_expect_success 'setup bare repo' ' @@ -118,7 +139,8 @@ test_expect_success 'setup bare repo' ' test_expect_success 'write graph in bare repo' ' cd "$TRASH_DIRECTORY/bare" && git commit-graph write && - test_path_is_file $baredir/info/commit-graph + test_path_is_file $baredir/info/commit-graph && + graph_read_expect "11" "large_edges" ' test_done From 1b70dfd5946f76e40516f2229afbf249f185bc7a Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:03 -0400 Subject: [PATCH 09/18] commit-graph: add core.commitGraph setting The commit graph feature is controlled by the new core.commitGraph config setting. This defaults to 0, so the feature is opt-in. The intention of core.commitGraph is that a user can always stop checking for or parsing commit graph files if core.commitGraph=0. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/config.txt | 4 ++++ cache.h | 1 + config.c | 5 +++++ environment.c | 1 + 4 files changed, 11 insertions(+) diff --git a/Documentation/config.txt b/Documentation/config.txt index f57e9cf10ca485..11f027194e6d3f 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -898,6 +898,10 @@ core.notesRef:: This setting defaults to "refs/notes/commits", and it can be overridden by the `GIT_NOTES_REF` environment variable. See linkgit:git-notes[1]. +core.commitGraph:: + Enable git commit graph feature. Allows reading from the + commit-graph file. + core.sparseCheckout:: Enable "sparse checkout" feature. See section "Sparse checkout" in linkgit:git-read-tree[1] for more information. diff --git a/cache.h b/cache.h index 21fbcc2414953d..3a18a02ef9a2ce 100644 --- a/cache.h +++ b/cache.h @@ -801,6 +801,7 @@ extern char *git_replace_ref_base; extern int fsync_object_files; extern int core_preload_index; +extern int core_commit_graph; extern int core_apply_sparse_checkout; extern int precomposed_unicode; extern int protect_hfs; diff --git a/config.c b/config.c index b0c20e6cb8ab1f..25ee4a676c61d0 100644 --- a/config.c +++ b/config.c @@ -1226,6 +1226,11 @@ static int git_default_core_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.commitgraph")) { + core_commit_graph = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "core.sparsecheckout")) { core_apply_sparse_checkout = git_config_bool(var, value); return 0; diff --git a/environment.c b/environment.c index de8431e01e7f4a..0e96be30ca08dc 100644 --- a/environment.c +++ b/environment.c @@ -62,6 +62,7 @@ enum push_default_type push_default = PUSH_DEFAULT_UNSPECIFIED; enum object_creation_mode object_creation_mode = OBJECT_CREATION_MODE; char *notes_ref_name; int grafts_replace_parents = 1; +int core_commit_graph; int core_apply_sparse_checkout; int merge_log_config = -1; int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */ From 4f2542b49e1525ebde595a5254743579a28a7382 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:04 -0400 Subject: [PATCH 10/18] commit-graph: close under reachability Teach write_commit_graph() to walk all parents from the commits discovered in packfiles. This prevents gaps given by loose objects or previously-missed packfiles. Also automatically add commits from the existing graph file, if it exists. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- commit-graph.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/commit-graph.c b/commit-graph.c index b1bd3a892d8992..ea29c5c2d86ae6 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -367,6 +367,50 @@ static int add_packed_commits(const struct object_id *oid, return 0; } +static void add_missing_parents(struct packed_oid_list *oids, struct commit *commit) +{ + struct commit_list *parent; + for (parent = commit->parents; parent; parent = parent->next) { + if (!(parent->item->object.flags & UNINTERESTING)) { + ALLOC_GROW(oids->list, oids->nr + 1, oids->alloc); + oidcpy(&oids->list[oids->nr], &(parent->item->object.oid)); + oids->nr++; + parent->item->object.flags |= UNINTERESTING; + } + } +} + +static void close_reachable(struct packed_oid_list *oids) +{ + int i; + struct commit *commit; + + for (i = 0; i < oids->nr; i++) { + commit = lookup_commit(&oids->list[i]); + if (commit) + commit->object.flags |= UNINTERESTING; + } + + /* + * As this loop runs, oids->nr may grow, but not more + * than the number of missing commits in the reachable + * closure. + */ + for (i = 0; i < oids->nr; i++) { + commit = lookup_commit(&oids->list[i]); + + if (commit && !parse_commit(commit)) + add_missing_parents(oids, commit); + } + + for (i = 0; i < oids->nr; i++) { + commit = lookup_commit(&oids->list[i]); + + if (commit) + commit->object.flags &= ~UNINTERESTING; + } +} + void write_commit_graph(const char *obj_dir) { struct packed_oid_list oids; @@ -390,6 +434,7 @@ void write_commit_graph(const char *obj_dir) ALLOC_ARRAY(oids.list, oids.alloc); for_each_packed_object(add_packed_commits, &oids, 0); + close_reachable(&oids); QSORT(oids.list, oids.nr, commit_compare); From 177722b344256b84f1c97b7363d3f19c04928039 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:05 -0400 Subject: [PATCH 11/18] commit: integrate commit graph with commit parsing Teach Git to inspect a commit graph file 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. If core.commitGraph is false, then do not check graph files. In test script t5318-commit-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 commit walks. Here are some performance results for a copy of the Linux repository where 'master' has 678,653 reachable commits and is behind 'origin/master' by 59,929 commits. | Command | Before | After | Rel % | |----------------------------------|--------|--------|-------| | log --oneline --topo-order -1000 | 8.31s | 0.94s | -88% | | branch -vv | 1.02s | 0.14s | -86% | | rev-list --all | 5.89s | 1.07s | -81% | | rev-list --all --objects | 66.15s | 58.45s | -11% | Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- alloc.c | 1 + commit-graph.c | 141 +++++++++++++++++++++++++++++++++++++++- commit-graph.h | 12 ++++ commit.c | 3 + commit.h | 3 + t/t5318-commit-graph.sh | 47 +++++++++++++- 6 files changed, 205 insertions(+), 2 deletions(-) diff --git a/alloc.c b/alloc.c index 12afadfacdd609..cf4f8b61e126c0 100644 --- a/alloc.c +++ b/alloc.c @@ -93,6 +93,7 @@ void *alloc_commit_node(void) struct commit *c = alloc_node(&commit_state, sizeof(struct commit)); c->object.type = OBJ_COMMIT; c->index = alloc_commit_index(); + c->graph_pos = COMMIT_NOT_FROM_GRAPH; return c; } diff --git a/commit-graph.c b/commit-graph.c index ea29c5c2d86ae6..f745186e7f5eba 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -38,7 +38,6 @@ #define GRAPH_MIN_SIZE (5 * GRAPH_CHUNKLOOKUP_WIDTH + GRAPH_FANOUT_SIZE + \ GRAPH_OID_LEN + 8) - char *get_commit_graph_filename(const char *obj_dir) { return xstrfmt("%s/info/commit-graph", obj_dir); @@ -179,6 +178,145 @@ struct commit_graph *load_commit_graph_one(const char *graph_file) exit(1); } +/* global storage */ +static struct commit_graph *commit_graph = NULL; + +static void prepare_commit_graph_one(const char *obj_dir) +{ + char *graph_name; + + if (commit_graph) + return; + + graph_name = get_commit_graph_filename(obj_dir); + commit_graph = load_commit_graph_one(graph_name); + + FREE_AND_NULL(graph_name); +} + +static int prepare_commit_graph_run_once = 0; +static void prepare_commit_graph(void) +{ + struct alternate_object_database *alt; + char *obj_dir; + + if (prepare_commit_graph_run_once) + return; + prepare_commit_graph_run_once = 1; + + obj_dir = get_object_directory(); + prepare_commit_graph_one(obj_dir); + prepare_alt_odb(); + for (alt = alt_odb_list; !commit_graph && alt; alt = alt->next) + prepare_commit_graph_one(alt->path); +} + +static void close_commit_graph(void) +{ + if (!commit_graph) + return; + + if (commit_graph->graph_fd >= 0) { + munmap((void *)commit_graph->data, commit_graph->data_len); + commit_graph->data = NULL; + close(commit_graph->graph_fd); + } + + FREE_AND_NULL(commit_graph); +} + +static int bsearch_graph(struct commit_graph *g, struct object_id *oid, uint32_t *pos) +{ + return bsearch_hash(oid->hash, g->chunk_oid_fanout, + g->chunk_oid_lookup, g->hash_len, pos); +} + +static struct commit_list **insert_parent_or_die(struct commit_graph *g, + uint64_t pos, + struct commit_list **pptr) +{ + struct commit *c; + struct object_id oid; + hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * pos); + c = lookup_commit(&oid); + if (!c) + die("could not find commit %s", oid_to_hex(&oid)); + c->graph_pos = pos; + return &commit_list_insert(c, pptr)->next; +} + +static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t pos) +{ + struct object_id oid; + uint32_t edge_value; + uint32_t *parent_data_ptr; + uint64_t date_low, date_high; + struct commit_list **pptr; + const unsigned char *commit_data = g->chunk_commit_data + (g->hash_len + 16) * pos; + + item->object.parsed = 1; + item->graph_pos = pos; + + hashcpy(oid.hash, commit_data); + item->tree = lookup_tree(&oid); + + date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; + date_low = get_be32(commit_data + g->hash_len + 12); + item->date = (timestamp_t)((date_high << 32) | date_low); + + pptr = &item->parents; + + edge_value = get_be32(commit_data + g->hash_len); + if (edge_value == GRAPH_PARENT_NONE) + return 1; + pptr = insert_parent_or_die(g, edge_value, pptr); + + edge_value = get_be32(commit_data + g->hash_len + 4); + if (edge_value == GRAPH_PARENT_NONE) + return 1; + if (!(edge_value & GRAPH_OCTOPUS_EDGES_NEEDED)) { + pptr = insert_parent_or_die(g, edge_value, pptr); + return 1; + } + + parent_data_ptr = (uint32_t*)(g->chunk_large_edges + + 4 * (uint64_t)(edge_value & GRAPH_EDGE_LAST_MASK)); + do { + edge_value = get_be32(parent_data_ptr); + pptr = insert_parent_or_die(g, + edge_value & GRAPH_EDGE_LAST_MASK, + pptr); + parent_data_ptr++; + } while (!(edge_value & GRAPH_LAST_EDGE)); + + return 1; +} + +int parse_commit_in_graph(struct commit *item) +{ + if (!core_commit_graph) + return 0; + if (item->object.parsed) + return 1; + + prepare_commit_graph(); + if (commit_graph) { + uint32_t pos; + int found; + if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) { + pos = item->graph_pos; + found = 1; + } else { + found = bsearch_graph(commit_graph, &(item->object.oid), &pos); + } + + if (found) + return fill_commit_in_graph(item, commit_graph, pos); + } + + return 0; +} + static void write_graph_chunk_fanout(struct hashfile *f, struct commit **commits, int nr_commits) @@ -530,6 +668,7 @@ void write_commit_graph(const char *obj_dir) write_graph_chunk_data(f, GRAPH_OID_LEN, commits.list, commits.nr); write_graph_chunk_large_edges(f, commits.list, commits.nr); + close_commit_graph(); finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC); commit_lock_file(&lk); diff --git a/commit-graph.h b/commit-graph.h index 2528478f06db26..73b28beed15b95 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -5,6 +5,18 @@ char *get_commit_graph_filename(const char *obj_dir); +/* + * 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. + */ +int parse_commit_in_graph(struct commit *item); + struct commit_graph { int graph_fd; diff --git a/commit.c b/commit.c index e8a49b9c84bf24..eb61729d105812 100644 --- a/commit.c +++ b/commit.c @@ -1,6 +1,7 @@ #include "cache.h" #include "tag.h" #include "commit.h" +#include "commit-graph.h" #include "pkt-line.h" #include "utf8.h" #include "diff.h" @@ -383,6 +384,8 @@ int parse_commit_gently(struct commit *item, int quiet_on_missing) return -1; if (item->object.parsed) return 0; + if (parse_commit_in_graph(item)) + return 0; buffer = read_sha1_file(item->object.oid.hash, &type, &size); if (!buffer) return quiet_on_missing ? -1 : diff --git a/commit.h b/commit.h index 0fb8271665c6c9..e57ae4b58380cc 100644 --- a/commit.h +++ b/commit.h @@ -9,6 +9,8 @@ #include "string-list.h" #include "pretty.h" +#define COMMIT_NOT_FROM_GRAPH 0xFFFFFFFF + struct commit_list { struct commit *item; struct commit_list *next; @@ -21,6 +23,7 @@ struct commit { timestamp_t date; struct commit_list *parents; struct tree *tree; + uint32_t graph_pos; }; extern int save_commit_buffer; diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 2f44f91193324c..51de9cc4552b08 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -7,6 +7,7 @@ test_expect_success 'setup full repo' ' mkdir full && cd "$TRASH_DIRECTORY/full" && git init && + git config core.commitGraph true && objdir=".git/objects" ' @@ -26,6 +27,29 @@ test_expect_success 'create commits and repack' ' git repack ' +graph_git_two_modes() { + git -c core.graph=true $1 >output + git -c core.graph=false $1 >expect + test_cmp output expect +} + +graph_git_behavior() { + MSG=$1 + DIR=$2 + BRANCH=$3 + COMPARE=$4 + test_expect_success "check normal git operations: $MSG" ' + cd "$TRASH_DIRECTORY/$DIR" && + graph_git_two_modes "log --oneline $BRANCH" && + graph_git_two_modes "log --topo-order $BRANCH" && + graph_git_two_modes "log --graph $COMPARE..$BRANCH" && + graph_git_two_modes "branch -vv" && + graph_git_two_modes "merge-base -a $BRANCH $COMPARE" + ' +} + +graph_git_behavior 'no graph' full commits/3 commits/1 + graph_read_expect() { OPTIONAL="" NUM_CHUNKS=3 @@ -50,6 +74,8 @@ test_expect_success 'write graph' ' graph_read_expect "3" ' +graph_git_behavior 'graph exists' full commits/3 commits/1 + test_expect_success 'Add more commits' ' cd "$TRASH_DIRECTORY/full" && git reset --hard commits/1 && @@ -86,7 +112,6 @@ test_expect_success 'Add more commits' ' # |___/____/ # 1 - test_expect_success 'write graph with merges' ' cd "$TRASH_DIRECTORY/full" && git commit-graph write && @@ -94,6 +119,10 @@ test_expect_success 'write graph with merges' ' graph_read_expect "10" "large_edges" ' +graph_git_behavior 'merge 1 vs 2' full merge/1 merge/2 +graph_git_behavior 'merge 1 vs 3' full merge/1 merge/3 +graph_git_behavior 'merge 2 vs 3' full merge/2 merge/3 + test_expect_success 'Add one more commit' ' cd "$TRASH_DIRECTORY/full" && test_commit 8 && @@ -115,6 +144,9 @@ test_expect_success 'Add one more commit' ' # |___/____/ # 1 +graph_git_behavior 'mixed mode, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'mixed mode, commit 8 vs merge 2' full commits/8 merge/2 + test_expect_success 'write graph with new commit' ' cd "$TRASH_DIRECTORY/full" && git commit-graph write && @@ -122,6 +154,9 @@ test_expect_success 'write graph with new commit' ' graph_read_expect "11" "large_edges" ' +graph_git_behavior 'full graph, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'full graph, commit 8 vs merge 2' full commits/8 merge/2 + test_expect_success 'write graph with nothing new' ' cd "$TRASH_DIRECTORY/full" && git commit-graph write && @@ -129,13 +164,20 @@ test_expect_success 'write graph with nothing new' ' graph_read_expect "11" "large_edges" ' +graph_git_behavior 'cleared graph, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'cleared graph, commit 8 vs merge 2' full commits/8 merge/2 + test_expect_success 'setup bare repo' ' cd "$TRASH_DIRECTORY" && git clone --bare --no-local full bare && cd bare && + git config core.commitGraph true && baredir="./objects" ' +graph_git_behavior 'bare repo, commit 8 vs merge 1' bare commits/8 merge/1 +graph_git_behavior 'bare repo, commit 8 vs merge 2' bare commits/8 merge/2 + test_expect_success 'write graph in bare repo' ' cd "$TRASH_DIRECTORY/bare" && git commit-graph write && @@ -143,4 +185,7 @@ test_expect_success 'write graph in bare repo' ' graph_read_expect "11" "large_edges" ' +graph_git_behavior 'bare repo with graph, commit 8 vs merge 1' bare commits/8 merge/1 +graph_git_behavior 'bare repo with graph, commit 8 vs merge 2' bare commits/8 merge/2 + test_done From 049d51a2bb9a03d2f2c2cce1ae41e57dbbf42244 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:06 -0400 Subject: [PATCH 12/18] commit-graph: read only from specific pack-indexes Teach git-commit-graph to inspect the objects only in a certain list of pack-indexes within the given pack directory. This allows updating the commit graph iteratively. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/git-commit-graph.txt | 11 +++++++++- builtin/commit-graph.c | 33 +++++++++++++++++++++++++++--- commit-graph.c | 26 +++++++++++++++++++++-- commit-graph.h | 4 +++- packfile.c | 4 ++-- packfile.h | 2 ++ t/t5318-commit-graph.sh | 10 +++++++++ 7 files changed, 81 insertions(+), 9 deletions(-) diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index 8aad8303f59caf..8143cc3f078e46 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -34,7 +34,9 @@ COMMANDS 'write':: Write a commit graph file based on the commits found in packfiles. -Includes all commits from the existing commit graph file. ++ +With the `--stdin-packs` option, generate the new commit graph by +walking objects only in the specified pack-indexes. 'read':: @@ -51,6 +53,13 @@ EXAMPLES $ git commit-graph write ------------------------------------------------ +* Write a graph file, extending the current graph file using commits +* in . ++ +------------------------------------------------ +$ echo | git commit-graph write --stdin-packs +------------------------------------------------ + * Read basic information from the commit-graph file. + ------------------------------------------------ diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index efd39331d7c54b..5c7019900307f0 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -8,7 +8,7 @@ static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph [--object-dir ]"), N_("git commit-graph read [--object-dir ]"), - N_("git commit-graph write [--object-dir ]"), + N_("git commit-graph write [--object-dir ] [--stdin-packs]"), NULL }; @@ -18,12 +18,13 @@ static const char * const builtin_commit_graph_read_usage[] = { }; static const char * const builtin_commit_graph_write_usage[] = { - N_("git commit-graph write [--object-dir ]"), + N_("git commit-graph write [--object-dir ] [--stdin-packs]"), NULL }; static struct opts_commit_graph { const char *obj_dir; + int stdin_packs; } opts; static int graph_read(int argc, const char **argv) @@ -76,10 +77,18 @@ static int graph_read(int argc, const char **argv) static int graph_write(int argc, const char **argv) { + const char **pack_indexes = NULL; + int packs_nr = 0; + const char **lines = NULL; + int lines_nr = 0; + int lines_alloc = 0; + static struct option builtin_commit_graph_write_options[] = { OPT_STRING(0, "object-dir", &opts.obj_dir, N_("dir"), N_("The object directory to store the graph")), + OPT_BOOL(0, "stdin-packs", &opts.stdin_packs, + N_("scan pack-indexes listed by stdin for commits")), OPT_END(), }; @@ -90,7 +99,25 @@ static int graph_write(int argc, const char **argv) if (!opts.obj_dir) opts.obj_dir = get_object_directory(); - write_commit_graph(opts.obj_dir); + if (opts.stdin_packs) { + struct strbuf buf = STRBUF_INIT; + lines_nr = 0; + lines_alloc = 128; + ALLOC_ARRAY(lines, lines_alloc); + + while (strbuf_getline(&buf, stdin) != EOF) { + ALLOC_GROW(lines, lines_nr + 1, lines_alloc); + lines[lines_nr++] = strbuf_detach(&buf, NULL); + } + + pack_indexes = lines; + packs_nr = lines_nr; + } + + write_commit_graph(opts.obj_dir, + pack_indexes, + packs_nr); + return 0; } diff --git a/commit-graph.c b/commit-graph.c index f745186e7f5eba..70472840a3bfb9 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -549,7 +549,9 @@ static void close_reachable(struct packed_oid_list *oids) } } -void write_commit_graph(const char *obj_dir) +void write_commit_graph(const char *obj_dir, + const char **pack_indexes, + int nr_packs) { struct packed_oid_list oids; struct packed_commit_list commits; @@ -571,7 +573,27 @@ void write_commit_graph(const char *obj_dir) oids.alloc = 1024; ALLOC_ARRAY(oids.list, oids.alloc); - for_each_packed_object(add_packed_commits, &oids, 0); + if (pack_indexes) { + struct strbuf packname = STRBUF_INIT; + int dirlen; + strbuf_addf(&packname, "%s/pack/", obj_dir); + dirlen = packname.len; + for (i = 0; i < nr_packs; i++) { + struct packed_git *p; + strbuf_setlen(&packname, dirlen); + strbuf_addstr(&packname, pack_indexes[i]); + p = add_packed_git(packname.buf, packname.len, 1); + if (!p) + die("error adding pack %s", packname.buf); + if (open_pack_index(p)) + die("error opening index for %s", packname.buf); + for_each_object_in_pack(p, add_packed_commits, &oids); + close_pack(p); + } + strbuf_release(&packname); + } else + for_each_packed_object(add_packed_commits, &oids, 0); + close_reachable(&oids); QSORT(oids.list, oids.nr, commit_compare); diff --git a/commit-graph.h b/commit-graph.h index 73b28beed15b95..f065f0866f83e2 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -36,6 +36,8 @@ struct commit_graph { struct commit_graph *load_commit_graph_one(const char *graph_file); -void write_commit_graph(const char *obj_dir); +void write_commit_graph(const char *obj_dir, + const char **pack_indexes, + int nr_packs); #endif diff --git a/packfile.c b/packfile.c index 5d07f330c8a4bf..f14179f937e341 100644 --- a/packfile.c +++ b/packfile.c @@ -304,7 +304,7 @@ void close_pack_index(struct packed_git *p) } } -static void close_pack(struct packed_git *p) +void close_pack(struct packed_git *p) { close_pack_windows(p); close_pack_fd(p); @@ -1850,7 +1850,7 @@ int has_pack_index(const unsigned char *sha1) return 1; } -static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) +int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) { uint32_t i; int r = 0; diff --git a/packfile.h b/packfile.h index a7fca598d672b7..b341f2bf5ef68c 100644 --- a/packfile.h +++ b/packfile.h @@ -63,6 +63,7 @@ extern void close_pack_index(struct packed_git *); extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); extern void close_pack_windows(struct packed_git *); +extern void close_pack(struct packed_git *); extern void close_all_packs(void); extern void unuse_pack(struct pack_window **); extern void clear_delta_base_cache(void); @@ -140,6 +141,7 @@ typedef int each_packed_object_fn(const struct object_id *oid, struct packed_git *pack, uint32_t pos, void *data); +extern int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn, void *data); extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags); /* diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 51de9cc4552b08..3bb44d0c09e15c 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -167,6 +167,16 @@ test_expect_success 'write graph with nothing new' ' graph_git_behavior 'cleared graph, commit 8 vs merge 1' full commits/8 merge/1 graph_git_behavior 'cleared graph, commit 8 vs merge 2' full commits/8 merge/2 +test_expect_success 'build graph from latest pack with closure' ' + cd "$TRASH_DIRECTORY/full" && + cat new-idx | git commit-graph write --stdin-packs && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "9" "large_edges" +' + +graph_git_behavior 'graph from pack, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'graph from pack, commit 8 vs merge 2' full commits/8 merge/2 + test_expect_success 'setup bare repo' ' cd "$TRASH_DIRECTORY" && git clone --bare --no-local full bare && From 3d5df01b5e42416a59e857135e932bbdd8cc3ba0 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:07 -0400 Subject: [PATCH 13/18] commit-graph: build graph from starting commits Teach git-commit-graph to read commits from stdin when the --stdin-commits flag is specified. Commits reachable from these commits are added to the graph. This is a much faster way to construct the graph than inspecting all packed objects, but is restricted to known tips. For the Linux repository, 700,000+ commits were added to the graph file starting from 'master' in 7-9 seconds, depending on the number of packfiles in the repo (1, 24, or 120). Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/git-commit-graph.txt | 14 +++++++++++++- builtin/commit-graph.c | 27 +++++++++++++++++++++------ commit-graph.c | 27 +++++++++++++++++++++++++-- commit-graph.h | 4 +++- t/t5318-commit-graph.sh | 13 +++++++++++++ 5 files changed, 75 insertions(+), 10 deletions(-) diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index 8143cc3f078e46..442ac243e689ad 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -36,7 +36,13 @@ COMMANDS Write a commit graph file based on the commits found in packfiles. + With the `--stdin-packs` option, generate the new commit graph by -walking objects only in the specified pack-indexes. +walking objects only in the specified pack-indexes. (Cannot be combined +with --stdin-commits.) ++ +With the `--stdin-commits` option, generate the new commit graph by +walking commits starting at the commits specified in stdin as a list +of OIDs in hex, one OID per line. (Cannot be combined with +--stdin-packs.) 'read':: @@ -60,6 +66,12 @@ $ git commit-graph write $ echo | git commit-graph write --stdin-packs ------------------------------------------------ +* Write a graph file containing all reachable commits. ++ +------------------------------------------------ +$ git show-ref -s | git commit-graph write --stdin-commits +------------------------------------------------ + * Read basic information from the commit-graph file. + ------------------------------------------------ diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index 5c7019900307f0..b5c0b0890562cb 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -8,7 +8,7 @@ static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph [--object-dir ]"), N_("git commit-graph read [--object-dir ]"), - N_("git commit-graph write [--object-dir ] [--stdin-packs]"), + N_("git commit-graph write [--object-dir ] [--stdin-packs|--stdin-commits]"), NULL }; @@ -18,13 +18,14 @@ static const char * const builtin_commit_graph_read_usage[] = { }; static const char * const builtin_commit_graph_write_usage[] = { - N_("git commit-graph write [--object-dir ] [--stdin-packs]"), + N_("git commit-graph write [--object-dir ] [--stdin-packs|--stdin-commits]"), NULL }; static struct opts_commit_graph { const char *obj_dir; int stdin_packs; + int stdin_commits; } opts; static int graph_read(int argc, const char **argv) @@ -79,6 +80,8 @@ static int graph_write(int argc, const char **argv) { const char **pack_indexes = NULL; int packs_nr = 0; + const char **commit_hex = NULL; + int commits_nr = 0; const char **lines = NULL; int lines_nr = 0; int lines_alloc = 0; @@ -89,6 +92,8 @@ static int graph_write(int argc, const char **argv) N_("The object directory to store the graph")), OPT_BOOL(0, "stdin-packs", &opts.stdin_packs, N_("scan pack-indexes listed by stdin for commits")), + OPT_BOOL(0, "stdin-commits", &opts.stdin_commits, + N_("start walk at commits listed by stdin")), OPT_END(), }; @@ -96,10 +101,12 @@ static int graph_write(int argc, const char **argv) builtin_commit_graph_write_options, builtin_commit_graph_write_usage, 0); + if (opts.stdin_packs && opts.stdin_commits) + die(_("cannot use both --stdin-commits and --stdin-packs")); if (!opts.obj_dir) opts.obj_dir = get_object_directory(); - if (opts.stdin_packs) { + if (opts.stdin_packs || opts.stdin_commits) { struct strbuf buf = STRBUF_INIT; lines_nr = 0; lines_alloc = 128; @@ -110,13 +117,21 @@ static int graph_write(int argc, const char **argv) lines[lines_nr++] = strbuf_detach(&buf, NULL); } - pack_indexes = lines; - packs_nr = lines_nr; + if (opts.stdin_packs) { + pack_indexes = lines; + packs_nr = lines_nr; + } + if (opts.stdin_commits) { + commit_hex = lines; + commits_nr = lines_nr; + } } write_commit_graph(opts.obj_dir, pack_indexes, - packs_nr); + packs_nr, + commit_hex, + commits_nr); return 0; } diff --git a/commit-graph.c b/commit-graph.c index 70472840a3bfb9..a59d1e387bea6a 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -551,7 +551,9 @@ static void close_reachable(struct packed_oid_list *oids) void write_commit_graph(const char *obj_dir, const char **pack_indexes, - int nr_packs) + int nr_packs, + const char **commit_hex, + int nr_commits) { struct packed_oid_list oids; struct packed_commit_list commits; @@ -591,7 +593,28 @@ void write_commit_graph(const char *obj_dir, close_pack(p); } strbuf_release(&packname); - } else + } + + if (commit_hex) { + for (i = 0; i < nr_commits; i++) { + const char *end; + struct object_id oid; + struct commit *result; + + if (commit_hex[i] && parse_oid_hex(commit_hex[i], &oid, &end)) + continue; + + result = lookup_commit_reference_gently(&oid, 1); + + if (result) { + ALLOC_GROW(oids.list, oids.nr + 1, oids.alloc); + oidcpy(&oids.list[oids.nr], &(result->object.oid)); + oids.nr++; + } + } + } + + if (!pack_indexes && !commit_hex) for_each_packed_object(add_packed_commits, &oids, 0); close_reachable(&oids); diff --git a/commit-graph.h b/commit-graph.h index f065f0866f83e2..fd035101b282bc 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -38,6 +38,8 @@ struct commit_graph *load_commit_graph_one(const char *graph_file); void write_commit_graph(const char *obj_dir, const char **pack_indexes, - int nr_packs); + int nr_packs, + const char **commit_hex, + int nr_commits); #endif diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index 3bb44d0c09e15c..c28cfb5d7fb2e6 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -177,6 +177,19 @@ test_expect_success 'build graph from latest pack with closure' ' graph_git_behavior 'graph from pack, commit 8 vs merge 1' full commits/8 merge/1 graph_git_behavior 'graph from pack, commit 8 vs merge 2' full commits/8 merge/2 +test_expect_success 'build graph from commits with closure' ' + cd "$TRASH_DIRECTORY/full" && + git tag -a -m "merge" tag/merge merge/2 && + git rev-parse tag/merge >commits-in && + git rev-parse merge/1 >>commits-in && + cat commits-in | git commit-graph write --stdin-commits && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "6" +' + +graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'graph from commits, commit 8 vs merge 2' full commits/8 merge/2 + test_expect_success 'setup bare repo' ' cd "$TRASH_DIRECTORY" && git clone --bare --no-local full bare && From 7547b95b4fbb8591726b1d9381c176cc27fc6aea Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Tue, 10 Apr 2018 08:56:08 -0400 Subject: [PATCH 14/18] commit-graph: implement "--append" option Teach git-commit-graph to add all commits from the existing commit-graph file to the file about to be written. This should be used when adding new commits without performing garbage collection. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- Documentation/git-commit-graph.txt | 10 ++++++++++ builtin/commit-graph.c | 10 +++++++--- commit-graph.c | 17 ++++++++++++++++- commit-graph.h | 3 ++- t/t5318-commit-graph.sh | 10 ++++++++++ 5 files changed, 45 insertions(+), 5 deletions(-) diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt index 442ac243e689ad..4c97b555cca5c1 100644 --- a/Documentation/git-commit-graph.txt +++ b/Documentation/git-commit-graph.txt @@ -43,6 +43,9 @@ With the `--stdin-commits` option, generate the new commit graph by walking commits starting at the commits specified in stdin as a list of OIDs in hex, one OID per line. (Cannot be combined with --stdin-packs.) ++ +With the `--append` option, include all commits that are present in the +existing commit-graph file. 'read':: @@ -72,6 +75,13 @@ $ echo | git commit-graph write --stdin-packs $ git show-ref -s | git commit-graph write --stdin-commits ------------------------------------------------ +* Write a graph file containing all commits in the current +* commit-graph file along with those reachable from HEAD. ++ +------------------------------------------------ +$ git rev-parse HEAD | git commit-graph write --stdin-commits --append +------------------------------------------------ + * Read basic information from the commit-graph file. + ------------------------------------------------ diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c index b5c0b0890562cb..37420ae0fde81e 100644 --- a/builtin/commit-graph.c +++ b/builtin/commit-graph.c @@ -8,7 +8,7 @@ static char const * const builtin_commit_graph_usage[] = { N_("git commit-graph [--object-dir ]"), N_("git commit-graph read [--object-dir ]"), - N_("git commit-graph write [--object-dir ] [--stdin-packs|--stdin-commits]"), + N_("git commit-graph write [--object-dir ] [--append] [--stdin-packs|--stdin-commits]"), NULL }; @@ -18,7 +18,7 @@ static const char * const builtin_commit_graph_read_usage[] = { }; static const char * const builtin_commit_graph_write_usage[] = { - N_("git commit-graph write [--object-dir ] [--stdin-packs|--stdin-commits]"), + N_("git commit-graph write [--object-dir ] [--append] [--stdin-packs|--stdin-commits]"), NULL }; @@ -26,6 +26,7 @@ static struct opts_commit_graph { const char *obj_dir; int stdin_packs; int stdin_commits; + int append; } opts; static int graph_read(int argc, const char **argv) @@ -94,6 +95,8 @@ static int graph_write(int argc, const char **argv) N_("scan pack-indexes listed by stdin for commits")), OPT_BOOL(0, "stdin-commits", &opts.stdin_commits, N_("start walk at commits listed by stdin")), + OPT_BOOL(0, "append", &opts.append, + N_("include all commits already in the commit-graph file")), OPT_END(), }; @@ -131,7 +134,8 @@ static int graph_write(int argc, const char **argv) pack_indexes, packs_nr, commit_hex, - commits_nr); + commits_nr, + opts.append); return 0; } diff --git a/commit-graph.c b/commit-graph.c index a59d1e387bea6a..3ff8c84c0e4438 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -553,7 +553,8 @@ void write_commit_graph(const char *obj_dir, const char **pack_indexes, int nr_packs, const char **commit_hex, - int nr_commits) + int nr_commits, + int append) { struct packed_oid_list oids; struct packed_commit_list commits; @@ -571,10 +572,24 @@ void write_commit_graph(const char *obj_dir, oids.nr = 0; oids.alloc = approximate_object_count() / 4; + if (append) { + prepare_commit_graph_one(obj_dir); + if (commit_graph) + oids.alloc += commit_graph->num_commits; + } + if (oids.alloc < 1024) oids.alloc = 1024; ALLOC_ARRAY(oids.list, oids.alloc); + if (append && commit_graph) { + for (i = 0; i < commit_graph->num_commits; i++) { + const unsigned char *hash = commit_graph->chunk_oid_lookup + + commit_graph->hash_len * i; + hashcpy(oids.list[oids.nr++].hash, hash); + } + } + if (pack_indexes) { struct strbuf packname = STRBUF_INIT; int dirlen; diff --git a/commit-graph.h b/commit-graph.h index fd035101b282bc..e1d8580c98a24a 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -40,6 +40,7 @@ void write_commit_graph(const char *obj_dir, const char **pack_indexes, int nr_packs, const char **commit_hex, - int nr_commits); + int nr_commits, + int append); #endif diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh index c28cfb5d7fb2e6..a380419b65bdf1 100755 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@ -190,6 +190,16 @@ test_expect_success 'build graph from commits with closure' ' graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1 graph_git_behavior 'graph from commits, commit 8 vs merge 2' full commits/8 merge/2 +test_expect_success 'build graph from commits with append' ' + cd "$TRASH_DIRECTORY/full" && + git rev-parse merge/3 | git commit-graph write --stdin-commits --append && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "10" "large_edges" +' + +graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'append graph, commit 8 vs merge 2' full commits/8 merge/2 + test_expect_success 'setup bare repo' ' cd "$TRASH_DIRECTORY" && git clone --bare --no-local full bare && From 891435d55da80ca3654b19834481205be6bdfe33 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Fri, 6 Apr 2018 19:09:32 +0000 Subject: [PATCH 15/18] treewide: rename tree to maybe_tree Using the commit-graph file to walk commit history removes the large cost of parsing commits during the walk. This exposes a performance issue: lookup_tree() takes a large portion of the computation time, even when Git never uses those trees. In anticipation of lazy-loading these trees, rename the 'tree' member of struct commit to 'maybe_tree'. This serves two purposes: it hints at the future role of possibly being NULL even if the commit has a valid tree, and it allows for unambiguous transformation from simple member access (i.e. commit->maybe_tree) to method access. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- blame.c | 18 +++++++++--------- builtin/checkout.c | 12 ++++++------ builtin/diff.c | 2 +- builtin/fast-export.c | 6 +++--- builtin/log.c | 4 ++-- builtin/reflog.c | 2 +- commit-graph.c | 4 ++-- commit.c | 2 +- commit.h | 2 +- fsck.c | 6 +++--- http-push.c | 2 +- line-log.c | 4 ++-- list-objects.c | 10 +++++----- log-tree.c | 6 +++--- merge-recursive.c | 5 +++-- notes-merge.c | 8 ++++---- packfile.c | 2 +- pretty.c | 4 ++-- ref-filter.c | 2 +- revision.c | 8 ++++---- sequencer.c | 12 ++++++------ sha1_name.c | 2 +- tree.c | 4 ++-- walker.c | 2 +- 24 files changed, 65 insertions(+), 64 deletions(-) diff --git a/blame.c b/blame.c index 200e0ad9a299ad..b78e649cacf4eb 100644 --- a/blame.c +++ b/blame.c @@ -553,10 +553,10 @@ static struct blame_origin *find_origin(struct commit *parent, diff_setup_done(&diff_opts); if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); + do_diff_cache(&parent->maybe_tree->object.oid, &diff_opts); else - diff_tree_oid(&parent->tree->object.oid, - &origin->commit->tree->object.oid, + diff_tree_oid(&parent->maybe_tree->object.oid, + &origin->commit->maybe_tree->object.oid, "", &diff_opts); diffcore_std(&diff_opts); @@ -622,10 +622,10 @@ static struct blame_origin *find_rename(struct commit *parent, diff_setup_done(&diff_opts); if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); + do_diff_cache(&parent->maybe_tree->object.oid, &diff_opts); else - diff_tree_oid(&parent->tree->object.oid, - &origin->commit->tree->object.oid, + diff_tree_oid(&parent->maybe_tree->object.oid, + &origin->commit->maybe_tree->object.oid, "", &diff_opts); diffcore_std(&diff_opts); @@ -1257,10 +1257,10 @@ static void find_copy_in_parent(struct blame_scoreboard *sb, diff_opts.flags.find_copies_harder = 1; if (is_null_oid(&target->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); + do_diff_cache(&parent->maybe_tree->object.oid, &diff_opts); else - diff_tree_oid(&parent->tree->object.oid, - &target->commit->tree->object.oid, + diff_tree_oid(&parent->maybe_tree->object.oid, + &target->commit->maybe_tree->object.oid, "", &diff_opts); if (!diff_opts.flags.find_copies_harder) diff --git a/builtin/checkout.c b/builtin/checkout.c index a52af2e5070531..ca6aa297941f24 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -484,7 +484,7 @@ static int merge_working_tree(const struct checkout_opts *opts, resolve_undo_clear(); if (opts->force) { - ret = reset_tree(new_branch_info->commit->tree, opts, 1, writeout_error); + ret = reset_tree(new_branch_info->commit->maybe_tree, opts, 1, writeout_error); if (ret) return ret; } else { @@ -570,18 +570,18 @@ static int merge_working_tree(const struct checkout_opts *opts, o.verbosity = 0; work = write_tree_from_memory(&o); - ret = reset_tree(new_branch_info->commit->tree, opts, 1, + ret = reset_tree(new_branch_info->commit->maybe_tree, opts, 1, writeout_error); if (ret) return ret; o.ancestor = old_branch_info->name; o.branch1 = new_branch_info->name; o.branch2 = "local"; - ret = merge_trees(&o, new_branch_info->commit->tree, work, - old_branch_info->commit->tree, &result); + ret = merge_trees(&o, new_branch_info->commit->maybe_tree, work, + old_branch_info->commit->maybe_tree, &result); if (ret < 0) exit(128); - ret = reset_tree(new_branch_info->commit->tree, opts, 0, + ret = reset_tree(new_branch_info->commit->maybe_tree, opts, 0, writeout_error); strbuf_release(&o.obuf); if (ret) @@ -1002,7 +1002,7 @@ static int parse_branchname_arg(int argc, const char **argv, *source_tree = parse_tree_indirect(rev); } else { parse_commit_or_die(new_branch_info->commit); - *source_tree = new_branch_info->commit->tree; + *source_tree = new_branch_info->commit->maybe_tree; } if (!*source_tree) /* case (1): want a tree */ diff --git a/builtin/diff.c b/builtin/diff.c index 16bfb22f7381ee..34f18a5f3f5c89 100644 --- a/builtin/diff.c +++ b/builtin/diff.c @@ -398,7 +398,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix) if (!obj) die(_("invalid object '%s' given."), name); if (obj->type == OBJ_COMMIT) - obj = &((struct commit *)obj)->tree->object; + obj = &((struct commit *)obj)->maybe_tree->object; if (obj->type == OBJ_TREE) { obj->flags |= flags; diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 27b2cc138e67c0..91e526b30d2830 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -578,11 +578,11 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, get_object_mark(&commit->parents->item->object) != 0 && !full_tree) { parse_commit_or_die(commit->parents->item); - diff_tree_oid(&commit->parents->item->tree->object.oid, - &commit->tree->object.oid, "", &rev->diffopt); + diff_tree_oid(&commit->parents->item->maybe_tree->object.oid, + &commit->maybe_tree->object.oid, "", &rev->diffopt); } else - diff_root_tree_oid(&commit->tree->object.oid, + diff_root_tree_oid(&commit->maybe_tree->object.oid, "", &rev->diffopt); /* Export the referenced blobs, and remember the marks. */ diff --git a/builtin/log.c b/builtin/log.c index 46b4ca13e5c11f..a1fbc608bc2424 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -1064,8 +1064,8 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout, diff_setup_done(&opts); - diff_tree_oid(&origin->tree->object.oid, - &head->tree->object.oid, + diff_tree_oid(&origin->maybe_tree->object.oid, + &head->maybe_tree->object.oid, "", &opts); diffcore_std(&opts); diff_flush(&opts); diff --git a/builtin/reflog.c b/builtin/reflog.c index ac3dcd7a51170c..29d80a35a13198 100644 --- a/builtin/reflog.c +++ b/builtin/reflog.c @@ -153,7 +153,7 @@ static int commit_is_complete(struct commit *commit) for (i = 0; i < found.nr; i++) { struct commit *c = (struct commit *)found.objects[i].item; - if (!tree_is_complete(&c->tree->object.oid)) { + if (!tree_is_complete(&c->maybe_tree->object.oid)) { is_incomplete = 1; c->object.flags |= INCOMPLETE; } diff --git a/commit-graph.c b/commit-graph.c index 3ff8c84c0e4438..49c622c5569f53 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -258,7 +258,7 @@ static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uin item->graph_pos = pos; hashcpy(oid.hash, commit_data); - item->tree = lookup_tree(&oid); + item->maybe_tree = lookup_tree(&oid); date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; date_low = get_be32(commit_data + g->hash_len + 12); @@ -369,7 +369,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len, uint32_t packedDate[2]; parse_commit(*list); - hashwrite(f, (*list)->tree->object.oid.hash, hash_len); + hashwrite(f, (*list)->maybe_tree->object.oid.hash, hash_len); parent = (*list)->parents; diff --git a/commit.c b/commit.c index 3e39c86abf885f..fbc092808cb3dd 100644 --- a/commit.c +++ b/commit.c @@ -335,7 +335,7 @@ int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long s if (get_sha1_hex(bufptr + 5, parent.hash) < 0) return error("bad tree pointer in commit %s", oid_to_hex(&item->object.oid)); - item->tree = lookup_tree(&parent); + item->maybe_tree = lookup_tree(&parent); bufptr += tree_entry_len + 1; /* "tree " + "hex sha1" + "\n" */ pptr = &item->parents; diff --git a/commit.h b/commit.h index e57ae4b58380cc..c4d6e6e0646590 100644 --- a/commit.h +++ b/commit.h @@ -22,7 +22,7 @@ struct commit { unsigned int index; timestamp_t date; struct commit_list *parents; - struct tree *tree; + struct tree *maybe_tree; uint32_t graph_pos; }; diff --git a/fsck.c b/fsck.c index 5c8c12dde38191..3228ca5beeaed5 100644 --- a/fsck.c +++ b/fsck.c @@ -396,9 +396,9 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio name = get_object_name(options, &commit->object); if (name) - put_object_name(options, &commit->tree->object, "%s:", name); + put_object_name(options, &commit->maybe_tree->object, "%s:", name); - result = options->walk((struct object *)commit->tree, OBJ_TREE, data, options); + result = options->walk((struct object *)commit->maybe_tree, OBJ_TREE, data, options); if (result < 0) return result; res = result; @@ -772,7 +772,7 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer, err = fsck_ident(&buffer, &commit->object, options); if (err) return err; - if (!commit->tree) { + if (!commit->maybe_tree) { err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", sha1_to_hex(tree_sha1)); if (err) return err; diff --git a/http-push.c b/http-push.c index 7dcd9daf62cf07..d83479f32f4cfa 100644 --- a/http-push.c +++ b/http-push.c @@ -1330,7 +1330,7 @@ static int get_delta(struct rev_info *revs, struct remote_lock *lock) int count = 0; while ((commit = get_revision(revs)) != NULL) { - p = process_tree(commit->tree, p); + p = process_tree(commit->maybe_tree, p); commit->object.flags |= LOCAL; if (!(commit->object.flags & UNINTERESTING)) count += add_send_request(&commit->object, lock); diff --git a/line-log.c b/line-log.c index cdc2257db56f7d..e714969ca22e86 100644 --- a/line-log.c +++ b/line-log.c @@ -817,8 +817,8 @@ static void queue_diffs(struct line_log_data *range, assert(commit); DIFF_QUEUE_CLEAR(&diff_queued_diff); - diff_tree_oid(parent ? &parent->tree->object.oid : NULL, - &commit->tree->object.oid, "", opt); + diff_tree_oid(parent ? &parent->maybe_tree->object.oid : NULL, + &commit->maybe_tree->object.oid, "", opt); if (opt->detect_rename) { filter_diffs_for_paths(range, 1); if (diff_might_be_rename()) diff --git a/list-objects.c b/list-objects.c index 168bef688a8948..bfd09f545c971e 100644 --- a/list-objects.c +++ b/list-objects.c @@ -195,7 +195,7 @@ static void mark_edge_parents_uninteresting(struct commit *commit, struct commit *parent = parents->item; if (!(parent->object.flags & UNINTERESTING)) continue; - mark_tree_uninteresting(parent->tree); + mark_tree_uninteresting(parent->maybe_tree); if (revs->edge_hint && !(parent->object.flags & SHOWN)) { parent->object.flags |= SHOWN; show_edge(parent); @@ -212,7 +212,7 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge) struct commit *commit = list->item; if (commit->object.flags & UNINTERESTING) { - mark_tree_uninteresting(commit->tree); + mark_tree_uninteresting(commit->maybe_tree); if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) { commit->object.flags |= SHOWN; show_edge(commit); @@ -227,7 +227,7 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge) struct commit *commit = (struct commit *)obj; if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING)) continue; - mark_tree_uninteresting(commit->tree); + mark_tree_uninteresting(commit->maybe_tree); if (!(obj->flags & SHOWN)) { obj->flags |= SHOWN; show_edge(commit); @@ -300,8 +300,8 @@ static void do_traverse(struct rev_info *revs, * an uninteresting boundary commit may not have its tree * parsed yet, but we are not going to show them anyway */ - if (commit->tree) - add_pending_tree(revs, commit->tree); + if (commit->maybe_tree) + add_pending_tree(revs, commit->maybe_tree); show_commit(commit, show_data); if (revs->tree_blobs_in_commit_order) diff --git a/log-tree.c b/log-tree.c index bdf23c5f7b89ed..99499af57c102f 100644 --- a/log-tree.c +++ b/log-tree.c @@ -806,7 +806,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log return 0; parse_commit_or_die(commit); - oid = &commit->tree->object.oid; + oid = &commit->maybe_tree->object.oid; /* Root commit? */ parents = get_saved_parents(opt, commit); @@ -831,7 +831,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log * we merged _in_. */ parse_commit_or_die(parents->item); - diff_tree_oid(&parents->item->tree->object.oid, + diff_tree_oid(&parents->item->maybe_tree->object.oid, oid, "", &opt->diffopt); log_tree_diff_flush(opt); return !opt->loginfo; @@ -846,7 +846,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log struct commit *parent = parents->item; parse_commit_or_die(parent); - diff_tree_oid(&parent->tree->object.oid, + diff_tree_oid(&parent->maybe_tree->object.oid, oid, "", &opt->diffopt); log_tree_diff_flush(opt); diff --git a/merge-recursive.c b/merge-recursive.c index 6ff971f9a2a8e2..0f75d75d1788ae 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -101,7 +101,7 @@ static struct commit *make_virtual_commit(struct tree *tree, const char *comment struct commit *commit = alloc_commit_node(); set_merge_remote_desc(commit, comment, (struct object *)commit); - commit->tree = tree; + commit->maybe_tree = tree; commit->object.parsed = 1; return commit; } @@ -2154,7 +2154,8 @@ int merge_recursive(struct merge_options *o, read_cache(); o->ancestor = "merged common ancestors"; - clean = merge_trees(o, h1->tree, h2->tree, merged_common_ancestors->tree, + clean = merge_trees(o, h1->maybe_tree, h2->maybe_tree, + merged_common_ancestors->maybe_tree, &mrtree); if (clean < 0) { flush_output(o); diff --git a/notes-merge.c b/notes-merge.c index c09c5e0e474a30..1d3edc89425d99 100644 --- a/notes-merge.c +++ b/notes-merge.c @@ -600,14 +600,14 @@ int notes_merge(struct notes_merge_options *o, printf("No merge base found; doing history-less merge\n"); } else if (!bases->next) { base_oid = &bases->item->object.oid; - base_tree_oid = &bases->item->tree->object.oid; + base_tree_oid = &bases->item->maybe_tree->object.oid; if (o->verbosity >= 4) printf("One merge base found (%.7s)\n", oid_to_hex(base_oid)); } else { /* TODO: How to handle multiple merge-bases? */ base_oid = &bases->item->object.oid; - base_tree_oid = &bases->item->tree->object.oid; + base_tree_oid = &bases->item->maybe_tree->object.oid; if (o->verbosity >= 3) printf("Multiple merge bases found. Using the first " "(%.7s)\n", oid_to_hex(base_oid)); @@ -634,8 +634,8 @@ int notes_merge(struct notes_merge_options *o, goto found_result; } - result = merge_from_diffs(o, base_tree_oid, &local->tree->object.oid, - &remote->tree->object.oid, local_tree); + result = merge_from_diffs(o, base_tree_oid, &local->maybe_tree->object.oid, + &remote->maybe_tree->object.oid, local_tree); if (result != 0) { /* non-trivial merge (with or without conflicts) */ /* Commit (partial) result */ diff --git a/packfile.c b/packfile.c index b1d33b646a0308..3eb9c4a36e66fa 100644 --- a/packfile.c +++ b/packfile.c @@ -1925,7 +1925,7 @@ static int add_promisor_object(const struct object_id *oid, struct commit *commit = (struct commit *) obj; struct commit_list *parents = commit->parents; - oidset_insert(set, &commit->tree->object.oid); + oidset_insert(set, &commit->maybe_tree->object.oid); for (; parents; parents = parents->next) oidset_insert(set, &parents->item->object.oid); } else if (obj->type == OBJ_TAG) { diff --git a/pretty.c b/pretty.c index f7ce4902301490..42095ea495a641 100644 --- a/pretty.c +++ b/pretty.c @@ -1161,10 +1161,10 @@ static size_t format_commit_one(struct strbuf *sb, /* in UTF-8 */ strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_RESET)); return 1; case 'T': /* tree hash */ - strbuf_addstr(sb, oid_to_hex(&commit->tree->object.oid)); + strbuf_addstr(sb, oid_to_hex(&commit->maybe_tree->object.oid)); return 1; case 't': /* abbreviated tree hash */ - strbuf_add_unique_abbrev(sb, commit->tree->object.oid.hash, + strbuf_add_unique_abbrev(sb, commit->maybe_tree->object.oid.hash, c->pretty_ctx->abbrev); return 1; case 'P': /* parent hashes */ diff --git a/ref-filter.c b/ref-filter.c index 99a45beb14ea88..a59654cfd372db 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -815,7 +815,7 @@ static void grab_commit_values(struct atom_value *val, int deref, struct object if (deref) name++; if (!strcmp(name, "tree")) { - v->s = xstrdup(oid_to_hex(&commit->tree->object.oid)); + v->s = xstrdup(oid_to_hex(&commit->maybe_tree->object.oid)); } else if (!strcmp(name, "numparent")) { v->value = commit_list_count(commit->parents); diff --git a/revision.c b/revision.c index 5c1cb7277c2fef..f61d1c930789b3 100644 --- a/revision.c +++ b/revision.c @@ -439,8 +439,8 @@ static void file_change(struct diff_options *options, static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct commit *commit) { - struct tree *t1 = parent->tree; - struct tree *t2 = commit->tree; + struct tree *t1 = parent->maybe_tree; + struct tree *t2 = commit->maybe_tree; if (!t1) return REV_TREE_NEW; @@ -476,7 +476,7 @@ static int rev_compare_tree(struct rev_info *revs, static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit) { int retval; - struct tree *t1 = commit->tree; + struct tree *t1 = commit->maybe_tree; if (!t1) return 0; @@ -614,7 +614,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) if (!revs->prune) return; - if (!commit->tree) + if (!commit->maybe_tree) return; if (!commit->parents) { diff --git a/sequencer.c b/sequencer.c index 6ca4499d23e74d..9269607a485eae 100644 --- a/sequencer.c +++ b/sequencer.c @@ -501,8 +501,8 @@ static int do_recursive_merge(struct commit *base, struct commit *next, o.show_rename_progress = 1; head_tree = parse_tree_indirect(head); - next_tree = next ? next->tree : empty_tree(); - base_tree = base ? base->tree : empty_tree(); + next_tree = next ? next->maybe_tree : empty_tree(); + base_tree = base ? base->maybe_tree : empty_tree(); for (xopt = opts->xopts; xopt != opts->xopts + opts->xopts_nr; xopt++) parse_merge_opt(&o, *xopt); @@ -562,7 +562,7 @@ static int is_index_unchanged(void) return error(_("unable to update cache tree")); return !oidcmp(&active_cache_tree->oid, - &head_commit->tree->object.oid); + &head_commit->maybe_tree->object.oid); } static int write_author_script(const char *message) @@ -1119,7 +1119,7 @@ static int try_to_commit(struct strbuf *msg, const char *author, } if (!(flags & ALLOW_EMPTY) && !oidcmp(current_head ? - ¤t_head->tree->object.oid : + ¤t_head->maybe_tree->object.oid : &empty_tree_oid, &tree)) { res = 1; /* run 'git commit' to display error message */ goto out; @@ -1217,12 +1217,12 @@ static int is_original_commit_empty(struct commit *commit) if (parse_commit(parent)) return error(_("could not parse parent commit %s"), oid_to_hex(&parent->object.oid)); - ptree_oid = &parent->tree->object.oid; + ptree_oid = &parent->maybe_tree->object.oid; } else { ptree_oid = the_hash_algo->empty_tree; /* commit is root */ } - return !oidcmp(ptree_oid, &commit->tree->object.oid); + return !oidcmp(ptree_oid, &commit->maybe_tree->object.oid); } /* diff --git a/sha1_name.c b/sha1_name.c index e7c18ffc26daf1..6ca2a2de37e2ad 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -896,7 +896,7 @@ struct object *peel_to_type(const char *name, int namelen, if (o->type == OBJ_TAG) o = ((struct tag*) o)->tagged; else if (o->type == OBJ_COMMIT) - o = &(((struct commit *) o)->tree->object); + o = &(((struct commit *) o)->maybe_tree->object); else { if (name) error("%.*s: expected %s type, but the object " diff --git a/tree.c b/tree.c index b224115e0f4d61..dbc5e0be544ef1 100644 --- a/tree.c +++ b/tree.c @@ -109,7 +109,7 @@ static int read_tree_1(struct tree *tree, struct strbuf *base, oid_to_hex(entry.oid), base->buf, entry.path); - oidcpy(&oid, &commit->tree->object.oid); + oidcpy(&oid, &commit->maybe_tree->object.oid); } else continue; @@ -248,7 +248,7 @@ struct tree *parse_tree_indirect(const struct object_id *oid) if (obj->type == OBJ_TREE) return (struct tree *) obj; else if (obj->type == OBJ_COMMIT) - obj = &(((struct commit *) obj)->tree->object); + obj = &(((struct commit *) obj)->maybe_tree->object); else if (obj->type == OBJ_TAG) obj = ((struct tag *) obj)->tagged; else diff --git a/walker.c b/walker.c index dffb9c8e37c220..1d5f3059a29841 100644 --- a/walker.c +++ b/walker.c @@ -87,7 +87,7 @@ static int process_commit(struct walker *walker, struct commit *commit) walker_say(walker, "walk %s\n", oid_to_hex(&commit->object.oid)); if (walker->get_tree) { - if (process(walker, &commit->tree->object)) + if (process(walker, &commit->maybe_tree->object)) return -1; if (!walker->get_all) walker->get_tree = 0; From 5bb03de102b40d9e564be3a3a39084a550db79cb Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Fri, 6 Apr 2018 19:09:34 +0000 Subject: [PATCH 16/18] commit: create get_commit_tree() method While walking the commit graph, we load struct commit objects into the object cache. During this process, we also load struct tree objects for the root tree of each of these commits. We load these objects even if we are only computing commit reachability information, such as a merge base or ahead/behind information. Create get_commit_tree() as a first step to removing direct references to the 'maybe_tree' member of struct commit. Create get_commit_tree_oid() as a shortcut for several references to "&commit->maybe_tree->object.oid" in the codebase. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- commit.c | 10 ++++++++++ commit.h | 3 +++ 2 files changed, 13 insertions(+) diff --git a/commit.c b/commit.c index fbc092808cb3dd..aea2ca1f8ba307 100644 --- a/commit.c +++ b/commit.c @@ -296,6 +296,16 @@ void free_commit_buffer(struct commit *commit) } } +struct tree *get_commit_tree(const struct commit *commit) +{ + return commit->maybe_tree; +} + +struct object_id *get_commit_tree_oid(const struct commit *commit) +{ + return &get_commit_tree(commit)->object.oid; +} + const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep) { struct commit_buffer *v = buffer_slab_peek(&buffer_slab, commit); diff --git a/commit.h b/commit.h index c4d6e6e0646590..dc4bf97d9f3b74 100644 --- a/commit.h +++ b/commit.h @@ -102,6 +102,9 @@ void unuse_commit_buffer(const struct commit *, const void *buffer); */ void free_commit_buffer(struct commit *); +struct tree *get_commit_tree(const struct commit *); +struct object_id *get_commit_tree_oid(const struct commit *); + /* * Disassociate any cached object buffer from the commit, but do not free it. * The buffer (or NULL, if none) is returned. From 2e27bd7731d47b374c1c14b53af07b3bfa39fcac Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Fri, 6 Apr 2018 19:09:38 +0000 Subject: [PATCH 17/18] treewide: replace maybe_tree with accessor methods In anticipation of making trees load lazily, create a Coccinelle script (contrib/coccinelle/commit.cocci) to ensure that all references to the 'maybe_tree' member of struct commit are either mutations or accesses through get_commit_tree() or get_commit_tree_oid(). Apply the Coccinelle script to create the rest of the patch. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- blame.c | 18 +++++++++--------- builtin/checkout.c | 18 ++++++++++++------ builtin/diff.c | 2 +- builtin/fast-export.c | 6 +++--- builtin/log.c | 4 ++-- builtin/reflog.c | 2 +- commit-graph.c | 2 +- contrib/coccinelle/commit.cocci | 30 ++++++++++++++++++++++++++++++ fsck.c | 8 +++++--- http-push.c | 2 +- line-log.c | 4 ++-- list-objects.c | 10 +++++----- log-tree.c | 6 +++--- merge-recursive.c | 4 ++-- notes-merge.c | 9 +++++---- packfile.c | 2 +- pretty.c | 5 +++-- ref-filter.c | 2 +- revision.c | 8 ++++---- sequencer.c | 12 ++++++------ sha1_name.c | 2 +- tree.c | 4 ++-- walker.c | 2 +- 23 files changed, 101 insertions(+), 61 deletions(-) create mode 100644 contrib/coccinelle/commit.cocci diff --git a/blame.c b/blame.c index b78e649cacf4eb..7f5700b3248bb5 100644 --- a/blame.c +++ b/blame.c @@ -553,10 +553,10 @@ static struct blame_origin *find_origin(struct commit *parent, diff_setup_done(&diff_opts); if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->maybe_tree->object.oid, &diff_opts); + do_diff_cache(get_commit_tree_oid(parent), &diff_opts); else - diff_tree_oid(&parent->maybe_tree->object.oid, - &origin->commit->maybe_tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), + get_commit_tree_oid(origin->commit), "", &diff_opts); diffcore_std(&diff_opts); @@ -622,10 +622,10 @@ static struct blame_origin *find_rename(struct commit *parent, diff_setup_done(&diff_opts); if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->maybe_tree->object.oid, &diff_opts); + do_diff_cache(get_commit_tree_oid(parent), &diff_opts); else - diff_tree_oid(&parent->maybe_tree->object.oid, - &origin->commit->maybe_tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), + get_commit_tree_oid(origin->commit), "", &diff_opts); diffcore_std(&diff_opts); @@ -1257,10 +1257,10 @@ static void find_copy_in_parent(struct blame_scoreboard *sb, diff_opts.flags.find_copies_harder = 1; if (is_null_oid(&target->commit->object.oid)) - do_diff_cache(&parent->maybe_tree->object.oid, &diff_opts); + do_diff_cache(get_commit_tree_oid(parent), &diff_opts); else - diff_tree_oid(&parent->maybe_tree->object.oid, - &target->commit->maybe_tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), + get_commit_tree_oid(target->commit), "", &diff_opts); if (!diff_opts.flags.find_copies_harder) diff --git a/builtin/checkout.c b/builtin/checkout.c index ca6aa297941f24..4e803ae0921d78 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -484,7 +484,8 @@ static int merge_working_tree(const struct checkout_opts *opts, resolve_undo_clear(); if (opts->force) { - ret = reset_tree(new_branch_info->commit->maybe_tree, opts, 1, writeout_error); + ret = reset_tree(get_commit_tree(new_branch_info->commit), + opts, 1, writeout_error); if (ret) return ret; } else { @@ -570,18 +571,23 @@ static int merge_working_tree(const struct checkout_opts *opts, o.verbosity = 0; work = write_tree_from_memory(&o); - ret = reset_tree(new_branch_info->commit->maybe_tree, opts, 1, + ret = reset_tree(get_commit_tree(new_branch_info->commit), + opts, 1, writeout_error); if (ret) return ret; o.ancestor = old_branch_info->name; o.branch1 = new_branch_info->name; o.branch2 = "local"; - ret = merge_trees(&o, new_branch_info->commit->maybe_tree, work, - old_branch_info->commit->maybe_tree, &result); + ret = merge_trees(&o, + get_commit_tree(new_branch_info->commit), + work, + get_commit_tree(old_branch_info->commit), + &result); if (ret < 0) exit(128); - ret = reset_tree(new_branch_info->commit->maybe_tree, opts, 0, + ret = reset_tree(get_commit_tree(new_branch_info->commit), + opts, 0, writeout_error); strbuf_release(&o.obuf); if (ret) @@ -1002,7 +1008,7 @@ static int parse_branchname_arg(int argc, const char **argv, *source_tree = parse_tree_indirect(rev); } else { parse_commit_or_die(new_branch_info->commit); - *source_tree = new_branch_info->commit->maybe_tree; + *source_tree = get_commit_tree(new_branch_info->commit); } if (!*source_tree) /* case (1): want a tree */ diff --git a/builtin/diff.c b/builtin/diff.c index 34f18a5f3f5c89..bfefff3a84896a 100644 --- a/builtin/diff.c +++ b/builtin/diff.c @@ -398,7 +398,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix) if (!obj) die(_("invalid object '%s' given."), name); if (obj->type == OBJ_COMMIT) - obj = &((struct commit *)obj)->maybe_tree->object; + obj = &get_commit_tree(((struct commit *)obj))->object; if (obj->type == OBJ_TREE) { obj->flags |= flags; diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 91e526b30d2830..c1304234cd6feb 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -578,11 +578,11 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, get_object_mark(&commit->parents->item->object) != 0 && !full_tree) { parse_commit_or_die(commit->parents->item); - diff_tree_oid(&commit->parents->item->maybe_tree->object.oid, - &commit->maybe_tree->object.oid, "", &rev->diffopt); + diff_tree_oid(get_commit_tree_oid(commit->parents->item), + get_commit_tree_oid(commit), "", &rev->diffopt); } else - diff_root_tree_oid(&commit->maybe_tree->object.oid, + diff_root_tree_oid(get_commit_tree_oid(commit), "", &rev->diffopt); /* Export the referenced blobs, and remember the marks. */ diff --git a/builtin/log.c b/builtin/log.c index a1fbc608bc2424..f4d30d2f3da84f 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -1064,8 +1064,8 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout, diff_setup_done(&opts); - diff_tree_oid(&origin->maybe_tree->object.oid, - &head->maybe_tree->object.oid, + diff_tree_oid(get_commit_tree_oid(origin), + get_commit_tree_oid(head), "", &opts); diffcore_std(&opts); diff_flush(&opts); diff --git a/builtin/reflog.c b/builtin/reflog.c index 29d80a35a13198..1ce4276d313feb 100644 --- a/builtin/reflog.c +++ b/builtin/reflog.c @@ -153,7 +153,7 @@ static int commit_is_complete(struct commit *commit) for (i = 0; i < found.nr; i++) { struct commit *c = (struct commit *)found.objects[i].item; - if (!tree_is_complete(&c->maybe_tree->object.oid)) { + if (!tree_is_complete(get_commit_tree_oid(c))) { is_incomplete = 1; c->object.flags |= INCOMPLETE; } diff --git a/commit-graph.c b/commit-graph.c index 49c622c5569f53..264aa6d919bc3d 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -369,7 +369,7 @@ static void write_graph_chunk_data(struct hashfile *f, int hash_len, uint32_t packedDate[2]; parse_commit(*list); - hashwrite(f, (*list)->maybe_tree->object.oid.hash, hash_len); + hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len); parent = (*list)->parents; diff --git a/contrib/coccinelle/commit.cocci b/contrib/coccinelle/commit.cocci new file mode 100644 index 00000000000000..ac38525941fef9 --- /dev/null +++ b/contrib/coccinelle/commit.cocci @@ -0,0 +1,30 @@ +@@ +expression c; +@@ +- &c->maybe_tree->object.oid ++ get_commit_tree_oid(c) + +@@ +expression c; +@@ +- c->maybe_tree->object.oid.hash ++ get_commit_tree_oid(c)->hash + +@@ +expression c; +@@ +- c->maybe_tree ++ get_commit_tree(c) + +@@ +expression c; +expression s; +@@ +- get_commit_tree(c) = s ++ c->maybe_tree = s + +@@ +expression c; +@@ +- return get_commit_tree(c); ++ return c->maybe_tree; diff --git a/fsck.c b/fsck.c index 3228ca5beeaed5..695fd71b137719 100644 --- a/fsck.c +++ b/fsck.c @@ -396,9 +396,11 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio name = get_object_name(options, &commit->object); if (name) - put_object_name(options, &commit->maybe_tree->object, "%s:", name); + put_object_name(options, &get_commit_tree(commit)->object, + "%s:", name); - result = options->walk((struct object *)commit->maybe_tree, OBJ_TREE, data, options); + result = options->walk((struct object *)get_commit_tree(commit), + OBJ_TREE, data, options); if (result < 0) return result; res = result; @@ -772,7 +774,7 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer, err = fsck_ident(&buffer, &commit->object, options); if (err) return err; - if (!commit->maybe_tree) { + if (!get_commit_tree(commit)) { err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", sha1_to_hex(tree_sha1)); if (err) return err; diff --git a/http-push.c b/http-push.c index d83479f32f4cfa..53a217291e5d66 100644 --- a/http-push.c +++ b/http-push.c @@ -1330,7 +1330,7 @@ static int get_delta(struct rev_info *revs, struct remote_lock *lock) int count = 0; while ((commit = get_revision(revs)) != NULL) { - p = process_tree(commit->maybe_tree, p); + p = process_tree(get_commit_tree(commit), p); commit->object.flags |= LOCAL; if (!(commit->object.flags & UNINTERESTING)) count += add_send_request(&commit->object, lock); diff --git a/line-log.c b/line-log.c index e714969ca22e86..437d44c00ae0b9 100644 --- a/line-log.c +++ b/line-log.c @@ -817,8 +817,8 @@ static void queue_diffs(struct line_log_data *range, assert(commit); DIFF_QUEUE_CLEAR(&diff_queued_diff); - diff_tree_oid(parent ? &parent->maybe_tree->object.oid : NULL, - &commit->maybe_tree->object.oid, "", opt); + diff_tree_oid(parent ? get_commit_tree_oid(parent) : NULL, + get_commit_tree_oid(commit), "", opt); if (opt->detect_rename) { filter_diffs_for_paths(range, 1); if (diff_might_be_rename()) diff --git a/list-objects.c b/list-objects.c index bfd09f545c971e..3eec510357337f 100644 --- a/list-objects.c +++ b/list-objects.c @@ -195,7 +195,7 @@ static void mark_edge_parents_uninteresting(struct commit *commit, struct commit *parent = parents->item; if (!(parent->object.flags & UNINTERESTING)) continue; - mark_tree_uninteresting(parent->maybe_tree); + mark_tree_uninteresting(get_commit_tree(parent)); if (revs->edge_hint && !(parent->object.flags & SHOWN)) { parent->object.flags |= SHOWN; show_edge(parent); @@ -212,7 +212,7 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge) struct commit *commit = list->item; if (commit->object.flags & UNINTERESTING) { - mark_tree_uninteresting(commit->maybe_tree); + mark_tree_uninteresting(get_commit_tree(commit)); if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) { commit->object.flags |= SHOWN; show_edge(commit); @@ -227,7 +227,7 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge) struct commit *commit = (struct commit *)obj; if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING)) continue; - mark_tree_uninteresting(commit->maybe_tree); + mark_tree_uninteresting(get_commit_tree(commit)); if (!(obj->flags & SHOWN)) { obj->flags |= SHOWN; show_edge(commit); @@ -300,8 +300,8 @@ static void do_traverse(struct rev_info *revs, * an uninteresting boundary commit may not have its tree * parsed yet, but we are not going to show them anyway */ - if (commit->maybe_tree) - add_pending_tree(revs, commit->maybe_tree); + if (get_commit_tree(commit)) + add_pending_tree(revs, get_commit_tree(commit)); show_commit(commit, show_data); if (revs->tree_blobs_in_commit_order) diff --git a/log-tree.c b/log-tree.c index 99499af57c102f..c106bd70df60e5 100644 --- a/log-tree.c +++ b/log-tree.c @@ -806,7 +806,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log return 0; parse_commit_or_die(commit); - oid = &commit->maybe_tree->object.oid; + oid = get_commit_tree_oid(commit); /* Root commit? */ parents = get_saved_parents(opt, commit); @@ -831,7 +831,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log * we merged _in_. */ parse_commit_or_die(parents->item); - diff_tree_oid(&parents->item->maybe_tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parents->item), oid, "", &opt->diffopt); log_tree_diff_flush(opt); return !opt->loginfo; @@ -846,7 +846,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log struct commit *parent = parents->item; parse_commit_or_die(parent); - diff_tree_oid(&parent->maybe_tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), oid, "", &opt->diffopt); log_tree_diff_flush(opt); diff --git a/merge-recursive.c b/merge-recursive.c index 0f75d75d1788ae..8de6e365273386 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -2154,8 +2154,8 @@ int merge_recursive(struct merge_options *o, read_cache(); o->ancestor = "merged common ancestors"; - clean = merge_trees(o, h1->maybe_tree, h2->maybe_tree, - merged_common_ancestors->maybe_tree, + clean = merge_trees(o, get_commit_tree(h1), get_commit_tree(h2), + get_commit_tree(merged_common_ancestors), &mrtree); if (clean < 0) { flush_output(o); diff --git a/notes-merge.c b/notes-merge.c index 1d3edc89425d99..4a73a2169be49d 100644 --- a/notes-merge.c +++ b/notes-merge.c @@ -600,14 +600,14 @@ int notes_merge(struct notes_merge_options *o, printf("No merge base found; doing history-less merge\n"); } else if (!bases->next) { base_oid = &bases->item->object.oid; - base_tree_oid = &bases->item->maybe_tree->object.oid; + base_tree_oid = get_commit_tree_oid(bases->item); if (o->verbosity >= 4) printf("One merge base found (%.7s)\n", oid_to_hex(base_oid)); } else { /* TODO: How to handle multiple merge-bases? */ base_oid = &bases->item->object.oid; - base_tree_oid = &bases->item->maybe_tree->object.oid; + base_tree_oid = get_commit_tree_oid(bases->item); if (o->verbosity >= 3) printf("Multiple merge bases found. Using the first " "(%.7s)\n", oid_to_hex(base_oid)); @@ -634,8 +634,9 @@ int notes_merge(struct notes_merge_options *o, goto found_result; } - result = merge_from_diffs(o, base_tree_oid, &local->maybe_tree->object.oid, - &remote->maybe_tree->object.oid, local_tree); + result = merge_from_diffs(o, base_tree_oid, + get_commit_tree_oid(local), + get_commit_tree_oid(remote), local_tree); if (result != 0) { /* non-trivial merge (with or without conflicts) */ /* Commit (partial) result */ diff --git a/packfile.c b/packfile.c index 3eb9c4a36e66fa..88ba8191518711 100644 --- a/packfile.c +++ b/packfile.c @@ -1925,7 +1925,7 @@ static int add_promisor_object(const struct object_id *oid, struct commit *commit = (struct commit *) obj; struct commit_list *parents = commit->parents; - oidset_insert(set, &commit->maybe_tree->object.oid); + oidset_insert(set, get_commit_tree_oid(commit)); for (; parents; parents = parents->next) oidset_insert(set, &parents->item->object.oid); } else if (obj->type == OBJ_TAG) { diff --git a/pretty.c b/pretty.c index 42095ea495a641..15997f5e0186c0 100644 --- a/pretty.c +++ b/pretty.c @@ -1161,10 +1161,11 @@ static size_t format_commit_one(struct strbuf *sb, /* in UTF-8 */ strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_RESET)); return 1; case 'T': /* tree hash */ - strbuf_addstr(sb, oid_to_hex(&commit->maybe_tree->object.oid)); + strbuf_addstr(sb, oid_to_hex(get_commit_tree_oid(commit))); return 1; case 't': /* abbreviated tree hash */ - strbuf_add_unique_abbrev(sb, commit->maybe_tree->object.oid.hash, + strbuf_add_unique_abbrev(sb, + get_commit_tree_oid(commit)->hash, c->pretty_ctx->abbrev); return 1; case 'P': /* parent hashes */ diff --git a/ref-filter.c b/ref-filter.c index a59654cfd372db..cffd8bf3ce72ab 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -815,7 +815,7 @@ static void grab_commit_values(struct atom_value *val, int deref, struct object if (deref) name++; if (!strcmp(name, "tree")) { - v->s = xstrdup(oid_to_hex(&commit->maybe_tree->object.oid)); + v->s = xstrdup(oid_to_hex(get_commit_tree_oid(commit))); } else if (!strcmp(name, "numparent")) { v->value = commit_list_count(commit->parents); diff --git a/revision.c b/revision.c index f61d1c930789b3..d64d2a859e9750 100644 --- a/revision.c +++ b/revision.c @@ -439,8 +439,8 @@ static void file_change(struct diff_options *options, static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct commit *commit) { - struct tree *t1 = parent->maybe_tree; - struct tree *t2 = commit->maybe_tree; + struct tree *t1 = get_commit_tree(parent); + struct tree *t2 = get_commit_tree(commit); if (!t1) return REV_TREE_NEW; @@ -476,7 +476,7 @@ static int rev_compare_tree(struct rev_info *revs, static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit) { int retval; - struct tree *t1 = commit->maybe_tree; + struct tree *t1 = get_commit_tree(commit); if (!t1) return 0; @@ -614,7 +614,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) if (!revs->prune) return; - if (!commit->maybe_tree) + if (!get_commit_tree(commit)) return; if (!commit->parents) { diff --git a/sequencer.c b/sequencer.c index 9269607a485eae..abebf6988fe7ec 100644 --- a/sequencer.c +++ b/sequencer.c @@ -501,8 +501,8 @@ static int do_recursive_merge(struct commit *base, struct commit *next, o.show_rename_progress = 1; head_tree = parse_tree_indirect(head); - next_tree = next ? next->maybe_tree : empty_tree(); - base_tree = base ? base->maybe_tree : empty_tree(); + next_tree = next ? get_commit_tree(next) : empty_tree(); + base_tree = base ? get_commit_tree(base) : empty_tree(); for (xopt = opts->xopts; xopt != opts->xopts + opts->xopts_nr; xopt++) parse_merge_opt(&o, *xopt); @@ -562,7 +562,7 @@ static int is_index_unchanged(void) return error(_("unable to update cache tree")); return !oidcmp(&active_cache_tree->oid, - &head_commit->maybe_tree->object.oid); + get_commit_tree_oid(head_commit)); } static int write_author_script(const char *message) @@ -1119,7 +1119,7 @@ static int try_to_commit(struct strbuf *msg, const char *author, } if (!(flags & ALLOW_EMPTY) && !oidcmp(current_head ? - ¤t_head->maybe_tree->object.oid : + get_commit_tree_oid(current_head) : &empty_tree_oid, &tree)) { res = 1; /* run 'git commit' to display error message */ goto out; @@ -1217,12 +1217,12 @@ static int is_original_commit_empty(struct commit *commit) if (parse_commit(parent)) return error(_("could not parse parent commit %s"), oid_to_hex(&parent->object.oid)); - ptree_oid = &parent->maybe_tree->object.oid; + ptree_oid = get_commit_tree_oid(parent); } else { ptree_oid = the_hash_algo->empty_tree; /* commit is root */ } - return !oidcmp(ptree_oid, &commit->maybe_tree->object.oid); + return !oidcmp(ptree_oid, get_commit_tree_oid(commit)); } /* diff --git a/sha1_name.c b/sha1_name.c index 6ca2a2de37e2ad..c9dead6b80f4e7 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -896,7 +896,7 @@ struct object *peel_to_type(const char *name, int namelen, if (o->type == OBJ_TAG) o = ((struct tag*) o)->tagged; else if (o->type == OBJ_COMMIT) - o = &(((struct commit *) o)->maybe_tree->object); + o = &(get_commit_tree(((struct commit *)o))->object); else { if (name) error("%.*s: expected %s type, but the object " diff --git a/tree.c b/tree.c index dbc5e0be544ef1..dec53f3ecae066 100644 --- a/tree.c +++ b/tree.c @@ -109,7 +109,7 @@ static int read_tree_1(struct tree *tree, struct strbuf *base, oid_to_hex(entry.oid), base->buf, entry.path); - oidcpy(&oid, &commit->maybe_tree->object.oid); + oidcpy(&oid, get_commit_tree_oid(commit)); } else continue; @@ -248,7 +248,7 @@ struct tree *parse_tree_indirect(const struct object_id *oid) if (obj->type == OBJ_TREE) return (struct tree *) obj; else if (obj->type == OBJ_COMMIT) - obj = &(((struct commit *) obj)->maybe_tree->object); + obj = &(get_commit_tree(((struct commit *)obj))->object); else if (obj->type == OBJ_TAG) obj = ((struct tag *) obj)->tagged; else diff --git a/walker.c b/walker.c index 1d5f3059a29841..f51b8558723354 100644 --- a/walker.c +++ b/walker.c @@ -87,7 +87,7 @@ static int process_commit(struct walker *walker, struct commit *commit) walker_say(walker, "walk %s\n", oid_to_hex(&commit->object.oid)); if (walker->get_tree) { - if (process(walker, &commit->maybe_tree->object)) + if (process(walker, &get_commit_tree(commit)->object)) return -1; if (!walker->get_all) walker->get_tree = 0; From 7b8a21dba1bce44d64bd86427d3d92437adc4707 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Fri, 6 Apr 2018 19:09:46 +0000 Subject: [PATCH 18/18] commit-graph: lazy-load trees for commits The commit-graph file provides quick access to commit data, including the OID of the root tree for each commit in the graph. When performing a deep commit-graph walk, we may not need to load most of the trees for these commits. Delay loading the tree object for a commit loaded from the graph until requested via get_commit_tree(). Do not lazy-load trees for commits not in the graph, since that requires duplicate parsing and the relative peformance improvement when trees are not needed is small. On the Linux repository, performance tests were run for the following command: git log --graph --oneline -1000 Before: 0.92s After: 0.66s Rel %: -28.3% Adding '-- kernel/' to the command requires loading the root tree for every commit that is walked. There was no measureable performance change as a result of this patch. Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- commit-graph.c | 26 +++++++++++++++++++++++--- commit-graph.h | 2 ++ commit.c | 8 +++++++- commit.h | 6 ++++++ 4 files changed, 38 insertions(+), 4 deletions(-) diff --git a/commit-graph.c b/commit-graph.c index 264aa6d919bc3d..70fa1b25fd3d07 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -247,7 +247,6 @@ static struct commit_list **insert_parent_or_die(struct commit_graph *g, static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t pos) { - struct object_id oid; uint32_t edge_value; uint32_t *parent_data_ptr; uint64_t date_low, date_high; @@ -257,8 +256,7 @@ static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uin item->object.parsed = 1; item->graph_pos = pos; - hashcpy(oid.hash, commit_data); - item->maybe_tree = lookup_tree(&oid); + item->maybe_tree = NULL; date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; date_low = get_be32(commit_data + g->hash_len + 12); @@ -317,6 +315,28 @@ int parse_commit_in_graph(struct commit *item) return 0; } +static struct tree *load_tree_for_commit(struct commit_graph *g, struct commit *c) +{ + struct object_id oid; + const unsigned char *commit_data = g->chunk_commit_data + + GRAPH_DATA_WIDTH * (c->graph_pos); + + hashcpy(oid.hash, commit_data); + c->maybe_tree = lookup_tree(&oid); + + return c->maybe_tree; +} + +struct tree *get_commit_tree_in_graph(const struct commit *c) +{ + if (c->maybe_tree) + return c->maybe_tree; + if (c->graph_pos == COMMIT_NOT_FROM_GRAPH) + BUG("get_commit_tree_in_graph called from non-commit-graph commit"); + + return load_tree_for_commit(commit_graph, (struct commit *)c); +} + static void write_graph_chunk_fanout(struct hashfile *f, struct commit **commits, int nr_commits) diff --git a/commit-graph.h b/commit-graph.h index e1d8580c98a24a..260a468e73acd8 100644 --- a/commit-graph.h +++ b/commit-graph.h @@ -17,6 +17,8 @@ char *get_commit_graph_filename(const char *obj_dir); */ int parse_commit_in_graph(struct commit *item); +struct tree *get_commit_tree_in_graph(const struct commit *c); + struct commit_graph { int graph_fd; diff --git a/commit.c b/commit.c index aea2ca1f8ba307..711f674c18d00c 100644 --- a/commit.c +++ b/commit.c @@ -298,7 +298,13 @@ void free_commit_buffer(struct commit *commit) struct tree *get_commit_tree(const struct commit *commit) { - return commit->maybe_tree; + if (commit->maybe_tree || !commit->object.parsed) + return commit->maybe_tree; + + if (commit->graph_pos == COMMIT_NOT_FROM_GRAPH) + BUG("commit has NULL tree, but was not loaded from commit-graph"); + + return get_commit_tree_in_graph(commit); } struct object_id *get_commit_tree_oid(const struct commit *commit) diff --git a/commit.h b/commit.h index dc4bf97d9f3b74..23a3f364edec6b 100644 --- a/commit.h +++ b/commit.h @@ -22,6 +22,12 @@ struct commit { unsigned int index; timestamp_t date; struct commit_list *parents; + + /* + * If the commit is loaded from the commit-graph file, then this + * member may be NULL. Only access it through get_commit_tree() + * or get_commit_tree_oid(). + */ struct tree *maybe_tree; uint32_t graph_pos; };