From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: me@ttaylorr.com, gitster@pobox.com, l.s.r@web.de,
szeder.dev@gmail.com, Chris Torek <chris.torek@gmail.com>,
Derrick Stolee <stolee@gmail.com>,
Derrick Stolee <derrickstolee@github.com>,
Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v2 13/17] commit-graph: use chunk-format read API
Date: Wed, 27 Jan 2021 15:01:52 +0000 [thread overview]
Message-ID: <8744d2785965773a2b561e9e1e91170530d052b1.1611759716.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.848.v2.git.1611759716.gitgitgadget@gmail.com>
From: Derrick Stolee <dstolee@microsoft.com>
Instead of parsing the table of contents directly, use the chunk-format
API methods read_table_of_contents() and pair_chunk(). While the current
implementation loses the duplicate-chunk detection, that will be added
in a future change.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
commit-graph.c | 154 ++++++++++++++--------------------------
t/t5318-commit-graph.sh | 2 +-
2 files changed, 53 insertions(+), 103 deletions(-)
diff --git a/commit-graph.c b/commit-graph.c
index ba33777dcb8..8aa4881d85d 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -299,15 +299,43 @@ static int verify_commit_graph_lite(struct commit_graph *g)
return 0;
}
+static int graph_read_oid_lookup(const unsigned char *chunk_start,
+ size_t chunk_size, void *data)
+{
+ struct commit_graph *g = data;
+ g->chunk_oid_lookup = chunk_start;
+ g->num_commits = chunk_size / g->hash_len;
+ return 0;
+}
+
+static int graph_read_bloom_data(const unsigned char *chunk_start,
+ size_t chunk_size, void *data)
+{
+ struct commit_graph *g = data;
+ uint32_t hash_version;
+ g->chunk_bloom_data = chunk_start;
+ hash_version = get_be32(chunk_start);
+
+ if (hash_version != 1)
+ return 0;
+
+ g->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings));
+ g->bloom_filter_settings->hash_version = hash_version;
+ g->bloom_filter_settings->num_hashes = get_be32(chunk_start + 4);
+ g->bloom_filter_settings->bits_per_entry = get_be32(chunk_start + 8);
+ g->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES;
+
+ return 0;
+}
+
struct commit_graph *parse_commit_graph(struct repository *r,
void *graph_map, size_t graph_size)
{
- const unsigned char *data, *chunk_lookup;
- uint32_t i;
+ const unsigned char *data;
struct commit_graph *graph;
- uint64_t next_chunk_offset;
uint32_t graph_signature;
unsigned char graph_version, hash_version;
+ struct chunkfile *cf = NULL;
if (!graph_map)
return NULL;
@@ -356,108 +384,28 @@ struct commit_graph *parse_commit_graph(struct repository *r,
return NULL;
}
- chunk_lookup = data + 8;
- next_chunk_offset = get_be64(chunk_lookup + 4);
- for (i = 0; i < graph->num_chunks; i++) {
- uint32_t chunk_id;
- uint64_t chunk_offset = next_chunk_offset;
- int chunk_repeated = 0;
-
- chunk_id = get_be32(chunk_lookup + 0);
-
- chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH;
- next_chunk_offset = get_be64(chunk_lookup + 4);
-
- if (chunk_offset > graph_size - the_hash_algo->rawsz) {
- error(_("commit-graph improper chunk offset %08x%08x"), (uint32_t)(chunk_offset >> 32),
- (uint32_t)chunk_offset);
- goto free_and_return;
- }
-
- 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;
- graph->num_commits = (next_chunk_offset - chunk_offset)
- / graph->hash_len;
- }
- break;
+ cf = init_chunkfile(NULL);
- case GRAPH_CHUNKID_DATA:
- if (graph->chunk_commit_data)
- chunk_repeated = 1;
- else
- graph->chunk_commit_data = data + chunk_offset;
- break;
-
- case GRAPH_CHUNKID_GENERATION_DATA:
- if (graph->chunk_generation_data)
- chunk_repeated = 1;
- else
- graph->chunk_generation_data = data + chunk_offset;
- break;
-
- case GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW:
- if (graph->chunk_generation_data_overflow)
- chunk_repeated = 1;
- else
- graph->chunk_generation_data_overflow = data + chunk_offset;
- break;
-
- case GRAPH_CHUNKID_EXTRAEDGES:
- if (graph->chunk_extra_edges)
- chunk_repeated = 1;
- else
- graph->chunk_extra_edges = data + chunk_offset;
- break;
-
- case GRAPH_CHUNKID_BASE:
- if (graph->chunk_base_graphs)
- chunk_repeated = 1;
- else
- graph->chunk_base_graphs = data + chunk_offset;
- break;
-
- case GRAPH_CHUNKID_BLOOMINDEXES:
- if (graph->chunk_bloom_indexes)
- chunk_repeated = 1;
- else if (r->settings.commit_graph_read_changed_paths)
- graph->chunk_bloom_indexes = data + chunk_offset;
- break;
-
- case GRAPH_CHUNKID_BLOOMDATA:
- if (graph->chunk_bloom_data)
- chunk_repeated = 1;
- else if (r->settings.commit_graph_read_changed_paths) {
- uint32_t hash_version;
- graph->chunk_bloom_data = data + chunk_offset;
- hash_version = get_be32(data + chunk_offset);
-
- if (hash_version != 1)
- break;
+ if (read_table_of_contents(cf, graph->data, graph_size,
+ GRAPH_HEADER_SIZE, graph->num_chunks))
+ goto free_and_return;
- graph->bloom_filter_settings = xmalloc(sizeof(struct bloom_filter_settings));
- graph->bloom_filter_settings->hash_version = hash_version;
- graph->bloom_filter_settings->num_hashes = get_be32(data + chunk_offset + 4);
- graph->bloom_filter_settings->bits_per_entry = get_be32(data + chunk_offset + 8);
- graph->bloom_filter_settings->max_changed_paths = DEFAULT_BLOOM_MAX_CHANGES;
- }
- break;
- }
+ pair_chunk(cf, GRAPH_CHUNKID_OIDFANOUT,
+ (const unsigned char **)&graph->chunk_oid_fanout);
+ read_chunk(cf, GRAPH_CHUNKID_OIDLOOKUP, graph_read_oid_lookup, graph);
+ pair_chunk(cf, GRAPH_CHUNKID_DATA, &graph->chunk_commit_data);
+ pair_chunk(cf, GRAPH_CHUNKID_EXTRAEDGES, &graph->chunk_extra_edges);
+ pair_chunk(cf, GRAPH_CHUNKID_BASE, &graph->chunk_base_graphs);
+ pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA,
+ &graph->chunk_generation_data);
+ pair_chunk(cf, GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW,
+ &graph->chunk_generation_data_overflow);
- if (chunk_repeated) {
- error(_("commit-graph chunk id %08x appears multiple times"), chunk_id);
- goto free_and_return;
- }
+ if (r->settings.commit_graph_read_changed_paths) {
+ pair_chunk(cf, GRAPH_CHUNKID_BLOOMINDEXES,
+ &graph->chunk_bloom_indexes);
+ read_chunk(cf, GRAPH_CHUNKID_BLOOMDATA,
+ graph_read_bloom_data, graph);
}
if (graph->chunk_bloom_indexes && graph->chunk_bloom_data) {
@@ -474,9 +422,11 @@ struct commit_graph *parse_commit_graph(struct repository *r,
if (verify_commit_graph_lite(graph))
goto free_and_return;
+ free_chunkfile(cf);
return graph;
free_and_return:
+ free_chunkfile(cf);
free(graph->bloom_filter_settings);
free(graph);
return NULL;
diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
index fa27df579a5..c7da741284e 100755
--- a/t/t5318-commit-graph.sh
+++ b/t/t5318-commit-graph.sh
@@ -564,7 +564,7 @@ test_expect_success 'detect bad hash version' '
test_expect_success 'detect low chunk count' '
corrupt_graph_and_verify $GRAPH_BYTE_CHUNK_COUNT "\01" \
- "missing the .* chunk"
+ "final chunk has non-zero id"
'
test_expect_success 'detect missing OID fanout chunk' '
--
gitgitgadget
next prev parent reply other threads:[~2021-01-27 15:36 UTC|newest]
Thread overview: 120+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-26 16:01 [PATCH 00/17] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-01-27 1:53 ` Chris Torek
2021-01-27 2:36 ` Taylor Blau
2021-01-26 16:01 ` [PATCH 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-01-27 2:42 ` Taylor Blau
2021-01-27 13:49 ` Derrick Stolee
2021-01-26 16:01 ` [PATCH 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-01-27 2:47 ` Taylor Blau
2021-01-26 16:01 ` [PATCH 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 2:49 ` Taylor Blau
2021-01-26 16:01 ` [PATCH 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-01-27 3:02 ` Taylor Blau
2021-01-26 16:01 ` [PATCH 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 14/17] midx: " Derrick Stolee via GitGitGadget
2021-01-27 3:06 ` Taylor Blau
2021-01-27 13:50 ` Derrick Stolee
2021-01-26 16:01 ` [PATCH 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-01-26 22:37 ` [PATCH 00/17] Refactor chunk-format into an API Junio C Hamano
2021-01-27 2:29 ` Taylor Blau
2021-01-27 15:01 ` [PATCH v2 " Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-04 21:24 ` Junio C Hamano
2021-02-04 22:40 ` Junio C Hamano
2021-02-05 11:37 ` Derrick Stolee
2021-02-05 19:25 ` Junio C Hamano
2021-01-27 15:01 ` [PATCH v2 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-04 22:59 ` Junio C Hamano
2021-02-05 11:42 ` Derrick Stolee
2021-01-27 15:01 ` [PATCH v2 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-04 23:40 ` Junio C Hamano
2021-02-05 12:19 ` Derrick Stolee
2021-02-05 19:37 ` Junio C Hamano
2021-02-08 22:26 ` Junio C Hamano
2021-02-09 1:33 ` Derrick Stolee
2021-02-09 20:47 ` Junio C Hamano
2021-01-27 15:01 ` Derrick Stolee via GitGitGadget [this message]
2021-01-27 15:01 ` [PATCH v2 14/17] midx: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-05 0:00 ` Junio C Hamano
2021-02-05 10:59 ` Chris Torek
2021-02-05 20:41 ` Junio C Hamano
2021-02-06 20:35 ` Chris Torek
2021-02-05 12:30 ` Derrick Stolee
2021-02-05 19:42 ` Junio C Hamano
2021-02-07 19:50 ` SZEDER Gábor
2021-02-08 5:41 ` Junio C Hamano
2021-01-27 15:01 ` [PATCH v2 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-05 0:05 ` Junio C Hamano
2021-02-05 12:31 ` Derrick Stolee
2021-01-27 15:01 ` [PATCH v2 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-05 0:15 ` Junio C Hamano
2021-01-27 16:03 ` [PATCH v2 00/17] Refactor chunk-format into an API Taylor Blau
2021-02-05 2:08 ` Junio C Hamano
2021-02-05 2:27 ` Derrick Stolee
2021-02-05 14:30 ` [PATCH v3 " Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-07 21:13 ` SZEDER Gábor
2021-02-08 13:44 ` Derrick Stolee
2021-02-11 19:43 ` SZEDER Gábor
2021-02-05 14:30 ` [PATCH v3 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-07 20:20 ` SZEDER Gábor
2021-02-08 13:35 ` Derrick Stolee
2021-02-05 14:30 ` [PATCH v3 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 14/17] midx: " Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-05 14:30 ` [PATCH v3 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 00/17] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-02-24 16:52 ` SZEDER Gábor
2021-02-24 17:12 ` Taylor Blau
2021-02-24 17:52 ` Derrick Stolee
2021-02-24 19:44 ` Junio C Hamano
2021-02-18 14:07 ` [PATCH v4 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 14/17] midx: " Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-18 14:07 ` [PATCH v4 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-18 21:47 ` Junio C Hamano
2021-02-19 12:42 ` Derrick Stolee
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=8744d2785965773a2b561e9e1e91170530d052b1.1611759716.git.gitgitgadget@gmail.com \
--to=gitgitgadget@gmail.com \
--cc=chris.torek@gmail.com \
--cc=derrickstolee@github.com \
--cc=dstolee@microsoft.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=l.s.r@web.de \
--cc=me@ttaylorr.com \
--cc=stolee@gmail.com \
--cc=szeder.dev@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).