From: "SZEDER Gábor" <szeder.dev@gmail.com>
To: git@vger.kernel.org
Cc: "Junio C Hamano" <gitster@pobox.com>,
"Garima Singh" <garima.singh@microsoft.com>,
"Derrick Stolee" <stolee@gmail.com>,
"Jakub Narebski" <jnareb@gmail.com>, "Jeff King" <peff@peff.net>,
"Taylor Blau" <me@ttaylorr.com>,
"SZEDER Gábor" <szeder.dev@gmail.com>
Subject: [PATCH 11/34] commit-graph: allocate the 'struct chunk_info' array dinamically
Date: Fri, 29 May 2020 10:50:15 +0200 [thread overview]
Message-ID: <20200529085038.26008-12-szeder.dev@gmail.com> (raw)
In-Reply-To: <20200529085038.26008-1-szeder.dev@gmail.com>
During writing a new commit-graph file, the size of the 'struct
chunk_info' array is hardcoded to be the maximum number of possible
chunks plus one for the terminating label. This array size must be
adjusted each time when a new chunk is added, which can be easily
forgotten.
So let's make the constant-sized 'struct chunk_info' array an
ALLOC_GROW()-able array instead.
There are a couple of cases where writing a new commit-graph file
returns with error; those spots were adjusted to free the dinamically
allocated 'struct chunk_info' array.
Arguably the several ALLOC_GROW() call sites look unusal, because we
usually call ALLOC_GROW() in loops, once in each iteration...
However, this way anyone who adds a new chunk will notice that they
have to cargo-cult the ALLOC_GROW() call as well.
Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com>
---
commit-graph.c | 74 ++++++++++++++++++++++++++++++++------------------
1 file changed, 47 insertions(+), 27 deletions(-)
diff --git a/commit-graph.c b/commit-graph.c
index d95c739c10..c8ba17e457 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1355,12 +1355,13 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
int fd;
struct hashfile *f;
struct lock_file lk = LOCK_INIT;
- struct chunk_info chunks[6];
+ struct chunk_info *chunks = NULL;
+ int chunks_nr = 0, chunks_alloc = 0;
const unsigned hashsz = the_hash_algo->rawsz;
struct strbuf progress_title = STRBUF_INIT;
- int num_chunks = 3;
uint64_t chunk_offset;
struct object_id file_hash;
+ int ret = 0;
if (ctx->split) {
struct strbuf tmp_file = STRBUF_INIT;
@@ -1398,35 +1399,48 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
}
- chunks[0].id = GRAPH_CHUNKID_OIDFANOUT;
- chunks[0].size = GRAPH_FANOUT_SIZE;
- chunks[1].id = GRAPH_CHUNKID_OIDLOOKUP;
- chunks[1].size = hashsz * ctx->commits.nr;
- chunks[2].id = GRAPH_CHUNKID_DATA;
- chunks[2].size = (hashsz + 16) * ctx->commits.nr;
+ ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+ chunks[chunks_nr].id = GRAPH_CHUNKID_OIDFANOUT;
+ chunks[chunks_nr].size = GRAPH_FANOUT_SIZE;
+ chunks_nr++;
+ ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+ chunks[chunks_nr].id = GRAPH_CHUNKID_OIDLOOKUP;
+ chunks[chunks_nr].size = hashsz * ctx->commits.nr;
+ chunks_nr++;
+ ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+ chunks[chunks_nr].id = GRAPH_CHUNKID_DATA;
+ chunks[chunks_nr].size = (hashsz + 16) * ctx->commits.nr;
+ chunks_nr++;
if (ctx->num_extra_edges) {
- chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES;
- chunks[num_chunks].size = 4 * ctx->num_extra_edges;
- num_chunks++;
+ ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+ chunks[chunks_nr].id = GRAPH_CHUNKID_EXTRAEDGES;
+ chunks[chunks_nr].size = 4 * ctx->num_extra_edges;
+ chunks_nr++;
}
if (ctx->num_commit_graphs_after > 1) {
- chunks[num_chunks].id = GRAPH_CHUNKID_BASE;
- chunks[num_chunks].size = hashsz * (ctx->num_commit_graphs_after - 1);
- num_chunks++;
+ ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+ chunks[chunks_nr].id = GRAPH_CHUNKID_BASE;
+ chunks[chunks_nr].size = hashsz * (ctx->num_commit_graphs_after - 1);
+ chunks_nr++;
}
- chunks[num_chunks].id = 0;
- chunks[num_chunks].size = 0;
+ ALLOC_GROW(chunks, chunks_nr + 1, chunks_alloc);
+ chunks[chunks_nr].id = 0;
+ chunks[chunks_nr].size = 0;
+ /*
+ * Do not increase 'chunks_nr', so it still reflects the number of
+ * actual chunks, without the Chunk Lookup table's terminating label.
+ */
hashwrite_be32(f, GRAPH_SIGNATURE);
hashwrite_u8(f, GRAPH_VERSION);
hashwrite_u8(f, oid_version());
- hashwrite_u8(f, num_chunks);
+ hashwrite_u8(f, chunks_nr);
hashwrite_u8(f, ctx->num_commit_graphs_after - 1);
- chunk_offset = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
- for (i = 0; i <= num_chunks; i++) {
+ chunk_offset = 8 + (chunks_nr + 1) * GRAPH_CHUNKLOOKUP_WIDTH;
+ for (i = 0; i <= chunks_nr; i++) {
uint32_t chunk_write[3];
chunk_write[0] = htonl(chunks[i].id);
@@ -1441,11 +1455,11 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
strbuf_addf(&progress_title,
Q_("Writing out commit graph in %d pass",
"Writing out commit graph in %d passes",
- num_chunks),
- num_chunks);
+ chunks_nr),
+ chunks_nr);
ctx->progress = start_delayed_progress(
progress_title.buf,
- num_chunks * ctx->commits.nr);
+ chunks_nr * ctx->commits.nr);
}
write_graph_chunk_fanout(f, ctx);
write_graph_chunk_oids(f, hashsz, ctx);
@@ -1454,7 +1468,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
write_graph_chunk_extra_edges(f, ctx);
if (ctx->num_commit_graphs_after > 1 &&
write_graph_chunk_base(f, ctx)) {
- return -1;
+ ret = -1;
+ goto cleanup;
}
stop_progress(&ctx->progress);
strbuf_release(&progress_title);
@@ -1481,7 +1496,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
if (!chainf) {
error(_("unable to open commit-graph chain file"));
- return -1;
+ ret = -1;
+ goto cleanup;
}
if (ctx->base_graph_name) {
@@ -1493,7 +1509,8 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
if (result) {
error(_("failed to rename base commit-graph file"));
- return -1;
+ ret = -1;
+ goto cleanup;
}
}
} else {
@@ -1513,13 +1530,16 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
if (result) {
error(_("failed to rename temporary commit-graph file"));
- return -1;
+ ret = -1;
+ goto cleanup;
}
}
commit_lock_file(&lk);
- return 0;
+cleanup:
+ free(chunks);
+ return ret;
}
static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
--
2.27.0.rc1.431.g5c813f95dc
next prev parent reply other threads:[~2020-05-29 8:52 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-29 8:50 [PoC PATCH 00/34] An alternative modified path Bloom filters implementation SZEDER Gábor
2020-05-28 22:09 ` Johannes Schindelin
2020-05-29 8:50 ` [PATCH 01/34] tree-walk.c: don't match submodule entries for 'submod/anything' SZEDER Gábor
2020-05-29 8:50 ` [PATCH 02/34] commit-graph: fix parsing the Chunk Lookup table SZEDER Gábor
2020-05-29 8:50 ` [PATCH 03/34] commit-graph-format.txt: all multi-byte numbers are in network byte order SZEDER Gábor
2020-05-29 8:50 ` [PATCH 04/34] commit-slab: add a function to deep free entries on the slab SZEDER Gábor
2020-06-04 16:43 ` Derrick Stolee
2020-06-27 15:56 ` SZEDER Gábor
2020-06-29 11:30 ` Derrick Stolee
2020-05-29 8:50 ` [PATCH 05/34] diff.h: drop diff_tree_oid() & friends' return value SZEDER Gábor
2020-05-29 8:50 ` [PATCH 06/34] commit-graph: clean up #includes SZEDER Gábor
2020-05-29 8:50 ` [PATCH 07/34] commit-graph: simplify parse_commit_graph() #1 SZEDER Gábor
2020-05-29 8:50 ` [PATCH 08/34] commit-graph: simplify parse_commit_graph() #2 SZEDER Gábor
2020-05-29 8:50 ` [PATCH 09/34] commit-graph: simplify write_commit_graph_file() #1 SZEDER Gábor
2020-05-29 8:50 ` [PATCH 10/34] commit-graph: simplify write_commit_graph_file() #2 SZEDER Gábor
2020-05-29 8:50 ` SZEDER Gábor [this message]
2020-05-29 8:50 ` [PATCH 12/34] commit-graph: unify the signatures of all write_graph_chunk_*() functions SZEDER Gábor
2020-05-29 8:50 ` [PATCH 13/34] commit-graph: simplify write_commit_graph_file() #3 SZEDER Gábor
2020-05-29 8:50 ` [PATCH 14/34] commit-graph: check chunk sizes after writing SZEDER Gábor
2020-05-29 8:50 ` [PATCH 15/34] commit-graph-format.txt: document the modified path Bloom filter chunks SZEDER Gábor
2020-06-02 17:59 ` SZEDER Gábor
2020-05-29 8:50 ` [PATCH 16/34] Add a generic and minimal Bloom filter implementation SZEDER Gábor
2020-05-29 8:50 ` [PATCH 17/34] Import a streaming-capable Murmur3 hash function implementation SZEDER Gábor
2020-05-29 8:50 ` [PATCH 18/34] commit-graph: write "empty" Modified Path Bloom Filter Index chunk SZEDER Gábor
2020-05-29 8:50 ` [PATCH 19/34] commit-graph: add commit slab for modified path Bloom filters SZEDER Gábor
2020-05-29 8:50 ` [PATCH 20/34] commit-graph: fill the Modified Path Bloom Filter Index chunk SZEDER Gábor
2020-05-29 8:50 ` [PATCH 21/34] commit-graph: load and use " SZEDER Gábor
2020-05-29 8:50 ` [PATCH 22/34] commit-graph: write the Modified Path Bloom Filters chunk SZEDER Gábor
2020-05-29 8:50 ` [PATCH 23/34] commit-graph: load and use " SZEDER Gábor
2020-05-29 8:50 ` [PATCH 24/34] commit-graph: check all leading directories in modified path Bloom filters SZEDER Gábor
2020-05-29 8:50 ` [PATCH 25/34] commit-graph: check embedded modified path Bloom filters with a mask SZEDER Gábor
2020-05-29 8:50 ` [PATCH 26/34] commit-graph: deduplicate modified path Bloom filters SZEDER Gábor
2020-05-29 8:50 ` [PATCH 27/34] commit-graph: load modified path Bloom filters for merge commits SZEDER Gábor
2020-05-29 8:50 ` [PATCH 28/34] commit-graph: write Modified Path Bloom Filter Merge Index chunk SZEDER Gábor
2020-05-29 8:50 ` [PATCH 29/34] commit-graph: extract init and free write_commit_graph_context SZEDER Gábor
2020-05-29 8:50 ` [PATCH 30/34] commit-graph: move write_commit_graph_reachable below write_commit_graph SZEDER Gábor
2020-05-29 8:50 ` [PATCH 31/34] t7007-show: make the first test compatible with the next patch SZEDER Gábor
2020-05-29 8:50 ` [PATCH 32/34] PoC commit-graph: use revision walk machinery for '--reachable' SZEDER Gábor
2020-05-29 8:50 ` [PATCH 33/34] commit-graph: write modified path Bloom filters in "history order" SZEDER Gábor
2020-05-29 8:50 ` [PATCH 34/34] commit-graph: use modified path Bloom filters with wildcards, if possible SZEDER Gábor
2020-05-29 13:59 ` [PoC PATCH 00/34] An alternative modified path Bloom filters implementation Derrick Stolee
2020-06-01 23:25 ` Taylor Blau
2020-06-02 17:08 ` Junio C Hamano
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=20200529085038.26008-12-szeder.dev@gmail.com \
--to=szeder.dev@gmail.com \
--cc=garima.singh@microsoft.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=jnareb@gmail.com \
--cc=me@ttaylorr.com \
--cc=peff@peff.net \
--cc=stolee@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).