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 v3 09/17] midx: return success/failure in chunk write methods
Date: Fri, 05 Feb 2021 14:30:44 +0000 [thread overview]
Message-ID: <7aa3242e15b7a0cca7b7d4394311697ed84bc05a.1612535453.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.848.v3.git.1612535452.gitgitgadget@gmail.com>
From: Derrick Stolee <dstolee@microsoft.com>
Historically, the chunk-writing methods in midx.c have returned the
amount of data written so the writer method could compare this with the
table of contents. This presents with some interesting issues:
1. If a chunk writing method has a bug that miscalculates the written
bytes, then we can satisfy the table of contents without actually
writing the right amount of data to the hashfile. The commit-graph
writing code checks the hashfile struct directly for a more robust
verification.
2. There is no way for a chunk writing method to gracefully fail.
Returning an int presents an opportunity to fail without a die().
3. The current pattern doesn't match chunk_write_fn type exactly, so we
cannot share code with commit-graph.c
For these reasons, convert the midx chunk writer methods to return an
'int'. Since none of them fail at the moment, they all return 0.
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
midx.c | 63 +++++++++++++++++++++++++---------------------------------
1 file changed, 27 insertions(+), 36 deletions(-)
diff --git a/midx.c b/midx.c
index 5be081f229ad..c92a6c47be01 100644
--- a/midx.c
+++ b/midx.c
@@ -650,7 +650,7 @@ static struct pack_midx_entry *get_sorted_entries(struct multi_pack_index *m,
return deduplicated_entries;
}
-static size_t write_midx_pack_names(struct hashfile *f, void *data)
+static int write_midx_pack_names(struct hashfile *f, void *data)
{
struct write_midx_context *ctx = data;
uint32_t i;
@@ -678,14 +678,13 @@ static size_t write_midx_pack_names(struct hashfile *f, void *data)
if (i < MIDX_CHUNK_ALIGNMENT) {
memset(padding, 0, sizeof(padding));
hashwrite(f, padding, i);
- written += i;
}
- return written;
+ return 0;
}
-static size_t write_midx_oid_fanout(struct hashfile *f,
- void *data)
+static int write_midx_oid_fanout(struct hashfile *f,
+ void *data)
{
struct write_midx_context *ctx = data;
struct pack_midx_entry *list = ctx->entries;
@@ -710,17 +709,16 @@ static size_t write_midx_oid_fanout(struct hashfile *f,
list = next;
}
- return MIDX_CHUNK_FANOUT_SIZE;
+ return 0;
}
-static size_t write_midx_oid_lookup(struct hashfile *f,
- void *data)
+static int write_midx_oid_lookup(struct hashfile *f,
+ void *data)
{
struct write_midx_context *ctx = data;
unsigned char hash_len = the_hash_algo->rawsz;
struct pack_midx_entry *list = ctx->entries;
uint32_t i;
- size_t written = 0;
for (i = 0; i < ctx->entries_nr; i++) {
struct pack_midx_entry *obj = list++;
@@ -734,19 +732,17 @@ static size_t write_midx_oid_lookup(struct hashfile *f,
}
hashwrite(f, obj->oid.hash, (int)hash_len);
- written += hash_len;
}
- return written;
+ return 0;
}
-static size_t write_midx_object_offsets(struct hashfile *f,
- void *data)
+static int write_midx_object_offsets(struct hashfile *f,
+ void *data)
{
struct write_midx_context *ctx = data;
struct pack_midx_entry *list = ctx->entries;
uint32_t i, nr_large_offset = 0;
- size_t written = 0;
for (i = 0; i < ctx->entries_nr; i++) {
struct pack_midx_entry *obj = list++;
@@ -766,20 +762,17 @@ static size_t write_midx_object_offsets(struct hashfile *f,
obj->offset);
else
hashwrite_be32(f, (uint32_t)obj->offset);
-
- written += MIDX_CHUNK_OFFSET_WIDTH;
}
- return written;
+ return 0;
}
-static size_t write_midx_large_offsets(struct hashfile *f,
- void *data)
+static int write_midx_large_offsets(struct hashfile *f,
+ void *data)
{
struct write_midx_context *ctx = data;
struct pack_midx_entry *list = ctx->entries;
struct pack_midx_entry *end = ctx->entries + ctx->entries_nr;
- size_t written = 0;
uint32_t nr_large_offset = ctx->num_large_offsets;
while (nr_large_offset) {
@@ -795,12 +788,12 @@ static size_t write_midx_large_offsets(struct hashfile *f,
if (!(offset >> 31))
continue;
- written += hashwrite_be64(f, offset);
+ hashwrite_be64(f, offset);
nr_large_offset--;
}
- return written;
+ return 0;
}
static int write_midx_internal(const char *object_dir, struct multi_pack_index *m,
@@ -812,7 +805,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
struct hashfile *f = NULL;
struct lock_file lk;
struct write_midx_context ctx = { 0 };
- uint64_t written = 0;
+ uint64_t header_size = 0;
uint32_t chunk_ids[MIDX_MAX_CHUNKS + 1];
uint64_t chunk_offsets[MIDX_MAX_CHUNKS + 1];
struct progress *progress = NULL;
@@ -940,10 +933,10 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
goto cleanup;
}
- written = write_midx_header(f, num_chunks, ctx.nr - dropped_packs);
+ header_size = write_midx_header(f, num_chunks, ctx.nr - dropped_packs);
chunk_ids[cur_chunk] = MIDX_CHUNKID_PACKNAMES;
- chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
+ chunk_offsets[cur_chunk] = header_size + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
cur_chunk++;
chunk_ids[cur_chunk] = MIDX_CHUNKID_OIDFANOUT;
@@ -981,39 +974,37 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
hashwrite_be32(f, chunk_ids[i]);
hashwrite_be64(f, chunk_offsets[i]);
-
- written += MIDX_CHUNKLOOKUP_WIDTH;
}
if (flags & MIDX_PROGRESS)
progress = start_delayed_progress(_("Writing chunks to multi-pack-index"),
num_chunks);
for (i = 0; i < num_chunks; i++) {
- if (written != chunk_offsets[i])
+ if (f->total + f->offset != chunk_offsets[i])
BUG("incorrect chunk offset (%"PRIu64" != %"PRIu64") for chunk id %"PRIx32,
chunk_offsets[i],
- written,
+ f->total + f->offset,
chunk_ids[i]);
switch (chunk_ids[i]) {
case MIDX_CHUNKID_PACKNAMES:
- written += write_midx_pack_names(f, &ctx);
+ write_midx_pack_names(f, &ctx);
break;
case MIDX_CHUNKID_OIDFANOUT:
- written += write_midx_oid_fanout(f, &ctx);
+ write_midx_oid_fanout(f, &ctx);
break;
case MIDX_CHUNKID_OIDLOOKUP:
- written += write_midx_oid_lookup(f, &ctx);
+ write_midx_oid_lookup(f, &ctx);
break;
case MIDX_CHUNKID_OBJECTOFFSETS:
- written += write_midx_object_offsets(f, &ctx);
+ write_midx_object_offsets(f, &ctx);
break;
case MIDX_CHUNKID_LARGEOFFSETS:
- written += write_midx_large_offsets(f, &ctx);
+ write_midx_large_offsets(f, &ctx);
break;
default:
@@ -1025,9 +1016,9 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
}
stop_progress(&progress);
- if (written != chunk_offsets[num_chunks])
+ if (hashfile_total(f) != chunk_offsets[num_chunks])
BUG("incorrect final offset %"PRIu64" != %"PRIu64,
- written,
+ hashfile_total(f),
chunk_offsets[num_chunks]);
finalize_hashfile(f, NULL, CSUM_FSYNC | CSUM_HASH_IN_STREAM);
--
gitgitgadget
next prev parent reply other threads:[~2021-02-05 16:43 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 ` [PATCH v2 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-27 15:01 ` [PATCH v2 14/17] midx: " 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 ` Derrick Stolee via GitGitGadget [this message]
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=7aa3242e15b7a0cca7b7d4394311697ed84bc05a.1612535453.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).