All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: szeder.dev@gmail.com, me@ttaylorr.com,
	Derrick Stolee <derrickstolee@github.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH 05/15] midx: add entries to write_midx_context
Date: Thu, 03 Dec 2020 16:16:44 +0000	[thread overview]
Message-ID: <491667de2baef422e801df1e2c7d3173462a96ff.1607012215.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.804.git.1607012215.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

In an effort to align write_midx_internal() with the chunk-format API,
continue to group necessary data into "struct write_midx_context". This
change collects the "struct pack_midx_entry *entries" list and its count
into the context.

Update write_midx_oid_fanout() and write_midx_oid_lookup() to take the
context directly, as these are easy conversions with this new data.

Only the callers of write_midx_object_offsets() and
write_midx_large_offsets() are updated here, since additional data in
the context before those methods can match chunk_write_fn.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 midx.c | 49 ++++++++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/midx.c b/midx.c
index 6ab655ddda..2af4452165 100644
--- a/midx.c
+++ b/midx.c
@@ -458,6 +458,9 @@ struct write_midx_context {
 	struct multi_pack_index *m;
 	struct progress *progress;
 	unsigned pack_paths_checked;
+
+	struct pack_midx_entry *entries;
+	uint32_t entries_nr;
 };
 
 static void add_pack_to_midx(const char *full_path, size_t full_path_len,
@@ -678,11 +681,11 @@ static size_t write_midx_pack_names(struct hashfile *f, void *data)
 }
 
 static size_t write_midx_oid_fanout(struct hashfile *f,
-				    struct pack_midx_entry *objects,
-				    uint32_t nr_objects)
+				    void *data)
 {
-	struct pack_midx_entry *list = objects;
-	struct pack_midx_entry *last = objects + nr_objects;
+	struct write_midx_context *ctx = (struct write_midx_context *)data;
+	struct pack_midx_entry *list = ctx->entries;
+	struct pack_midx_entry *last = ctx->entries + ctx->entries_nr;
 	uint32_t count = 0;
 	uint32_t i;
 
@@ -706,18 +709,19 @@ static size_t write_midx_oid_fanout(struct hashfile *f,
 	return MIDX_CHUNK_FANOUT_SIZE;
 }
 
-static size_t write_midx_oid_lookup(struct hashfile *f, unsigned char hash_len,
-				    struct pack_midx_entry *objects,
-				    uint32_t nr_objects)
+static size_t write_midx_oid_lookup(struct hashfile *f,
+				    void *data)
 {
-	struct pack_midx_entry *list = objects;
+	struct write_midx_context *ctx = (struct write_midx_context *)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 < nr_objects; i++) {
+	for (i = 0; i < ctx->entries_nr; i++) {
 		struct pack_midx_entry *obj = list++;
 
-		if (i < nr_objects - 1) {
+		if (i < ctx->entries_nr - 1) {
 			struct pack_midx_entry *next = list;
 			if (oidcmp(&obj->oid, &next->oid) >= 0)
 				BUG("OIDs not in order: %s >= %s",
@@ -805,8 +809,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 	uint64_t written = 0;
 	uint32_t chunk_ids[MIDX_MAX_CHUNKS + 1];
 	uint64_t chunk_offsets[MIDX_MAX_CHUNKS + 1];
-	uint32_t nr_entries, num_large_offsets = 0;
-	struct pack_midx_entry *entries = NULL;
+	uint32_t num_large_offsets = 0;
 	struct progress *progress = NULL;
 	int large_offsets_needed = 0;
 	int pack_name_concat_len = 0;
@@ -852,12 +855,12 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 	if (ctx.m && ctx.nr == ctx.m->num_packs && !packs_to_drop)
 		goto cleanup;
 
-	entries = get_sorted_entries(ctx.m, ctx.info, ctx.nr, &nr_entries);
+	ctx.entries = get_sorted_entries(ctx.m, ctx.info, ctx.nr, &ctx.entries_nr);
 
-	for (i = 0; i < nr_entries; i++) {
-		if (entries[i].offset > 0x7fffffff)
+	for (i = 0; i < ctx.entries_nr; i++) {
+		if (ctx.entries[i].offset > 0x7fffffff)
 			num_large_offsets++;
-		if (entries[i].offset > 0xffffffff)
+		if (ctx.entries[i].offset > 0xffffffff)
 			large_offsets_needed = 1;
 	}
 
@@ -947,10 +950,10 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 
 	cur_chunk++;
 	chunk_ids[cur_chunk] = MIDX_CHUNKID_OBJECTOFFSETS;
-	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * the_hash_algo->rawsz;
+	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + ctx.entries_nr * the_hash_algo->rawsz;
 
 	cur_chunk++;
-	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + nr_entries * MIDX_CHUNK_OFFSET_WIDTH;
+	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + ctx.entries_nr * MIDX_CHUNK_OFFSET_WIDTH;
 	if (large_offsets_needed) {
 		chunk_ids[cur_chunk] = MIDX_CHUNKID_LARGEOFFSETS;
 
@@ -993,19 +996,19 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 				break;
 
 			case MIDX_CHUNKID_OIDFANOUT:
-				written += write_midx_oid_fanout(f, entries, nr_entries);
+				written += write_midx_oid_fanout(f, &ctx);
 				break;
 
 			case MIDX_CHUNKID_OIDLOOKUP:
-				written += write_midx_oid_lookup(f, the_hash_algo->rawsz, entries, nr_entries);
+				written += write_midx_oid_lookup(f, &ctx);
 				break;
 
 			case MIDX_CHUNKID_OBJECTOFFSETS:
-				written += write_midx_object_offsets(f, large_offsets_needed, pack_perm, entries, nr_entries);
+				written += write_midx_object_offsets(f, large_offsets_needed, pack_perm, ctx.entries, ctx.entries_nr);
 				break;
 
 			case MIDX_CHUNKID_LARGEOFFSETS:
-				written += write_midx_large_offsets(f, num_large_offsets, entries, nr_entries);
+				written += write_midx_large_offsets(f, num_large_offsets, ctx.entries, ctx.entries_nr);
 				break;
 
 			default:
@@ -1035,7 +1038,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 	}
 
 	free(ctx.info);
-	free(entries);
+	free(ctx.entries);
 	free(pack_perm);
 	free(midx_name);
 	return result;
-- 
gitgitgadget


  parent reply	other threads:[~2020-12-03 16:17 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-03 16:16 [PATCH 00/15] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` [PATCH 01/15] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` [PATCH 02/15] chunk-format: add API for writing table of contents Derrick Stolee via GitGitGadget
2020-12-08 17:56   ` Taylor Blau
2020-12-03 16:16 ` [PATCH 03/15] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` [PATCH 04/15] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` Derrick Stolee via GitGitGadget [this message]
2020-12-03 21:42   ` [PATCH 05/15] midx: add entries to write_midx_context Junio C Hamano
2020-12-04 13:39     ` Derrick Stolee
2020-12-08 18:00   ` Taylor Blau
2020-12-03 16:16 ` [PATCH 06/15] midx: add pack_perm " Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` [PATCH 07/15] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` [PATCH 08/15] midx: convert chunk write methods to return int Derrick Stolee via GitGitGadget
2020-12-03 21:50   ` Junio C Hamano
2020-12-04 13:40     ` Derrick Stolee
2020-12-03 16:16 ` [PATCH 09/15] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2020-12-03 16:16 ` [PATCH 10/15] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2020-12-08 18:42   ` Taylor Blau
2020-12-10 14:36     ` Derrick Stolee
2020-12-03 16:16 ` [PATCH 11/15] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2020-12-03 22:00   ` Junio C Hamano
2020-12-08 18:43     ` Taylor Blau
2020-12-03 16:16 ` [PATCH 12/15] chunk-format: create write_chunks() Derrick Stolee via GitGitGadget
2020-12-08 18:45   ` Taylor Blau
2020-12-03 16:16 ` [PATCH 13/15] chunk-format: create chunk reading API Derrick Stolee via GitGitGadget
2020-12-03 22:17   ` Junio C Hamano
2020-12-04 13:47     ` Derrick Stolee
2020-12-04 20:17       ` Junio C Hamano
2020-12-03 22:43   ` Junio C Hamano
2020-12-04 13:45     ` Derrick Stolee
2020-12-03 16:16 ` [PATCH 14/15] commit-graph: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2020-12-07 13:43   ` Derrick Stolee
2020-12-03 16:16 ` [PATCH 15/15] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2020-12-04 12:48 ` [PATCH 00/15] Refactor chunk-format into an API René Scharfe
2020-12-04 13:57   ` Derrick Stolee
2020-12-04 19:42   ` Junio C Hamano
2020-12-08 18:49   ` Taylor Blau
2020-12-09 17:13     ` René Scharfe
2020-12-10  0:50       ` Taylor Blau
2020-12-10 14:30         ` 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

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=491667de2baef422e801df1e2c7d3173462a96ff.1607012215.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=derrickstolee@github.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=me@ttaylorr.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.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.