git.vger.kernel.org archive mirror
 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 06/15] midx: add pack_perm to write_midx_context
Date: Thu, 03 Dec 2020 16:16:45 +0000	[thread overview]
Message-ID: <0a2f81e7cfd39d69f6388bbfc8b157ba28321a21.1607012215.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 "uint32_t *pack_perm" and large_offsets_needed bit
into the context.

Update write_midx_object_offsets() to match chunk_write_fn.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 midx.c | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/midx.c b/midx.c
index 2af4452165..f7c3a54a33 100644
--- a/midx.c
+++ b/midx.c
@@ -461,6 +461,9 @@ struct write_midx_context {
 
 	struct pack_midx_entry *entries;
 	uint32_t entries_nr;
+
+	uint32_t *pack_perm;
+	unsigned large_offsets_needed:1;
 };
 
 static void add_pack_to_midx(const char *full_path, size_t full_path_len,
@@ -736,27 +739,27 @@ static size_t write_midx_oid_lookup(struct hashfile *f,
 	return written;
 }
 
-static size_t write_midx_object_offsets(struct hashfile *f, int large_offset_needed,
-					uint32_t *perm,
-					struct pack_midx_entry *objects, uint32_t nr_objects)
+static size_t write_midx_object_offsets(struct hashfile *f,
+					void *data)
 {
-	struct pack_midx_entry *list = objects;
+	struct write_midx_context *ctx = (struct write_midx_context *)data;
+	struct pack_midx_entry *list = ctx->entries;
 	uint32_t i, nr_large_offset = 0;
 	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 (perm[obj->pack_int_id] == PACK_EXPIRED)
+		if (ctx->pack_perm[obj->pack_int_id] == PACK_EXPIRED)
 			BUG("object %s is in an expired pack with int-id %d",
 			    oid_to_hex(&obj->oid),
 			    obj->pack_int_id);
 
-		hashwrite_be32(f, perm[obj->pack_int_id]);
+		hashwrite_be32(f, ctx->pack_perm[obj->pack_int_id]);
 
-		if (large_offset_needed && obj->offset >> 31)
+		if (ctx->large_offsets_needed && obj->offset >> 31)
 			hashwrite_be32(f, MIDX_LARGE_OFFSET_NEEDED | nr_large_offset++);
-		else if (!large_offset_needed && obj->offset >> 32)
+		else if (!ctx->large_offsets_needed && obj->offset >> 32)
 			BUG("object %s requires a large offset (%"PRIx64") but the MIDX is not writing large offsets!",
 			    oid_to_hex(&obj->oid),
 			    obj->offset);
@@ -805,13 +808,11 @@ 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 };
-	uint32_t *pack_perm = NULL;
 	uint64_t written = 0;
 	uint32_t chunk_ids[MIDX_MAX_CHUNKS + 1];
 	uint64_t chunk_offsets[MIDX_MAX_CHUNKS + 1];
 	uint32_t num_large_offsets = 0;
 	struct progress *progress = NULL;
-	int large_offsets_needed = 0;
 	int pack_name_concat_len = 0;
 	int dropped_packs = 0;
 	int result = 0;
@@ -857,11 +858,12 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 
 	ctx.entries = get_sorted_entries(ctx.m, ctx.info, ctx.nr, &ctx.entries_nr);
 
+	ctx.large_offsets_needed = 0;
 	for (i = 0; i < ctx.entries_nr; i++) {
 		if (ctx.entries[i].offset > 0x7fffffff)
 			num_large_offsets++;
 		if (ctx.entries[i].offset > 0xffffffff)
-			large_offsets_needed = 1;
+			ctx.large_offsets_needed = 1;
 	}
 
 	QSORT(ctx.info, ctx.nr, pack_info_compare);
@@ -900,13 +902,13 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 	 *
 	 * pack_perm[old_id] = new_id
 	 */
-	ALLOC_ARRAY(pack_perm, ctx.nr);
+	ALLOC_ARRAY(ctx.pack_perm, ctx.nr);
 	for (i = 0; i < ctx.nr; i++) {
 		if (ctx.info[i].expired) {
 			dropped_packs++;
-			pack_perm[ctx.info[i].orig_pack_int_id] = PACK_EXPIRED;
+			ctx.pack_perm[ctx.info[i].orig_pack_int_id] = PACK_EXPIRED;
 		} else {
-			pack_perm[ctx.info[i].orig_pack_int_id] = i - dropped_packs;
+			ctx.pack_perm[ctx.info[i].orig_pack_int_id] = i - dropped_packs;
 		}
 	}
 
@@ -927,7 +929,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 		close_midx(ctx.m);
 
 	cur_chunk = 0;
-	num_chunks = large_offsets_needed ? 5 : 4;
+	num_chunks = ctx.large_offsets_needed ? 5 : 4;
 
 	if (ctx.nr - dropped_packs == 0) {
 		error(_("no pack files to index."));
@@ -954,7 +956,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 
 	cur_chunk++;
 	chunk_offsets[cur_chunk] = chunk_offsets[cur_chunk - 1] + ctx.entries_nr * MIDX_CHUNK_OFFSET_WIDTH;
-	if (large_offsets_needed) {
+	if (ctx.large_offsets_needed) {
 		chunk_ids[cur_chunk] = MIDX_CHUNKID_LARGEOFFSETS;
 
 		cur_chunk++;
@@ -1004,7 +1006,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 				break;
 
 			case MIDX_CHUNKID_OBJECTOFFSETS:
-				written += write_midx_object_offsets(f, large_offsets_needed, pack_perm, ctx.entries, ctx.entries_nr);
+				written += write_midx_object_offsets(f, &ctx);
 				break;
 
 			case MIDX_CHUNKID_LARGEOFFSETS:
@@ -1039,7 +1041,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index *
 
 	free(ctx.info);
 	free(ctx.entries);
-	free(pack_perm);
+	free(ctx.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 ` [PATCH 05/15] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2020-12-03 21:42   ` Junio C Hamano
2020-12-04 13:39     ` Derrick Stolee
2020-12-08 18:00   ` Taylor Blau
2020-12-03 16:16 ` Derrick Stolee via GitGitGadget [this message]
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=0a2f81e7cfd39d69f6388bbfc8b157ba28321a21.1607012215.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 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 NNTP newsgroup(s).