git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[RFC PATCH 03/14] midx: use `strvec` for `keep_hashes`

From
Taylor Blau <me@ttaylorr.com>
Date
Feb 25, 2026, 00:21 UTC
Message-ID
<b2fffdfc8910308b6c816dfba9e04196a5aaf4ac.1771978829.git.me@ttaylorr.com>
In-Reply-To
<cover.1771978829.git.me@ttaylorr.com>

The `keep_hashes` array in `write_midx_internal()` accumulates the checksums of MIDX files that should be retained when pruning stale entries from the MIDX chain. For similar reasons as in a previous commit, rewrite this using a strvec, requiring us to pass one fewer parameter.

Unlike the aforementioned previous commit, use a `strvec` instead of a `string_list`, which provides a more ergonomic interface to adjust the values at a particular indice. The ordering is important here, as this value is used to determine the contents of the resulting `multi-pack-index-chain` file when writing with "--incremental".

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 midx-write.c | 51 ++++++++++++++++++++++++++-------------------------
 midx.c       | 20 ++++++++++----------
 2 files changed, 36 insertions(+), 35 deletions(-)
diff --git a/midx-write.c b/midx-write.c
index 0ff2e45aa7a..7fdc4d31243 100644
--- a/midx-write.c
+++ b/midx-write.c
@@ -29,8 +29,7 @@ extern void clear_midx_files_ext(struct odb_source *source, const char *ext,
 				 const char *keep_hash);
 extern void clear_incremental_midx_files_ext(struct odb_source *source,
 					     const char *ext,
-					     const char **keep_hashes,
-					     uint32_t hashes_nr);
+					     const struct strvec *keep_hashes);
 extern int cmp_idx_or_pack_name(const char *idx_or_pack_name,
 				const char *idx_name);
 
@@ -1109,8 +1108,7 @@ static int link_midx_to_chain(struct multi_pack_index *m)
 }
 
 static void clear_midx_files(struct odb_source *source,
-			     const char **hashes, uint32_t hashes_nr,
-			     unsigned incremental)
+			     const struct strvec *hashes, unsigned incremental)
 {
 	/*
 	 * if incremental:
@@ -1124,13 +1122,15 @@ static void clear_midx_files(struct odb_source *source,
 	 */
 	struct strbuf buf = STRBUF_INIT;
 	const char *exts[] = { MIDX_EXT_BITMAP, MIDX_EXT_REV, MIDX_EXT_MIDX };
-	uint32_t i, j;
+	uint32_t i;
 
 	for (i = 0; i < ARRAY_SIZE(exts); i++) {
-		clear_incremental_midx_files_ext(source, exts[i],
-						 hashes, hashes_nr);
-		for (j = 0; j < hashes_nr; j++)
-			clear_midx_files_ext(source, exts[i], hashes[j]);
+		clear_incremental_midx_files_ext(source, exts[i], hashes);
+		if (hashes) {
+			for (size_t j = 0; j < hashes->nr; j++)
+				clear_midx_files_ext(source, exts[i],
+						     hashes->v[j]);
+		}
 	}
 
 	if (incremental)
@@ -1266,7 +1266,7 @@ static int write_midx_internal(struct write_midx_opts *opts)
 	int pack_name_concat_len = 0;
 	int dropped_packs = 0;
 	int result = -1;
-	const char **keep_hashes = NULL;
+	struct strvec keep_hashes = STRVEC_INIT;
 	size_t keep_hashes_nr = 0;
 	struct chunkfile *cf;
 
@@ -1721,7 +1721,7 @@ static int write_midx_internal(struct write_midx_opts *opts)
 	} else {
 		keep_hashes_nr = ctx.num_multi_pack_indexes_before + 1;
 	}
-	CALLOC_ARRAY(keep_hashes, keep_hashes_nr);
+	strvec_init_alloc(&keep_hashes, keep_hashes_nr);
 
 	if (ctx.incremental) {
 		FILE *chainf = fdopen_lock_file(&lk, "w");
@@ -1758,39 +1758,45 @@ static int write_midx_internal(struct write_midx_opts *opts)
 			for (i = 0; i < num_layers_before_from; i++) {
 				uint32_t j = num_layers_before_from - i - 1;
 
-				keep_hashes[j] = xstrdup(midx_get_checksum_hex(m));
+				keep_hashes.v[j] = xstrdup(midx_get_checksum_hex(m));
+				keep_hashes.nr++;
 				m = m->base_midx;
 			}
 
-			keep_hashes[i] = xstrdup(hash_to_hex_algop(midx_hash,
+			keep_hashes.v[i] = xstrdup(hash_to_hex_algop(midx_hash,
 								   r->hash_algo));
+			keep_hashes.nr++;
 
 			i = 0;
 			for (m = ctx.m;
 			     m && midx_hashcmp(m, ctx.compact_to, r->hash_algo);
 			     m = m->base_midx) {
-				keep_hashes[keep_hashes_nr - i - 1] =
+				keep_hashes.v[keep_hashes_nr - i - 1] =
 					xstrdup(midx_get_checksum_hex(m));
+				keep_hashes.nr++;
 				i++;
 			}
 		} else {
-			keep_hashes[ctx.num_multi_pack_indexes_before] =
+			keep_hashes.v[ctx.num_multi_pack_indexes_before] =
 				xstrdup(hash_to_hex_algop(midx_hash,
 							  r->hash_algo));
+			keep_hashes.nr++;
 
 			for (uint32_t i = 0; i < ctx.num_multi_pack_indexes_before; i++) {
 				uint32_t j = ctx.num_multi_pack_indexes_before - i - 1;
 
-				keep_hashes[j] = xstrdup(midx_get_checksum_hex(m));
+				keep_hashes.v[j] = xstrdup(midx_get_checksum_hex(m));
+				keep_hashes.nr++;
 				m = m->base_midx;
 			}
 		}
 
 		for (uint32_t i = 0; i < keep_hashes_nr; i++)
-			fprintf(get_lock_file_fp(&lk), "%s\n", keep_hashes[i]);
+			fprintf(get_lock_file_fp(&lk), "%s\n", keep_hashes.v[i]);
 	} else {
-		keep_hashes[ctx.num_multi_pack_indexes_before] =
+		keep_hashes.v[ctx.num_multi_pack_indexes_before] =
 			xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo));
+		keep_hashes.nr++;
 	}
 
 	if (ctx.m || ctx.base_midx)
@@ -1799,8 +1805,7 @@ static int write_midx_internal(struct write_midx_opts *opts)
 	if (commit_lock_file(&lk) < 0)
 		die_errno(_("could not write multi-pack-index"));
 
-	clear_midx_files(opts->source, keep_hashes, keep_hashes_nr,
-			 ctx.incremental);
+	clear_midx_files(opts->source, &keep_hashes, ctx.incremental);
 	result = 0;
 
 cleanup:
@@ -1816,11 +1821,7 @@ static int write_midx_internal(struct write_midx_opts *opts)
 	free(ctx.entries);
 	free(ctx.pack_perm);
 	free(ctx.pack_order);
-	if (keep_hashes) {
-		for (uint32_t i = 0; i < keep_hashes_nr; i++)
-			free((char *)keep_hashes[i]);
-		free(keep_hashes);
-	}
+	strvec_clear(&keep_hashes);
 	strbuf_release(&midx_name);
 	close_midx(midx_to_free);
 
diff --git a/midx.c b/midx.c
index c5e3553e2bb..20732c256a6 100644
--- a/midx.c
+++ b/midx.c
@@ -12,6 +12,7 @@
 #include "chunk-format.h"
 #include "pack-bitmap.h"
 #include "pack-revindex.h"
+#include "strvec.h"
 
 #define MIDX_PACK_ERROR ((void *)(intptr_t)-1)
 
@@ -19,8 +20,7 @@ int midx_checksum_valid(struct multi_pack_index *m);
 void clear_midx_files_ext(struct odb_source *source, const char *ext,
 			  const char *keep_hash);
 void clear_incremental_midx_files_ext(struct odb_source *source, const char *ext,
-				      char **keep_hashes,
-				      uint32_t hashes_nr);
+				      const struct strvec *keep_hashes);
 int cmp_idx_or_pack_name(const char *idx_or_pack_name,
 			 const char *idx_name);
 
@@ -791,20 +791,20 @@ void clear_midx_files_ext(struct odb_source *source, const char *ext,
 }
 
 void clear_incremental_midx_files_ext(struct odb_source *source, const char *ext,
-				      char **keep_hashes,
-				      uint32_t hashes_nr)
+				      const struct strvec *keep_hashes)
 {
 	struct clear_midx_data data = {
 		.keep = STRING_LIST_INIT_NODUP,
 		.ext = ext,
 	};
-	uint32_t i;
 
-	for (i = 0; i < hashes_nr; i++)
-		string_list_append(&data.keep,
-				   xstrfmt("multi-pack-index-%s.%s",
-					   keep_hashes[i], ext));
-	string_list_sort(&data.keep);
+	if (keep_hashes) {
+		for (size_t i = 0; i < keep_hashes->nr; i++)
+			string_list_append(&data.keep,
+					   xstrfmt("multi-pack-index-%s.%s",
+						   keep_hashes->v[i], ext));
+		string_list_sort(&data.keep);
+	}
 
 	for_each_file_in_pack_subdir(source->path, "multi-pack-index.d",
 				     clear_midx_file_ext, &data);

-- 
2.53.0.185.g29bc4dff628
Previous: Taylor BlauNext: Taylor Blau
Message 11 of 21 in “repack: incremental MIDX/bitmap-based repacking”
  1. 00/14 repack: incremental MIDX/bitmap-based repackingTaylor Blau, Feb 25, 2026
  2. 06/14 repack: track the ODB source via existing_packsTaylor Blau, Feb 25, 2026
  3. Taylor BlauFeb 25, 2026
  4. 01/14 midx: use `string_list` for retained MIDX filesTaylor Blau, Feb 25, 2026
  5. Junio C HamanoFeb 26, 2026
  6. Taylor BlauFeb 27, 2026
  7. 02/14 strvec: introduce `strvec_init_alloc()`Taylor Blau, Feb 25, 2026
  8. Junio C HamanoFeb 26, 2026
  9. Junio C HamanoFeb 26, 2026
  10. Taylor BlauFeb 27, 2026
  11. 03/14 midx: use `strvec` for `keep_hashes`Taylor Blau, Feb 25, 2026
  12. 04/14 midx: introduce `--checksum-only` for incremental MIDX writesTaylor Blau, Feb 25, 2026
  13. 05/14 midx: support custom `--base` for incremental MIDX writesTaylor Blau, Feb 25, 2026
  14. 07/14 midx: expose `midx_layer_contains_pack()`Taylor Blau, Feb 25, 2026
  15. 08/14 repack-midx: factor out `repack_prepare_midx_command()`Taylor Blau, Feb 25, 2026
  16. 09/14 repack-midx: extract `repack_fill_midx_stdin_packs()`Taylor Blau, Feb 25, 2026
  17. 10/14 repack-geometry: prepare for incremental MIDX repackingTaylor Blau, Feb 25, 2026
  18. 11/14 builtin/repack.c: convert `--write-midx` to an `OPT_CALLBACK`Taylor Blau, Feb 25, 2026
  19. 12/14 repack: implement incremental MIDX repackingTaylor Blau, Feb 25, 2026
  20. 13/14 repack: introduce `--write-midx=incremental`Taylor Blau, Feb 25, 2026
  21. 14/14 repack: allow `--write-midx=incremental` without `--geometric`Taylor Blau, Feb 25, 2026

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.