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

[PATCH 5/8] get-repack --max-pack-size: write_object() takes 'limit' arg

From
DHDana How <danahow@gmail.com>
Date
Apr 8, 2007, 23:24 UTC
Message-ID
<46197994.70009@gmail.com>

Accept new 'limit' argument and check against it before each group of writes. Update delta usability rules for possibility of delta base being in a previously- written pack. Inline sha1write_compressed() so we know the exact size of the written data when it needs to be compressed.

Signed-off-by: Dana How <how@deathvalley.cswitch.com>
---
 builtin-pack-objects.c |   66 ++++++++++++++++++++++++++++++++++++++++++------
 1 files changed, 58 insertions(+), 8 deletions(-)
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 7ab0712..9530008 100644
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
@@ -373,7 +373,8 @@ static int revalidate_loose_object(struct object_entry *entry,
 }
 
 static off_t write_object(struct sha1file *f,
-				  struct object_entry *entry)
+				  struct object_entry *entry,
+				  unsigned long limit)
 {
 	unsigned long size;
 	enum object_type type;
@@ -407,6 +408,10 @@ static off_t write_object(struct sha1file *f,
 			if (revalidate_loose_object(entry, map, mapsize))
 				die("corrupt loose object %s",
 				    sha1_to_hex(entry->sha1));
+			if ( limit && mapsize + 20 >= limit ) {
+				munmap(map, mapsize);
+				return 0;
+			}
 			sha1write(f, map, mapsize);
 			munmap(map, mapsize);
 			written++;
@@ -418,24 +423,51 @@ static off_t write_object(struct sha1file *f,
 	}
 
 	if (!to_reuse) {
+		z_stream stream;
+		unsigned long maxsize;
+		void *out;
+					/* no if no delta */
+		int usable_delta =	!entry->delta ? 0 :
+					/* yes if unlimited packfile */
+					!offset_limit ? 1 :
+					/* no if base written to previous pack */
+					entry->delta->prev_pack ? 0 :
+					/* otherwise double-check written to this
+					 * pack,  like we do below
+					 */
+					entry->delta->offset ? 1 : 0;
 		buf = read_sha1_file(entry->sha1, &type, &size);
 		if (!buf)
 			die("unable to read %s", sha1_to_hex(entry->sha1));
 		if (size != entry->size)
 			die("object %s size inconsistency (%lu vs %lu)",
 			    sha1_to_hex(entry->sha1), size, entry->size);
-		if (entry->delta) {
+		if (usable_delta) {
 			buf = delta_against(buf, size, entry);
 			size = entry->delta_size;
 			obj_type = (allow_ofs_delta && entry->delta->offset) ?
 				OBJ_OFS_DELTA : OBJ_REF_DELTA;
 		}
+		/* compress the data to store and put compressed length in datalen */
+		memset(&stream, 0, sizeof(stream));
+		deflateInit(&stream, zlib_compression_level);
+		maxsize = deflateBound(&stream, size);
+		out = xmalloc(maxsize);
+		/* Compress it */
+		stream.next_in = buf;
+		stream.avail_in = size;
+		stream.next_out = out;
+		stream.avail_out = maxsize;
+		while (deflate(&stream, Z_FINISH) == Z_OK)
+			/* nothing */;
+		deflateEnd(&stream);
+		datalen = stream.total_out;
+		deflateEnd(&stream);
 		/*
 		 * The object header is a byte of 'type' followed by zero or
 		 * more bytes of length.
 		 */
 		hdrlen = encode_header(obj_type, size, header);
-		sha1write(f, header, hdrlen);
 
 		if (obj_type == OBJ_OFS_DELTA) {
 			/*
@@ -448,6 +480,12 @@ static off_t write_object(struct sha1file *f,
 			header[pos] = ofs & 127;
 			while (ofs >>= 7)
 				header[--pos] = 128 | (--ofs & 127);
+			if ( limit && hdrlen + sizeof(header) - pos + datalen + 20 >= limit ) {
+				free(out);
+				free(buf);
+				return 0;
+			}
+			sha1write(f, header, hdrlen);
 			sha1write(f, header + pos, sizeof(header) - pos);
 			hdrlen += sizeof(header) - pos;
 		} else if (obj_type == OBJ_REF_DELTA) {
@@ -455,10 +493,17 @@ static off_t write_object(struct sha1file *f,
 			 * Deltas with a base reference contain
 			 * an additional 20 bytes for the base sha1.
 			 */
+			if ( limit && hdrlen + 20 + datalen + 20 >= limit ) {
+				free(out);
+				free(buf);
+				return 0;
+			}
+			sha1write(f, header, hdrlen);
 			sha1write(f, entry->delta->sha1, 20);
 			hdrlen += 20;
 		}
-		datalen = sha1write_compressed(f, buf, size);
+		sha1write(f, out, datalen);
+		free(out);
 		free(buf);
 	}
 	else {
@@ -472,23 +517,28 @@ static off_t write_object(struct sha1file *f,
 			reused_delta++;
 		}
 		hdrlen = encode_header(obj_type, entry->size, header);
-		sha1write(f, header, hdrlen);
+		datalen = find_packed_object_size(p, entry->in_pack_offset)
+				- entry->in_pack_header_size;
 		if (obj_type == OBJ_OFS_DELTA) {
 			off_t ofs = entry->offset - entry->delta->offset;
 			unsigned pos = sizeof(header) - 1;
 			header[pos] = ofs & 127;
 			while (ofs >>= 7)
 				header[--pos] = 128 | (--ofs & 127);
+			if ( limit && hdrlen + sizeof(header) - pos + datalen + 20 >= limit )
+				return 0;
+			sha1write(f, header, hdrlen);
 			sha1write(f, header + pos, sizeof(header) - pos);
 			hdrlen += sizeof(header) - pos;
 		} else if (obj_type == OBJ_REF_DELTA) {
+			if ( limit && hdrlen + 20 + datalen + 20 >= limit )
+				return 0;
+			sha1write(f, header, hdrlen);
 			sha1write(f, entry->delta->sha1, 20);
 			hdrlen += 20;
 		}
 
 		offset = entry->in_pack_offset + entry->in_pack_header_size;
-		datalen = find_packed_object_size(p, entry->in_pack_offset)
-				- entry->in_pack_header_size;
 		if (!pack_to_stdout && check_pack_inflate(p, &w_curs,
 				offset, datalen, entry->size))
 			die("corrupt delta in pack %s", sha1_to_hex(entry->sha1));
@@ -515,7 +565,7 @@ static off_t write_one(struct sha1file *f,
 	if (e->delta)
 		offset = write_one(f, e->delta, offset);
 	e->offset = offset;
-	return offset + write_object(f, e);
+	return offset + write_object(f, e, 0);
 }
 
 /*
-- 
1.5.1.89.g8abf0
Next: Junio C Hamano
Message 1 of 10 in “get-repack --max-pack-size: write_object() takes 'limit' arg”
  1. 5/8 get-repack --max-pack-size: write_object() takes 'limit' argDana How, Apr 8, 2007
  2. Junio C HamanoApr 9, 2007
  3. Junio C HamanoApr 9, 2007
  4. Nicolas PitreApr 9, 2007
  5. Nicolas PitreApr 9, 2007
  6. Dana HowApr 9, 2007
  7. Nicolas PitreApr 9, 2007
  8. Dana HowApr 9, 2007
  9. Nicolas PitreApr 9, 2007
  10. Junio C HamanoApr 9, 2007

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.