midx: implement midx_repack()

To repack with a non-zero batch-size, first sort all pack-files by
their modified time. Second, walk those pack-files from oldest
to newest, compute their expected size, and add the packs to a list
if they are smaller than the given batch-size. Stop when the total
expected size is at least the batch size.

If the batch size is zero, select all packs in the multi-pack-index.

Finally, collect the objects from the multi-pack-index that are in
the selected packs and send them to 'git pack-objects'. Write a new
multi-pack-index that includes the new pack.

Using a batch size of zero is very similar to a standard 'git repack'
command, except that we do not delete the old packs and instead rely
on the new multi-pack-index to prevent new processes from reading the
old packs. This does not disrupt other Git processes that are currently
reading the old packs based on the old multi-pack-index.

While first designing a 'git multi-pack-index repack' operation, I
started by collecting the batches based on the actual size of the
objects instead of the size of the pack-files. This allows repacking
a large pack-file that has very few referencd objects. However, this
came at a significant cost of parsing pack-files instead of simply
reading the multi-pack-index and getting the file information for
the pack-files. The "expected size" version provides similar
behavior, but could skip a pack-file if the average object size is
much larger than the actual size of the referenced objects, or
can create a large pack if the actual size of the referenced objects
is larger than the expected size.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 150 insertions, 1 deletions

diff --git a/midx.c b/midx.c
index fbed8a8adb..d649644420 100644
--- a/midx.c
+++ b/midx.c
@@ -9,6 +9,7 @@
 #include "midx.h"
 #include "progress.h"
 #include "trace2.h"
+#include "run-command.h"
 
 #define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */
 #define MIDX_VERSION 1
@@ -1227,7 +1228,155 @@ int expire_midx_packs(struct repository *r, const char *object_dir)
 	return result;
 }
 
-int midx_repack(struct repository *r, const char *object_dir, size_t batch_size)
+struct repack_info {
+	timestamp_t mtime;
+	uint32_t referenced_objects;
+	uint32_t pack_int_id;
+};
+
+static int compare_by_mtime(const void *a_, const void *b_)
 {
+	const struct repack_info *a, *b;
+
+	a = (const struct repack_info *)a_;
+	b = (const struct repack_info *)b_;
+
+	if (a->mtime < b->mtime)
+		return -1;
+	if (a->mtime > b->mtime)
+		return 1;
+	return 0;
+}
+
+static int fill_included_packs_all(struct multi_pack_index *m,
+				   unsigned char *include_pack)
+{
+	uint32_t i;
+
+	for (i = 0; i < m->num_packs; i++)
+		include_pack[i] = 1;
+
+	return m->num_packs < 2;
+}
+
+static int fill_included_packs_batch(struct repository *r,
+				     struct multi_pack_index *m,
+				     unsigned char *include_pack,
+				     size_t batch_size)
+{
+	uint32_t i, packs_to_repack;
+	size_t total_size;
+	struct repack_info *pack_info = xcalloc(m->num_packs, sizeof(struct repack_info));
+
+	for (i = 0; i < m->num_packs; i++) {
+		pack_info[i].pack_int_id = i;
+
+		if (prepare_midx_pack(r, m, i))
+			continue;
+
+		pack_info[i].mtime = m->packs[i]->mtime;
+	}
+
+	for (i = 0; batch_size && i < m->num_objects; i++) {
+		uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
+		pack_info[pack_int_id].referenced_objects++;
+	}
+
+	QSORT(pack_info, m->num_packs, compare_by_mtime);
+
+	total_size = 0;
+	packs_to_repack = 0;
+	for (i = 0; total_size < batch_size && i < m->num_packs; i++) {
+		int pack_int_id = pack_info[i].pack_int_id;
+		struct packed_git *p = m->packs[pack_int_id];
+		size_t expected_size;
+
+		if (!p)
+			continue;
+		if (open_pack_index(p) || !p->num_objects)
+			continue;
+
+		expected_size = (size_t)(p->pack_size
+					 * pack_info[i].referenced_objects);
+		expected_size /= p->num_objects;
+
+		if (expected_size >= batch_size)
+			continue;
+
+		packs_to_repack++;
+		total_size += expected_size;
+		include_pack[pack_int_id] = 1;
+	}
+
+	free(pack_info);
+
+	if (total_size < batch_size || packs_to_repack < 2)
+		return 1;
+
 	return 0;
 }
+
+int midx_repack(struct repository *r, const char *object_dir, size_t batch_size)
+{
+	int result = 0;
+	uint32_t i;
+	unsigned char *include_pack;
+	struct child_process cmd = CHILD_PROCESS_INIT;
+	struct strbuf base_name = STRBUF_INIT;
+	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+
+	if (!m)
+		return 0;
+
+	include_pack = xcalloc(m->num_packs, sizeof(unsigned char));
+
+	if (batch_size) {
+		if (fill_included_packs_batch(r, m, include_pack, batch_size))
+			goto cleanup;
+	} else if (fill_included_packs_all(m, include_pack))
+		goto cleanup;
+
+	argv_array_push(&cmd.args, "pack-objects");
+
+	strbuf_addstr(&base_name, object_dir);
+	strbuf_addstr(&base_name, "/pack/pack");
+	argv_array_push(&cmd.args, base_name.buf);
+	strbuf_release(&base_name);
+
+	cmd.git_cmd = 1;
+	cmd.in = cmd.out = -1;
+
+	if (start_command(&cmd)) {
+		error(_("could not start pack-objects"));
+		result = 1;
+		goto cleanup;
+	}
+
+	for (i = 0; i < m->num_objects; i++) {
+		struct object_id oid;
+		uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
+
+		if (!include_pack[pack_int_id])
+			continue;
+
+		nth_midxed_object_oid(&oid, m, i);
+		xwrite(cmd.in, oid_to_hex(&oid), the_hash_algo->hexsz);
+		xwrite(cmd.in, "\n", 1);
+	}
+	close(cmd.in);
+
+	if (finish_command(&cmd)) {
+		error(_("could not finish pack-objects"));
+		result = 1;
+		goto cleanup;
+	}
+
+	result = write_midx_internal(object_dir, m, NULL);
+	m = NULL;
+
+cleanup:
+	if (m)
+		close_midx(m);
+	free(include_pack);
+	return result;
+}