[v2,0/5] optimizations for many alternates

Commit Message

Eric Wong June 29, 2021, 8:53 p.m. UTC

v2 has better naming for 3/5, fix test for sha256 in 5/5
Thanks to René and Junio for feedback so far.

Eric Wong (5):
  speed up alt_odb_usable() with many alternates
  avoid strlen via strbuf_addstr in link_alt_odb_entry
  make object_directory.loose_objects_subdir_seen a bitmap
  oidcpy_with_padding: constify `src' arg
  oidtree: a crit-bit tree for odb_loose_cache

 Makefile                |   3 +
 alloc.c                 |   6 ++
 alloc.h                 |   1 +
 cbtree.c                | 167 ++++++++++++++++++++++++++++++++++++++++
 cbtree.h                |  56 ++++++++++++++
 hash.h                  |   2 +-
 object-file.c           |  69 ++++++++++-------
 object-name.c           |  28 +++----
 object-store.h          |  24 +++++-
 object.c                |   2 +
 oidtree.c               |  94 ++++++++++++++++++++++
 oidtree.h               |  29 +++++++
 t/helper/test-oidtree.c |  47 +++++++++++
 t/helper/test-tool.c    |   1 +
 t/helper/test-tool.h    |   1 +
 t/t0069-oidtree.sh      |  52 +++++++++++++
 16 files changed, 533 insertions(+), 49 deletions(-)
 create mode 100644 cbtree.c
 create mode 100644 cbtree.h
 create mode 100644 oidtree.c
 create mode 100644 oidtree.h
 create mode 100644 t/helper/test-oidtree.c
 create mode 100755 t/t0069-oidtree.sh

Interdiff against v1:

Patch

diff --git a/object-file.c b/object-file.c
index d33b84c4a4..6c397fb4f1 100644
--- a/object-file.c
+++ b/object-file.c
@@ -2463,16 +2463,17 @@  struct oidtree *odb_loose_cache(struct object_directory *odb,
 {
 	int subdir_nr = oid->hash[0];
 	struct strbuf buf = STRBUF_INIT;
-	size_t BM_SIZE = sizeof(odb->loose_objects_subdir_seen[0]) * CHAR_BIT;
+	size_t word_bits = bitsizeof(odb->loose_objects_subdir_seen[0]);
+	size_t word_index = subdir_nr / word_bits;
+	size_t mask = 1 << (subdir_nr % word_bits);
 	uint32_t *bitmap;
-	uint32_t bit = 1 << (subdir_nr % BM_SIZE);
 
 	if (subdir_nr < 0 ||
-	    subdir_nr >= ARRAY_SIZE(odb->loose_objects_subdir_seen) * BM_SIZE)
+	    subdir_nr >= bitsizeof(odb->loose_objects_subdir_seen))
 		BUG("subdir_nr out of range");
 
-	bitmap = &odb->loose_objects_subdir_seen[subdir_nr / BM_SIZE];
-	if (*bitmap & bit)
+	bitmap = &odb->loose_objects_subdir_seen[word_index];
+	if (*bitmap & mask)
 		return &odb->loose_objects_cache;
 
 	strbuf_addstr(&buf, odb->path);
@@ -2480,7 +2481,7 @@  struct oidtree *odb_loose_cache(struct object_directory *odb,
 				    append_loose_object,
 				    NULL, NULL,
 				    &odb->loose_objects_cache);
-	*bitmap |= bit;
+	*bitmap |= mask;
 	strbuf_release(&buf);
 	return &odb->loose_objects_cache;
 }
diff --git a/t/helper/test-oidtree.c b/t/helper/test-oidtree.c
index 44bb2e7c29..e0da13eea3 100644
--- a/t/helper/test-oidtree.c
+++ b/t/helper/test-oidtree.c
@@ -13,6 +13,7 @@  int cmd__oidtree(int argc, const char **argv)
 	struct oidtree ot = OIDTREE_INIT;
 	struct strbuf line = STRBUF_INIT;
 	int nongit_ok;
+	int algo = GIT_HASH_UNKNOWN;
 
 	setup_git_directory_gently(&nongit_ok);
 
@@ -21,20 +22,21 @@  int cmd__oidtree(int argc, const char **argv)
 		struct object_id oid;
 
 		if (skip_prefix(line.buf, "insert ", &arg)) {
-			if (get_oid_hex(arg, &oid))
-				die("not a hexadecimal oid: %s", arg);
+			if (get_oid_hex_any(arg, &oid) == GIT_HASH_UNKNOWN)
+				die("insert not a hexadecimal oid: %s", arg);
+			algo = oid.algo;
 			oidtree_insert(&ot, &oid);
 		} else if (skip_prefix(line.buf, "contains ", &arg)) {
 			if (get_oid_hex(arg, &oid))
-				die("not a hexadecimal oid: %s", arg);
+				die("contains not a hexadecimal oid: %s", arg);
 			printf("%d\n", oidtree_contains(&ot, &oid));
 		} else if (skip_prefix(line.buf, "each ", &arg)) {
-			char buf[GIT_SHA1_HEXSZ  + 1] = { '0' };
+			char buf[GIT_MAX_HEXSZ + 1] = { '0' };
 			memset(&oid, 0, sizeof(oid));
 			memcpy(buf, arg, strlen(arg));
-			buf[GIT_SHA1_HEXSZ] = 0;
+			buf[hash_algos[algo].hexsz] = 0;
 			get_oid_hex_any(buf, &oid);
-			oid.algo = GIT_HASH_SHA1;
+			oid.algo = algo;
 			oidtree_each(&ot, &oid, strlen(arg), print_oid, NULL);
 		} else if (!strcmp(line.buf, "destroy"))
 			oidtree_destroy(&ot);
diff --git a/t/t0069-oidtree.sh b/t/t0069-oidtree.sh
index bb4229210c..0594f57c81 100755
--- a/t/t0069-oidtree.sh
+++ b/t/t0069-oidtree.sh
@@ -10,9 +10,9 @@  echoid () {
 	do
 		echo "$1"
 		shift
-	done | awk -v prefix="$prefix" '{
+	done | awk -v prefix="$prefix" -v ZERO_OID=$ZERO_OID '{
 		printf("%s%s", prefix, $0);
-		need = 40 - length($0);
+		need = length(ZERO_OID) - length($0);
 		for (i = 0; i < need; i++)
 			printf("0");
 		printf "\n";