Merge branch 'nd/split-index'

An experiment to use two files (the base file and incremental
changes relative to it) to represent the index to reduce I/O cost
of rewriting a large index when only small part of the working tree
changes.

* nd/split-index: (32 commits)
  t1700: new tests for split-index mode
  t2104: make sure split index mode is off for the version test
  read-cache: force split index mode with GIT_TEST_SPLIT_INDEX
  read-tree: note about dropping split-index mode or index version
  read-tree: force split-index mode off on --index-output
  rev-parse: add --shared-index-path to get shared index path
  update-index --split-index: do not split if $GIT_DIR is read only
  update-index: new options to enable/disable split index mode
  split-index: strip pathname of on-disk replaced entries
  split-index: do not invalidate cache-tree at read time
  split-index: the reading part
  split-index: the writing part
  read-cache: mark updated entries for split index
  read-cache: save deleted entries in split index
  read-cache: mark new entries for split index
  read-cache: split-index mode
  read-cache: save index SHA-1 after reading
  entry.c: update cache_changed if refresh_cache is set in checkout_entry()
  cache-tree: mark istate->cache_changed on prime_cache_tree()
  cache-tree: mark istate->cache_changed on cache tree update
  ...

.gitignore

@@ -181,6 +181,7 @@
 /test-date
 /test-delta
 /test-dump-cache-tree
+/test-dump-split-index
 /test-scrap-cache-tree
 /test-genrandom
 /test-hashmap

Documentation/git-rev-parse.txt

@@ -245,6 +245,10 @@ print a message to stderr and exit with nonzero status.
 --show-toplevel::
 	Show the absolute path of the top-level directory.
 
+--shared-index-path::
+	Show the path to the shared index file in split index mode, or
+	empty if not in split-index mode.
+
 Other Options
 ~~~~~~~~~~~~~
 

Documentation/git-update-index.txt

@@ -161,6 +161,17 @@ may not support it yet.
 	Only meaningful with `--stdin` or `--index-info`; paths are
 	separated with NUL character instead of LF.
 
+--split-index::
+--no-split-index::
+	Enable or disable split index mode. If enabled, the index is
+	split into two files, $GIT_DIR/index and $GIT_DIR/sharedindex.<SHA-1>.
+	Changes are accumulated in $GIT_DIR/index while the shared
+	index file contains all index entries stays unchanged. If
+	split-index mode is already enabled and `--split-index` is
+	given again, all changes in $GIT_DIR/index are pushed back to
+	the shared index file. This mode is designed for very large
+	indexes that take a signficant amount of time to read or write.
+
 \--::
 	Do not interpret any more arguments as options.
 

Documentation/gitrepository-layout.txt

@@ -155,6 +155,10 @@ index::
 	The current index file for the repository.  It is
 	usually not found in a bare repository.
 
+sharedindex.<SHA-1>::
+	The shared index part, to be referenced by $GIT_DIR/index and
+	other temporary index files. Only valid in split index mode.
+
 info::
 	Additional information about the repository is recorded
 	in this directory.

Documentation/technical/index-format.txt

@@ -129,6 +129,9 @@ Git index format
   (Version 4) In version 4, the padding after the pathname does not
   exist.
 
+  Interpretation of index entries in split index mode is completely
+  different. See below for details.
+
 == Extensions
 
 === Cached tree
@@ -198,3 +201,35 @@ Git index format
   - At most three 160-bit object names of the entry in stages from 1 to 3
     (nothing is written for a missing stage).
 
+=== Split index
+
+  In split index mode, the majority of index entries could be stored
+  in a separate file. This extension records the changes to be made on
+  top of that to produce the final index.
+
+  The signature for this extension is { 'l', 'i, 'n', 'k' }.
+
+  The extension consists of:
+
+  - 160-bit SHA-1 of the shared index file. The shared index file path
+    is $GIT_DIR/sharedindex.<SHA-1>. If all 160 bits are zero, the
+    index does not require a shared index file.
+
+  - An ewah-encoded delete bitmap, each bit represents an entry in the
+    shared index. If a bit is set, its corresponding entry in the
+    shared index will be removed from the final index.  Note, because
+    a delete operation changes index entry positions, but we do need
+    original positions in replace phase, it's best to just mark
+    entries for removal, then do a mass deletion after replacement.
+
+  - An ewah-encoded replace bitmap, each bit represents an entry in
+    the shared index. If a bit is set, its corresponding entry in the
+    shared index will be replaced with an entry in this index
+    file. All replaced entries are stored in sorted order in this
+    index. The first "1" bit in the replace bitmap corresponds to the
+    first index entry, the second "1" bit to the second entry and so
+    on. Replaced entries may have empty path names to save space.
+
+  The remaining index entries after replaced ones will be added to the
+  final index. These added entries are also sorted by entry namme then
+  stage.

Makefile

@@ -552,6 +552,7 @@ TEST_PROGRAMS_NEED_X += test-ctype
 TEST_PROGRAMS_NEED_X += test-date
 TEST_PROGRAMS_NEED_X += test-delta
 TEST_PROGRAMS_NEED_X += test-dump-cache-tree
+TEST_PROGRAMS_NEED_X += test-dump-split-index
 TEST_PROGRAMS_NEED_X += test-genrandom
 TEST_PROGRAMS_NEED_X += test-hashmap
 TEST_PROGRAMS_NEED_X += test-index-version
@@ -875,6 +876,7 @@ LIB_OBJS += sha1_name.o
 LIB_OBJS += shallow.o
 LIB_OBJS += sideband.o
 LIB_OBJS += sigchain.o
+LIB_OBJS += split-index.o
 LIB_OBJS += strbuf.o
 LIB_OBJS += streaming.o
 LIB_OBJS += string-list.o

builtin/add.c

@@ -299,7 +299,6 @@ static int add_files(struct dir_struct *dir, int flags)
 int cmd_add(int argc, const char **argv, const char *prefix)
 {
 	int exit_status = 0;
-	int newfd;
 	struct pathspec pathspec;
 	struct dir_struct dir;
 	int flags;
@@ -345,7 +344,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 	add_new_files = !take_worktree_changes && !refresh_only;
 	require_pathspec = !take_worktree_changes;
 
-	newfd = hold_locked_index(&lock_file, 1);
+	hold_locked_index(&lock_file, 1);
 
 	flags = ((verbose ? ADD_CACHE_VERBOSE : 0) |
 		 (show_only ? ADD_CACHE_PRETEND : 0) |
@@ -443,8 +442,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 
 finish:
 	if (active_cache_changed) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(&lock_file))
+		if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 			die(_("Unable to write new index file"));
 	}
 

builtin/apply.c

@@ -3084,13 +3084,15 @@ static void prepare_fn_table(struct patch *patch)
 	}
 }
 
-static int checkout_target(struct cache_entry *ce, struct stat *st)
+static int checkout_target(struct index_state *istate,
+			   struct cache_entry *ce, struct stat *st)
 {
 	struct checkout costate;
 
 	memset(&costate, 0, sizeof(costate));
 	costate.base_dir = "";
 	costate.refresh_cache = 1;
+	costate.istate = istate;
 	if (checkout_entry(ce, &costate, NULL) || lstat(ce->name, st))
 		return error(_("cannot checkout %s"), ce->name);
 	return 0;
@@ -3257,7 +3259,7 @@ static int load_current(struct image *image, struct patch *patch)
 	if (lstat(name, &st)) {
 		if (errno != ENOENT)
 			return error(_("%s: %s"), name, strerror(errno));
-		if (checkout_target(ce, &st))
+		if (checkout_target(&the_index, ce, &st))
 			return -1;
 	}
 	if (verify_index_match(ce, &st))
@@ -3411,7 +3413,7 @@ static int check_preimage(struct patch *patch, struct cache_entry **ce, struct s
 		}
 		*ce = active_cache[pos];
 		if (stat_ret < 0) {
-			if (checkout_target(*ce, st))
+			if (checkout_target(&the_index, *ce, st))
 				return -1;
 		}
 		if (!cached && verify_index_match(*ce, st))
@@ -3644,7 +3646,7 @@ static void build_fake_ancestor(struct patch *list, const char *filename)
 {
 	struct patch *patch;
 	struct index_state result = { NULL };
-	int fd;
+	static struct lock_file lock;
 
 	/* Once we start supporting the reverse patch, it may be
 	 * worth showing the new sha1 prefix, but until then...
@@ -3682,8 +3684,8 @@ static void build_fake_ancestor(struct patch *list, const char *filename)
 			die ("Could not add %s to temporary index", name);
 	}
 
-	fd = open(filename, O_WRONLY | O_CREAT, 0666);
-	if (fd < 0 || write_index(&result, fd) || close(fd))
+	hold_lock_file_for_update(&lock, filename, LOCK_DIE_ON_ERROR);
+	if (write_locked_index(&result, &lock, COMMIT_LOCK))
 		die ("Could not write temporary index to %s", filename);
 
 	discard_index(&result);
@@ -4502,8 +4504,7 @@ int cmd_apply(int argc, const char **argv, const char *prefix_)
 	}
 
 	if (update_index) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(&lock_file))
+		if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 			die(_("Unable to write new index file"));
 	}
 

builtin/blame.c

@@ -2389,7 +2389,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
 	 * right now, but someday we might optimize diff-index --cached
 	 * with cache-tree information.
 	 */
-	cache_tree_invalidate_path(active_cache_tree, path);
+	cache_tree_invalidate_path(&the_index, path);
 
 	return commit;
 }

builtin/checkout-index.c

@@ -135,6 +135,7 @@ static int option_parse_u(const struct option *opt,
 	int *newfd = opt->value;
 
 	state.refresh_cache = 1;
+	state.istate = &the_index;
 	if (*newfd < 0)
 		*newfd = hold_locked_index(&lock_file, 1);
 	return 0;
@@ -279,8 +280,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 		checkout_all(prefix, prefix_length);
 
 	if (0 <= newfd &&
-	    (write_cache(newfd, active_cache, active_nr) ||
-	     commit_locked_index(&lock_file)))
+	    write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 		die("Unable to write new index file");
 	return 0;
 }

builtin/checkout.c

@@ -225,7 +225,6 @@ static int checkout_paths(const struct checkout_opts *opts,
 	int flag;
 	struct commit *head;
 	int errs = 0;
-	int newfd;
 	struct lock_file *lock_file;
 
 	if (opts->track != BRANCH_TRACK_UNSPECIFIED)
@@ -256,7 +255,7 @@ static int checkout_paths(const struct checkout_opts *opts,
 
 	lock_file = xcalloc(1, sizeof(struct lock_file));
 
-	newfd = hold_locked_index(lock_file, 1);
+	hold_locked_index(lock_file, 1);
 	if (read_cache_preload(&opts->pathspec) < 0)
 		return error(_("corrupt index file"));
 
@@ -337,6 +336,7 @@ static int checkout_paths(const struct checkout_opts *opts,
 	memset(&state, 0, sizeof(state));
 	state.force = 1;
 	state.refresh_cache = 1;
+	state.istate = &the_index;
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
 		if (ce->ce_flags & CE_MATCHED) {
@@ -352,8 +352,7 @@ static int checkout_paths(const struct checkout_opts *opts,
 		}
 	}
 
-	if (write_cache(newfd, active_cache, active_nr) ||
-	    commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
 	read_ref_full("HEAD", rev, 0, &flag);
@@ -444,8 +443,8 @@ static int merge_working_tree(const struct checkout_opts *opts,
 {
 	int ret;
 	struct lock_file *lock_file = xcalloc(1, sizeof(struct lock_file));
-	int newfd = hold_locked_index(lock_file, 1);
 
+	hold_locked_index(lock_file, 1);
 	if (read_cache_preload(NULL) < 0)
 		return error(_("corrupt index file"));
 
@@ -553,8 +552,7 @@ static int merge_working_tree(const struct checkout_opts *opts,
 		}
 	}
 
-	if (write_cache(newfd, active_cache, active_nr) ||
-	    commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
 	if (!opts->force && !opts->quiet)

builtin/clone.c

@@ -617,7 +617,7 @@ static int checkout(void)
 	struct unpack_trees_options opts;
 	struct tree *tree;
 	struct tree_desc t;
-	int err = 0, fd;
+	int err = 0;
 
 	if (option_no_checkout)
 		return 0;
@@ -641,7 +641,7 @@ static int checkout(void)
 	setup_work_tree();
 
 	lock_file = xcalloc(1, sizeof(struct lock_file));
-	fd = hold_locked_index(lock_file, 1);
+	hold_locked_index(lock_file, 1);
 
 	memset(&opts, 0, sizeof opts);
 	opts.update = 1;
@@ -657,8 +657,7 @@ static int checkout(void)
 	if (unpack_trees(1, &t, &opts) < 0)
 		die(_("unable to checkout working tree"));
 
-	if (write_cache(fd, active_cache, active_nr) ||
-	    commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
 	err |= run_hook_le(NULL, "post-checkout", sha1_to_hex(null_sha1),

builtin/commit.c

@@ -305,7 +305,6 @@ static void refresh_cache_or_die(int refresh_flags)
 static char *prepare_index(int argc, const char **argv, const char *prefix,
 			   const struct commit *current_head, int is_status)
 {
-	int fd;
 	struct string_list partial;
 	struct pathspec pathspec;
 	int refresh_flags = REFRESH_QUIET;
@@ -321,12 +320,11 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 
 	if (interactive) {
 		char *old_index_env = NULL;
-		fd = hold_locked_index(&index_lock, 1);
+		hold_locked_index(&index_lock, 1);
 
 		refresh_cache_or_die(refresh_flags);
 
-		if (write_cache(fd, active_cache, active_nr) ||
-		    close_lock_file(&index_lock))
+		if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 			die(_("unable to create temporary index"));
 
 		old_index_env = getenv(INDEX_ENVIRONMENT);
@@ -360,12 +358,11 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 	 * (B) on failure, rollback the real index.
 	 */
 	if (all || (also && pathspec.nr)) {
-		fd = hold_locked_index(&index_lock, 1);
+		hold_locked_index(&index_lock, 1);
 		add_files_to_cache(also ? prefix : NULL, &pathspec, 0);
 		refresh_cache_or_die(refresh_flags);
 		update_main_cache_tree(WRITE_TREE_SILENT);
-		if (write_cache(fd, active_cache, active_nr) ||
-		    close_lock_file(&index_lock))
+		if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 			die(_("unable to write new_index file"));
 		commit_style = COMMIT_NORMAL;
 		return index_lock.filename;
@@ -381,12 +378,12 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 	 * We still need to refresh the index here.
 	 */
 	if (!only && !pathspec.nr) {
-		fd = hold_locked_index(&index_lock, 1);
+		hold_locked_index(&index_lock, 1);
 		refresh_cache_or_die(refresh_flags);
 		if (active_cache_changed) {
 			update_main_cache_tree(WRITE_TREE_SILENT);
-			if (write_cache(fd, active_cache, active_nr) ||
-			    commit_locked_index(&index_lock))
+			if (write_locked_index(&the_index, &index_lock,
+					       COMMIT_LOCK))
 				die(_("unable to write new_index file"));
 		} else {
 			rollback_lock_file(&index_lock);
@@ -432,24 +429,22 @@ static char *prepare_index(int argc, const char **argv, const char *prefix,
 	if (read_cache() < 0)
 		die(_("cannot read the index"));
 
-	fd = hold_locked_index(&index_lock, 1);
+	hold_locked_index(&index_lock, 1);
 	add_remove_files(&partial);
 	refresh_cache(REFRESH_QUIET);
-	if (write_cache(fd, active_cache, active_nr) ||
-	    close_lock_file(&index_lock))
+	if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 		die(_("unable to write new_index file"));
 
-	fd = hold_lock_file_for_update(&false_lock,
-				       git_path("next-index-%"PRIuMAX,
-						(uintmax_t) getpid()),
-				       LOCK_DIE_ON_ERROR);
+	hold_lock_file_for_update(&false_lock,
+				  git_path("next-index-%"PRIuMAX,
+					   (uintmax_t) getpid()),
+				  LOCK_DIE_ON_ERROR);
 
 	create_base_index(current_head);
 	add_remove_files(&partial);
 	refresh_cache(REFRESH_QUIET);
 
-	if (write_cache(fd, active_cache, active_nr) ||
-	    close_lock_file(&false_lock))
+	if (write_locked_index(&the_index, &false_lock, CLOSE_LOCK))
 		die(_("unable to write temporary index file"));
 
 	discard_cache();