1 files changed, 71 insertions, 0 deletions

diff --git a/bulk-checkin.c b/bulk-checkin.c
index ad855267d2..df451bdf42 100644
--- a/bulk-checkin.c
+++ b/bulk-checkin.c
@@ -3,15 +3,20 @@
  */
 #include "cache.h"
 #include "bulk-checkin.h"
+#include "lockfile.h"
 #include "repository.h"
 #include "csum-file.h"
 #include "pack.h"
 #include "strbuf.h"
+#include "string-list.h"
+#include "tmp-objdir.h"
 #include "packfile.h"
 #include "object-store.h"
 
 static int odb_transaction_nesting;
 
+static struct tmp_objdir *bulk_fsync_objdir;
+
 static struct bulk_checkin_packfile {
 	char *pack_tmp_name;
 	struct hashfile *f;
@@ -80,6 +85,40 @@ clear_exit:
 	reprepare_packed_git(the_repository);
 }
 
+/*
+ * Cleanup after batch-mode fsync_object_files.
+ */
+static void flush_batch_fsync(void)
+{
+	struct strbuf temp_path = STRBUF_INIT;
+	struct tempfile *temp;
+
+	if (!bulk_fsync_objdir)
+		return;
+
+	/*
+	 * Issue a full hardware flush against a temporary file to ensure
+	 * that all objects are durable before any renames occur. The code in
+	 * fsync_loose_object_bulk_checkin has already issued a writeout
+	 * request, but it has not flushed any writeback cache in the storage
+	 * hardware or any filesystem logs. This fsync call acts as a barrier
+	 * to ensure that the data in each new object file is durable before
+	 * the final name is visible.
+	 */
+	strbuf_addf(&temp_path, "%s/bulk_fsync_XXXXXX", get_object_directory());
+	temp = xmks_tempfile(temp_path.buf);
+	fsync_or_die(get_tempfile_fd(temp), get_tempfile_path(temp));
+	delete_tempfile(&temp);
+	strbuf_release(&temp_path);
+
+	/*
+	 * Make the object files visible in the primary ODB after their data is
+	 * fully durable.
+	 */
+	tmp_objdir_migrate(bulk_fsync_objdir);
+	bulk_fsync_objdir = NULL;
+}
+
 static int already_written(struct bulk_checkin_packfile *state, struct object_id *oid)
 {
 	int i;
@@ -274,6 +313,37 @@ static int deflate_to_pack(struct bulk_checkin_packfile *state,
 	return 0;
 }
 
+void prepare_loose_object_bulk_checkin(void)
+{
+	/*
+	 * We lazily create the temporary object directory
+	 * the first time an object might be added, since
+	 * callers may not know whether any objects will be
+	 * added at the time they call begin_odb_transaction.
+	 */
+	if (!odb_transaction_nesting || bulk_fsync_objdir)
+		return;
+
+	bulk_fsync_objdir = tmp_objdir_create("bulk-fsync");
+	if (bulk_fsync_objdir)
+		tmp_objdir_replace_primary_odb(bulk_fsync_objdir, 0);
+}
+
+void fsync_loose_object_bulk_checkin(int fd, const char *filename)
+{
+	/*
+	 * If we have an active ODB transaction, we issue a call that
+	 * cleans the filesystem page cache but avoids a hardware flush
+	 * command. Later on we will issue a single hardware flush
+	 * before renaming the objects to their final names as part of
+	 * flush_batch_fsync.
+	 */
+	if (!bulk_fsync_objdir ||
+	    git_fsync(fd, FSYNC_WRITEOUT_ONLY) < 0) {
+		fsync_or_die(fd, filename);
+	}
+}
+
 int index_bulk_checkin(struct object_id *oid,
 		       int fd, size_t size, enum object_type type,
 		       const char *path, unsigned flags)
@@ -292,6 +362,7 @@ void begin_odb_transaction(void)
 
 void flush_odb_transaction(void)
 {
+	flush_batch_fsync();
 	flush_bulk_checkin_packfile(&bulk_checkin_packfile);
 }