Operating systems both old and new are reliant on the venerable hierarchical file system. For some time now, however, attempts have been made to either define new file systems or to bolt on applications that offer much improved functionality to attach and use metadata. This is because researchers have shown that traditional file systems are not able to meet users' needs in terms of organising large numbers of files effectively, and to support expeditious retrieval of those files when they are needed at a later time.Numerous proposals for post-hierarchical file management systems have been described in the literature; researchers focus on different dimensions of such systems in order to solve or reduce identified limitations. In some cases this leads to significantly different file system architectures, while in other cases new functionality is added on top of a traditional system through special purpose userspace applications. Orthogonally, some proposals focus on tags while others favour named attribute-value pairs. Still other choices are, seemingly, made in an ad hoc and often implicit manner. This paper investigates the different dimensions and associated choices that participate in the proposal of new approaches and that affect their ability to improve on current systems. The Cartesian product of those dimensions and options forms a large design space; we map some of the existing literature onto that design space and discuss approaches to evaluate new proposals.