Abstract: A clock distribution tree for a digital network is automatically established through the use of spanning tree computations at nodes of the network. The computations rely, at least in part, upon the exchange of clock distribution messages between the nodes of the network. Each clock distribution message includes information regarding a clock source available at the source node of the message. The clock distribution tree is hierarchical in nature, with nodes that are lower in the hierarchy (i.e., at a higher stratum level) extracting clock from links with nodes that are higher in the hierarchy (i.e., at a lower stratum level); this helps preserve the synchronous digital hierarchy of the network. The spanning tree computations involve a root selection process and a convergence test. The root selection process is made on the basis of configuration vectors exchanged as part of the clock distribution messages.