We present efficient locking mechanisms for hierarchical data structures. Several applications work on an abstract hierarchy of objects, and a parallel execution on this hierarchy necessitates synchronization across workers operating on different parts of the hierarchy. Existing synchronization mechanisms are too coarse, too inefficient, or too ad hoc, resulting in reduced or unpredictable amount of concurrency.We propose a new locking approach based on the structural properties of the underlying hierarchy.We show that the developed techniques are efficient evenwhen the hierarchy is an arbitrary graph. Theoretically,we present our approach as a locking-cost-minimizing instance of a generic algebraic model of synchronization for hierarchies. Using STMBench7, we illustrate considerable reduction in the locking cost, resulting in an average throughput improvement of 42%. © 2017 ACM.