Robert Stewart (Heriot-Watt University), Patrick Maier (University of Glasgow) & Phil Trinder (University of Glasgow).
Accepted for publication in The Journal of Functional Programming, published by Cambridge University Press.
Reliability is set to become a major concern on emergent large-scale architectures. While there are many parallel languages, and indeed many parallel functional languages, very few address reliability. The notable exception is the widely emulated Erlang distributed actor model that provides explicit supervision and recovery of actors with isolated state.
We investigate scalable transparent fault tolerant functional computation with automatic supervision and recovery of tasks. We do so by developing HdpH-RS, a variant of the Haskell distributed parallel Haskell (HdpH) DSL with Reliable Scheduling. Extending the distributed work stealing protocol of HdpH for task supervision and recovery is challenging. To eliminate elusive concurrency bugs, we validate the HdpH-RS work stealing protocol using the SPIN model checker.
HdpH-RS differs from the actor model in that its principal entities are tasks, i.e. independent stateless computations, rather than isolated stateful actors. Thanks to statelessness, fault recovery can be performed automatically and entirely hidden in the HdpH-RS runtime system. Statelessness is also key for proving a crucial property of the semantics of HdpH-RS: fault recovery does not change the result of the program, akin to deterministic parallelism.
HdpH-RS provides a simple distributed fork/join-style programming model, with minimal exposure of fault tolerance at the language level, and a library of higher level abstractions such as algorithmic skeletons. In fact, the HdpH-RS DSL is exactly the same as the HdpH DSL, hence users can opt in or out of fault tolerant execution without any refactoring.
Computations in HdpH-RS are always as reliable as the root node, no matter how many nodes and cores are actually used. We benchmark HdpH-RS on conventional clusters and an HPC platform: all benchmarks survive Chaos Monkey random fault injection; the system scales well e.g. up to 1400 cores on the HPC; reliability and recovery overheads are consistently low even at scale.
Material on these pages is copyright Cambridge University Press or reproduced with permission from other copyright owners. It may be downloaded and printed for personal reference, but not otherwise copied, altered in any way or transmitted to others (unless explicitly stated otherwise) without the written permission of Cambridge University Press. Hypertext links to other Web locations are for the convenience of users and do not constitute any endorsement or authorisation by Cambridge University Press.