Abstract
This paper analyzes the relationship between a distributed checkpoint/rollback scheme based on causal logging, called Manetho, and a reversible concurrent model of computation, based on the \(\pi \)-calculus with imperative rollback developed by Lanese et al. in [14]. We show a rather tight relationship between rollback based on causal logging as performed in Manetho and the rollback algorithm underlying the calculus in [14]. Our main result is that the latter can faithfully simulate Manetho, where the notion of simulation we use is that of weak barbed simulation, and that the converse only holds if possible rollbacks in are restricted.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The description of the Manetho protocol differs slightly between the publication [8] and Elnozahy’s PhD thesis [6]. In particular, the latter involves a coordinating checkpointing scheme, which is not the case in the former. For the sake of simplicity, in this paper we follow the description in [8]. Checkpoint coordination in any case is not necessary for the correct operation of the recovery process in a causal logging checkpoint/rollback scheme. In [6] it is essentially used to simplify the garbage collection of recovery information.
- 2.
In particular: \(X\{^Y/_X\}\{^Z/_Y\} = Z\) and \(X\{^{Y,Z}/_{X,Y}\} = Y\).
- 3.
For simplicity, we let this choice be non-deterministic, but we could easily extend the syntax of \(\text{ lr- }\pi {}\) to accommodate e.g. imperative rollback instructions as in [14].
References
Aggarwal, D., Kiehn, A.: Analyzing mutable checkpointing via invariants. In: Dastani, M., Sirjani, M. (eds.) FSEN 2015. LNCS, vol. 9392, pp. 176–190. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24644-4_12
Cao, G., Singhal, M.: Checkpointing with mutable checkpoints. Theor. Comput. Sci. 290(2), 1127–1148 (2003)
Chothia, T., Duggan, D.: Abstractions for fault-tolerant global computing. Theor. Comput. Sci. 322(3), 567–613 (2004)
Cristescu, I., Krivine, J., Varacca, D.: A compositional semantics for the reversible p-calculus. In: 28th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS). IEEE Computer Society (2013)
Danos, V., Krivine, J.: Reversible communicating systems. In: Gardner, P., Yoshida, N. (eds.) CONCUR 2004. LNCS, vol. 3170, pp. 292–307. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28644-8_19
Elnozahy, E.N.: Manetho: fault-tolerance in distributed systems using rollback-recovery and process replication. Ph.D. thesis, Rice University, TX, USA (1993)
Elnozahy, E.N., Alvisi, L., Wang, Y.M., Johnson, D.B.: A survey of rollback-recovery protocols in message-passing systems. ACM Comput. Surv. 34(3), 375–408 (2002)
Elnozahy, E.N., Zwaenepoel, W.: Manetho: transparent rollback-recovery with low overhead, limited rollback and fast output commit. IEEE Trans. Comput. 41(5), 526–531 (1992)
Field, J., Varela, C.A.: Transactors: a programming model for maintaining globally consistent distributed state in unreliable environments. In: 32nd ACM Symposium on the Principles of Programming Languages (POPL). ACM (2005)
Giachino, E., Lanese, I., Mezzina, C.A., Tiezzi, F.: Causal-consistent rollback in a tuple-based language. J. Log. Algebr. Methods Program. 88, 99–120 (2017)
Hélary, J.M., Netzer, R.H.B., Raynal, M.: Consistency issues in distributed checkpoints. IEEE Trans. Softw. Eng. 25(2), 274–281 (1999)
Lanese, I., Lienhardt, M., Mezzina, C.A., Schmitt, A., Stefani, J.-B.: Concurrent flexible reversibility. In: Felleisen, M., Gardner, P. (eds.) ESOP 2013. LNCS, vol. 7792, pp. 370–390. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37036-6_21
Lanese, I., Mezzina, C.A., Stefani, J.-B.: Reversing higher-order pi. In: Gastin, P., Laroussinie, F. (eds.) CONCUR 2010. LNCS, vol. 6269, pp. 478–493. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15375-4_33
Lanese, I., Mezzina, C.A., Schmitt, A., Stefani, J.-B.: Controlling reversibility in higher-order pi. In: Katoen, J.-P., König, B. (eds.) CONCUR 2011. LNCS, vol. 6901, pp. 297–311. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23217-6_20
Lanese, I., Mezzina, C.A., Stefani, J.-B.: Reversibility in the higher-order \(\pi \)-calculus. Theor. Comput. Sci. 625, 25–84 (2016)
Leeman, G.B.: A formal approach to undo operations in programming languages. ACM Trans. Program. Lang. Syst. 8(1), 50–87 (1986)
Milner, R., Sangiorgi, D.: Barbed bisimulation. In: Kuich, W. (ed.) ICALP 1992. LNCS, vol. 623, pp. 685–695. Springer, Heidelberg (1992). https://doi.org/10.1007/3-540-55719-9_114
Nishida, N., Palacios, A., Vidal, G.: A reversible semantics for Erlang. In: Hermenegildo, M.V., Lopez-Garcia, P. (eds.) LOPSTR 2016. LNCS, vol. 10184, pp. 259–274. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-63139-4_15
Perumalla, K.S., Park, A.J.: Reverse computation for rollback-based fault tolerance in large parallel systems - evaluating the potential gains and systems effects. Cluster Comput. 17(2), 303–313 (2014)
Vassor, M., Stefani, J.B.: A comparison between stable causal log (Manetho) and a modified roll-pi calculus (2018). https://team.inria.fr/spades/long-version-checkpoint-vs-reversibility/
Ziarek, L., Jagannathan, S.: Lightweight checkpointing for concurrent ML. J. Funct. Program. 20(2), 137–173 (2010)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Vassor, M., Stefani, JB. (2018). Checkpoint/Rollback vs Causally-Consistent Reversibility. In: Kari, J., Ulidowski, I. (eds) Reversible Computation. RC 2018. Lecture Notes in Computer Science(), vol 11106. Springer, Cham. https://doi.org/10.1007/978-3-319-99498-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-99498-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99497-0
Online ISBN: 978-3-319-99498-7
eBook Packages: Computer ScienceComputer Science (R0)