Optimal checkpointing and local recording for domino-free rollback recovery

Venkatesh, K.; Radhakrishnan, T.; Li, H.F.

doi:10.1016/0020-0190(87)90203-1

Cited by 61 publications

(20 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an optimistic algorithm in the sense that it performs well, when errors are infrequent. Independent checkpoint algorithms have the benefit that no coordination between the members of a distributed system is required, but may suffer from the "domino effect' [36]'. The "domino effect" occurs when two or more members of the system keep rolling back to previously taken checkpoints in an attempt to reach a globally consistent state, leading to unnecessary delays in the completion of an action.…”

Section: Coordinated Checkpointingmentioning

confidence: 99%

Self-healing multitier architectures using cascading rescue points

Zavou

Portokalidis

Keromytis

2012

Proceedings of the 28th Annual Computer Security Applications Conference

View full text Add to dashboard Cite

Software bugs and vulnerabilities cause serious problems to both home users and the Internet infrastructure, limiting the availability of Internet services, causing loss of data, and reducing system integrity. Software self-healing using rescue points (RPs) is a known mechanism for recovering from unforeseen errors. However, applying it on multitier architectures can be problematic because certain actions, like transmitting data over the network, cannot be undone. We propose cascading rescue points (CRPs) to address the state inconsistency issues that can arise when using traditional RPs to recover from errors in interconnected applications. With CRPs, when an application executing within a RP transmits data, the remote peer is notified to also perform a checkpoint, so the communicating entities checkpoint in a coordinated, but loosely coupled way. Notifications are also sent when RPs successfully complete execution, and when recovery is initiated, so that the appropriate action is performed by remote parties. We developed a tool that implements CRPs by dynamically instrumenting binaries and transparently injecting notifications in the already established TCP channels between applications. We tested our tool with various applications, including the MySQL and Apache servers, and show that it allows them to successfully recover from errors, while incurring moderate overhead between 4.54% and 71.56%.

show abstract

Section: Coordinated Checkpointingmentioning

confidence: 99%

Self-healing multitier architectures using cascading rescue points

Zavou

Portokalidis

Keromytis

2012

Proceedings of the 28th Annual Computer Security Applications Conference

View full text Add to dashboard Cite

show abstract

“…However, in this approach because of the absence of any coordination among the processes there may not exist a recent consistent global checkpoint which may cause a rollback of the computation. This is known as domino effect (B. Randell, 1975;K. Venkatesh et al, 1987).…”

Section: Introductionmentioning

confidence: 99%

A Low-Overhead Non-Block Check Pointing and Recovery Approach for Mobile Computing Environment

Gupta¹,

Liu²,

Koneru³

2012

Advances and Applications in Mobile Computing

View full text Add to dashboard Cite

“…onat. [7]ompnicatioy nhisitivedependencytrackiandiensera Only corresponding checkpoints with ordinal numbers n Z. et al [71 employ transitive dependency tracking and insert a where n is an integer, are required to be consistent with each checkpoint before processing any message that introduces other for bounding rollback propagation. Overhead anala new dependency.…”

mentioning

confidence: 99%

Lazy Checkpoint Coordination for Bounding Rollback Propagation

Wang¹,

Fuchs²

1993

View full text Add to dashboard Cite

Abstractshown that logging a nondeterministic event equivalently places a logical checkpoint [18] trace-driven simulation for several parallel programs isWe will use the term eager checkpoint coordination for used to evaluate the benefits of the proposed scheme.the coordination action performed when checkpoints are initiated, as described above. In contrast. processes in a system with lazy checkpoint coordination only coordinate

show abstract

Optimal checkpointing and local recording for domino-free rollback recovery

Cited by 61 publications

References 4 publications

Self-healing multitier architectures using cascading rescue points

Self-healing multitier architectures using cascading rescue points

A Low-Overhead Non-Block Check Pointing and Recovery Approach for Mobile Computing Environment

Lazy Checkpoint Coordination for Bounding Rollback Propagation

Contact Info

Product

Resources

About