Quality-aware schedulers for weak consistency key-value data stores

Xu, Chen; Sharaf, Mohamed A.; Zhou, Xiaofang; Zhou, Aoying

doi:10.1007/s10619-013-7136-4

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [20] used an on-demand selective method, Freshness/Tardiness (FIT), to maintain consistency and scalability using state-transfer updating. To manage the trade-off between latency and consistency, running transactions are selectively scheduled such that pending changes are applied.…”

Section: Related Workmentioning

confidence: 99%

“…To find the committed delay for successful transactions, this work customizes the updating transaction to obtain the beginning time, ending time, and data. Using the beginning and ending time, the duration of the transaction can be retrieved with different throughputs (10,20,30,40,50,60,70,80) operation/sec at each node. Figure 6 depicts the results of the average duration with each throughput.…”

Section: Total Transaction Delaymentioning

confidence: 99%

See 1 more Smart Citation

ODCS: On-Demand Hierarchical Consistent Synchronization Approach for the IoT

Saleh,

Alansari,

Hamiaz

et al. 2023

Electronics

View full text Add to dashboard Cite

An IoT data system is a time constraint in which some data needs to be serviced on or before its deadline. Distributed processing is one of the most latent sources in such systems and is considered a vital design concern. Many sources of delay in the IoT can affect the availability of data from different resources, which may cause missing data deadlines, resulting in a catastrophic effect. In fact, such systems are inherently distributed in nature and use distributed processing. The distributed processing permits different nodes to obtain the information from remote sites, which may take a long time to access the required data. Therefore, it is considered one of the most latent sources in such systems, which is considered a vital design concern. The typical recommended solution for this problem is to commit distributed transactions locally. Therefore, replication techniques are used to enhance the availability of data and consequently avoid the resulting latency. However, the use of local processing raises inconsistent periods. Therefore, this study proposes a new synchronization framework to minimize periods of temporal inconsistency. It permits several connected nodes to synchronize the shared data on demand concurrently without any need to use distributed synchronization, which consumes the system resource and raises its delay cost. The proposed framework aims to enhance the timely response of IoT real-time systems by minimizing the temporal inconsistency periods. The results indicate that the synchronization framework can be completed within a reasonable time period. They also depict improved consistency by minimizing the temporal inconsistency duration and increasing the chance of meeting critical time requirements.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Total Transaction Delaymentioning

confidence: 99%