SACache: Size-Aware Load Balancing for Large-Scale Storage Systems

Su, Yihong; Jin, Hang; Liu, Fang; Li, Weijun

doi:10.1007/978-3-030-78618-2_8

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, some worker threads are overloaded and become the performance bottleneck under skewed data access. This load imbalance is an inherent problem of partitioning-based architectures [17,63].…”

Section: Understanding Prism Performancementioning

confidence: 99%

Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices

Song

Kim

Monga

et al. 2023

Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems,

View full text Add to dashboard Cite

As data generation has been on an upward trend, storing vast volumes of data cost-effectively as well as efficiently accessing them is paramount. At the same time, today's storage landscape continues to diversify, from high-bandwidth storage devices such as NVMe SSDs to low-latency non-volatile memory (e.g., Intel Optane DCPMM). These heterogeneous storage devices have the potential to deliver high performance in terms of bandwidth and latency with cost efficiency, while achieving the performance and cost targets together still remains a challenging problem.We provide our solution, Prism, a novel key-value store that utilizes modern heterogeneous storage devices. Prism uses heterogeneous storage devices synergistically to harness the advantages of each storage device while suppressing their downsides. We devise new techniques to balance the latency-bandwidth tradeoff when reading from SSD. For ensuring multicore scalability and crash consistency of data across heterogeneous storage media, Prism proposes cross-storage concurrency control and cross-storage crash consistency protocols. Our evaluation shows that Prism outperforms state-of-the-art key-value stores by up to 13.1× with significantly lower tail latency.

show abstract

Section: Understanding Prism Performancementioning

confidence: 99%

Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices

Song

Kim

Monga

et al. 2023

Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems,

View full text Add to dashboard Cite

show abstract

“…Unequal distribution of workloads among processing nodes can result in hotspots and uneven utilization [ 44]. Achieving load distribution equity is essential for maintaining consistent performance.…”

Section: Load Distribution Disparitiesmentioning

confidence: 99%

Optimization of Performance in Cloud Data Streaming: Comprehensive Review

Hussein,

Hussein

2023

ijmst

View full text Add to dashboard Cite

With the proliferation of cloud computing, the landscape of data processing has undergone a transformative shift. Cloud data streaming, a linchpin of real-time data processing, has emerged as a critical enabler for organizations seeking timely insights and informed decision-making. However, optimizing the performance of cloud data streaming systems poses intricate challenges that necessitate exploration. This comprehensive review article navigates the multifaceted terrain of enhancing performance in cloud data streaming. It encompasses foundational concepts, performance evaluation metrics, prevalent challenges, advanced optimization strategies, illustrative case studies, comparative analysis of platforms, anticipatory trends, and directions for further research.

show abstract

SACache: Size-Aware Load Balancing for Large-Scale Storage Systems

Cited by 2 publications

References 8 publications

Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices

Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices

Optimization of Performance in Cloud Data Streaming: Comprehensive Review

Contact Info

Product

Resources

About