SwapKV: A Hotness Aware In-memory Key-Value Store for Hybrid Memory Systems

Cui, Lixiao; He, Kewen; Li, Yusen; Zhang, Jiachen; Wang, Gang; Liu, Xao-Guang

doi:10.1109/tkde.2021.3077264

Cited by 6 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, memory provides a relatively compact and quickly accessible memory structure. However, while this technique is suitable for small-scale and limited memory management, it suffers from system inefficiency when applied to large-scale memory management due to the frequent increase in processing count and the increase in management points [21]. The platform proposed in this paper enables large-scale memory management through large-scale message processing by organizing and utilizing a message buffer pool in the memory in addition to small-scale.…”

Section: ) Data Page Buffer Pool Techniquesmentioning

confidence: 99%

RMPF: Real-Time Message Processing Framework on Multi-Service Domains

Kim,

Han,

Jeong

2024

IEEE Access

View full text Add to dashboard Cite

In the world of real-time computing, there is a demand for platforms that deliver both speed and efficiency while conserving hardware resources. High reliability applications typically use dedicated platforms for their inherent reliability, but they are more expensive. On the other hand, traditional generalpurpose platforms are cheaper but suffer from wasted hardware resources when processing messages, hindering distributed processing and process monitoring. To address these limitations, this paper presents the Real-time Message Processing Framework on Multi-service Domains (RMPF), an innovative integrated platform for real-time distributed message processing on multi-service domains. The platform supports a scalable and flexible multi-layer architecture by providing modularity that allows each layer to be designed and updated independently. The interaction between each layer enables real-time distributed message processing and distributed management of multi-service processing in a city-main based, high-speed distributed environment. By accelerating message processing, using a dedicated buffer pool created for each application process, and monitoring the status of all messages in the buffer, the high reliability inherent in dedicated platforms is ensured. In addition, it minimizes the waste of hardware resources by running application processes as daemons in buffer pools. In particular, to provide domain-based multiservice, it supports RMPF grouping by task to distribute tasks to appropriate domains to eliminate system bottlenecks. It is also implemented in a modular way to achieve both scalability and adaptability through various multiservice distributed management schemes such as multiservice API, recovery, monitoring, and multiservice provisioning.INDEX TERMS Multi service, distributed message processing, unified platform, memory management, multi domain.

show abstract

Section: ) Data Page Buffer Pool Techniquesmentioning

confidence: 99%

RMPF: Real-Time Message Processing Framework on Multi-Service Domains

Kim,

Han,

Jeong

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

HaCache: A Hybrid Adaptive Cache for Persistent Memory Based Key-Value Systems

Cui

Wang

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Challenges and future directions for energy, latency, and lifetime improvements in NVMs

Kargar

Nawab

2022

Distrib Parallel Databases

View full text Add to dashboard Cite

Recently, non-volatile memory (NVM) technology has revolutionized the landscape of memory systems. With many advantages, such as non volatility and near zero standby power consumption, these byte-addressable memory technologies are taking the place of DRAMs. Nonetheless, they also present some limitations, such as limited write endurance, which hinders their widespread use in today’s systems. Furthermore, adjusting current data management systems to embrace these new memory technologies and all their potential is proving to be a nontrivial task. Because of this, a substantial amount of research has been done, from both the database community and the storage systems community, that tries to improve various aspects of NVMs to integrate these technologies into the memory hierarchy. In this work, which is the extended version of Kargar and Nawab (Proc. VLDB Endowment 14(12):3194–3197, 2021), we explore state-of-the-art work on deploying NVMs in database and storage systems communities and the ways their limitations are being handled within these communities. In particular, we focus on (1) the challenges that are related to high energy consumption, low write endurance and asymmetric read/write costs and (2) how these challenges can be solved using hardware and software solutions, especially by reducing the number of bit flips in write operations. We believe that this area has not gained enough attention in the data management community and this tutorial will provide information on how to integrate recent advances from the NVM storage community into existing and future data management systems.

show abstract

SwapKV: A Hotness Aware In-memory Key-Value Store for Hybrid Memory Systems

Cited by 6 publications

References 22 publications

RMPF: Real-Time Message Processing Framework on Multi-Service Domains

RMPF: Real-Time Message Processing Framework on Multi-Service Domains

HaCache: A Hybrid Adaptive Cache for Persistent Memory Based Key-Value Systems

Challenges and future directions for energy, latency, and lifetime improvements in NVMs

Contact Info

Product

Resources

About