E3:{Energy-Efficient} microservices on {SmartNIC-Accelerated} servers

M Liu, S Peter, A Krishnamurthy… - 2019 USENIX Annual …, 2019 - usenix.org
We investigate the use of SmartNIC-accelerated servers to execute microservice-based
applications in the data center. By offloading suitable microservices to the SmartNIC's low …

Software-defined “hardware” infrastructures: A survey on enabling technologies and open research directions

A Roozbeh, J Soares, GQ Maguire… - … Surveys & Tutorials, 2018 - ieeexplore.ieee.org
This paper provides an overview of software-defined “hardware” infrastructures (SDHI).
SDHI builds upon the concept of hardware (HW) resource disaggregation. HW resource …

Flash storage disaggregation

A Klimovic, C Kozyrakis, E Thereska, B John… - Proceedings of the …, 2016 - dl.acm.org
PCIe-based Flash is commonly deployed to provide datacenter applications with high IO
rates. However, its capacity and bandwidth are often underutilized as it is difficult to design …

Exploiting combined locality for {Wide-Stripe} erasure coding in distributed storage

Y Hu, L Cheng, Q Yao, PPC Lee, W Wang… - … USENIX Conference on …, 2021 - usenix.org
Erasure coding is a low-cost redundancy mechanism for distributed storage systems by
storing stripes of data and parity chunks. Wide stripes are recently proposed to suppress the …

Shoal: A network architecture for disaggregated racks

V Shrivastav, A Valadarsky, H Ballani, P Costa… - … USENIX Symposium on …, 2019 - usenix.org
Disaggregated racks comprise a dense cluster of separate pools of compute, memory and
storage blades, all inter-connected through an internal network within a single rack …

The five-minute rule 30 years later and its impact on the storage hierarchy

R Appuswamy, G Graefe, R Borovica-Gajic… - Communications of the …, 2019 - dl.acm.org
The five-minute rule 30 years later and its impact on the storage hierarchy Page 1 114
COMMUNICATIONS OF THE ACM | NOVEMBER 2019 | VOL. 62 | NO. 11 contributed articles …

Optimizing network performance in distributed machine learning

L Mai, C Hong, P Costa - 7th USENIX Workshop on Hot Topics in Cloud …, 2015 - usenix.org
To cope with the ever growing availability of training data, there have been several
proposals to scale machine learning computation beyond a single server and distribute it …

Project Silica: towards sustainable cloud archival storage in glass

P Anderson, EB Aranas, Y Assaf, R Behrendt… - Proceedings of the 29th …, 2023 - dl.acm.org
Sustainable and cost-effective long-term storage remains an unsolved problem. The most
widely used storage technologies today are magnetic (hard disk drives and tape). They use …

Composable architecture for rack scale big data computing

CS Li, H Franke, C Parris, B Abali, M Kesavan… - Future Generation …, 2017 - Elsevier
The rapid growth of cloud computing, both in terms of the spectrum and volume of cloud
workloads, necessitates re-visiting the traditional rack-mountable servers based datacenter …

OligoArchive: Using DNA in the DBMS storage hierarchy

R Appuswamy, K Lebrigand, P Barbry… - Biennal Conference on …, 2019 - hal.science
The demand for data-driven decision making coupled with need to retain data to meet
regulatory compliance requirements has resulted in a rapid increase in the amount of …