Redy-Reference-Cited by-同舟云学术

Redy

Published:2021-12 Issue:4 Volume:15 Page:766-779
ISSN:2150-8097
Container-title:Proceedings of the VLDB Endowment
language:en
Short-container-title:Proc. VLDB Endow.

Author:

Zhang Qizhen¹,Bernstein Philip A.²,Berger Daniel S.²,Chandramouli Badrish²

Affiliation:

1. University of Pennsylvania

2. Microsoft Research

Abstract

Redy is a cloud service that provides high performance caches using RDMA-accessible remote memory. An application can customize the performance of each cache with a service level objective (SLO) for latency and throughput. By using remote memory, it can leverage stranded memory and spot VM instances to reduce the cost of its caches and improve data center resource utilization. Redy automatically customizes the resource configuration for the given SLO, handles the dynamics of remote memory regions, and recovers from failures. The experimental evaluation shows that Redy can deliver its promised performance and robustness under remote memory dynamics in the cloud. We augment a production key-value store, FASTER, with a Redy cache. When the working set exceeds local memory, using Redy is significantly faster than spilling to SSDs.

Publisher

Association for Computing Machinery (ACM)

Subject

General Earth and Planetary Sciences,Water Science and Technology,Geography, Planning and Development

Link

https://dl.acm.org/doi/pdf/10.14778/3503585.3503587

Reference63 articles.

1. Connectx-6 single/dual-port adapter supporting 200Gb/s with VPI. https://www.nvidia.com/en-us/networking/infiniband-adapters/connectx-6 (visited on 12/24/2021). Connectx-6 single/dual-port adapter supporting 200Gb/s with VPI. https://www.nvidia.com/en-us/networking/infiniband-adapters/connectx-6 (visited on 12/24/2021).

2. Connectx®-3 pro en single/dual-port adapters 10/40/56gbe adapters w/ pci express 3.0. https://www.mellanox.com/products/ethernet-adapters/connectx-3-pro (visited on 12/24/2021). Connectx®-3 pro en single/dual-port adapters 10/40/56gbe adapters w/ pci express 3.0. https://www.mellanox.com/products/ethernet-adapters/connectx-3-pro (visited on 12/24/2021).

3. Fabric performance tools. https://docs.mellanox.com/display/winof2/Fabric+Performance+Utilities (visited on 12/24/2021). Fabric performance tools. https://docs.mellanox.com/display/winof2/Fabric+Performance+Utilities (visited on 12/24/2021).

4. Memcached. https://www.memcached.org/ (visited on 12/24/2021). Memcached. https://www.memcached.org/ (visited on 12/24/2021).

5. Nvidia mellanox connectx-5 single/dual-port adapter supporting 100Gb/s with VPI. https://www.nvidia.com/en-us/networking/infiniband-adapters/connectx-5/ (visited on 12/24/2021). Nvidia mellanox connectx-5 single/dual-port adapter supporting 100Gb/s with VPI. https://www.nvidia.com/en-us/networking/infiniband-adapters/connectx-5/ (visited on 12/24/2021).

Cited by 13 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Graph Neural Network-Based SLO-Aware Proactive Resource Autoscaling Framework for Microservices;IEEE/ACM Transactions on Networking;2024-08

2. DDS: DPU-Optimized Disaggregated Storage;Proceedings of the VLDB Endowment;2024-07

3. Optimizing LSM-based indexes for disaggregated memory;The VLDB Journal;2024-06-19

4. CXL and the Return of Scale-Up Database Engines;Proceedings of the VLDB Endowment;2024-06

5. Cowbird: Freeing CPUs to Compute by Offloading the Disaggregation of Memory;Proceedings of the ACM SIGCOMM 2023 Conference;2023-09