Evaluating Dynamics and Bottlenecks of Memory Collaboration in Cluster Systems

Samih, Ahmad; Ren, Wei; Maciocco, Christian; Tai, Tsung-Yuan Charlie; Duan, Ronghui; Duan, Jiangang; Solihin, Yan

doi:10.1109/ccgrid.2012.59

Cited by 4 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Memory Disaggregation Systems. In last few decades, many software systems tried to leverage remote machine's memory for paging [1,22,26,28,33,40,42,46,50,58], for a global virtual memory abstraction [10,27,38], and to create distributed data stores [25,37,43,52]. There are also proposals for hardware-based remote access to disaggregated memory using PCIe interconnects [44] and extended NUMA fabric [51].…”

Section: Related Workmentioning

confidence: 99%

Mitigating the Performance-Efficiency Tradeoff in Resilient Memory Disaggregation

Lee¹,

Maruf²,

Chowdhury³

et al. 2019

Preprint

View full text Add to dashboard Cite

Memory disaggregation has received attention in recent years as a promising idea to reduce the total cost of ownership (TCO) of memory in modern datacenters. However, relying on remote memory expands an application's failure domain and makes it susceptible to tail latency variations. In attempts to making disaggregated memory resilient, stateof-the-art solutions face the classic tradeoff between performance and efficiency: some double the memory overhead of disaggregation by replicating to remote memory, while many others limit performance by replicating to the local disk.We present Hydra, a configurable, erasure-coded resilience mechanism for common memory disaggregation solutions. It can transparently handle uncertainties arising from remote failures, evictions, memory corruptions, and stragglers from network imbalance with a significantly better performanceefficiency tradeoff than the state-of-the-art. We design a finetuned data path to achieve single µs read/write latency to remote memory, develop decentralized algorithms for clusterwide memory management, and analyze how to select parameters to mitigate independent and correlated uncertainties. Our integration of Hydra with two major memory disaggregation systems and evaluation on a 50-machine RDMA cluster demonstrates that it achieves the best of both worlds: it improves the latency and throughput of memory-intensive applications by up to 64.78× and 20.61×, respectively, over the state-of-the-art disk backup-based solution. At the same time, it provides performance similar to that of in-memory replication with 1.6× lower memory overhead.

show abstract

Section: Related Workmentioning

confidence: 99%

Mitigating the Performance-Efficiency Tradeoff in Resilient Memory Disaggregation

Lee¹,

Maruf²,

Chowdhury³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Remote Memory Solutions. A good number of software systems have been proposed over the years to access remote machine's memory for paging [1, 19,21,25,31,44,45,50,55,64,65], global virtual machine abstraction [6,24,42], and distributed data stores and file systems [9,20,41,47,58]. Hardware-based remote access using PCIe interconnects [48] or extended NUMA memory fabric [56] are also proposed to disaggregate memory.…”

Section: Related Workmentioning

confidence: 99%

Effectively Prefetching Remote Memory with Leap

Maruf¹,

Chowdhury²

2019

Preprint

View full text Add to dashboard Cite

Memory disaggregation over RDMA can improve the performance of memory-constrained applications by replacing disk swapping with remote memory accesses. However, state-ofthe-art memory disaggregation solutions still use data path components designed for slow disks. As a result, applications experience remote memory access latency significantly higher than that of the underlying low-latency network, which itself is too high for many applications.In this paper, we propose Leap, a prefetching solution for remote memory accesses due to memory disaggregation. At its core, Leap employs an online, majority-based prefetching algorithm, which increases the page cache hit rate. We complement it with a lightweight and efficient data path in the kernel that isolates each application's data path to the disaggregated memory and mitigates latency bottlenecks arising from legacy throughput-optimizing operations. Integration of Leap in the Linux kernel improves the median and tail remote page access latencies of memory-bound applications by up to 104.04× and 22.62×, respectively, over the default data path. This leads to up to 10.16× performance improvements for applications using disaggregated memory in comparison to the state-of-the-art solutions.

show abstract

FluidMem: Full, Flexible, and Fast Memory Disaggregation for the Cloud

Caldwell

Goodarzy

et al. 2020

2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

Evaluating Dynamics and Bottlenecks of Memory Collaboration in Cluster Systems

Cited by 4 publications

References 21 publications

Mitigating the Performance-Efficiency Tradeoff in Resilient Memory Disaggregation

Mitigating the Performance-Efficiency Tradeoff in Resilient Memory Disaggregation

Effectively Prefetching Remote Memory with Leap

FluidMem: Full, Flexible, and Fast Memory Disaggregation for the Cloud

Contact Info

Product

Resources

About