A tenant pressure-aware performance isolation scheme, called IP-Zone, is proposed that partitions users into independent regions and maximizes zone parallelism through cross-resource allocation and flexible address mapping and improves IOPS and throughput.
Abstract
In cloud computing, multi-tenant shared storage is widely used for efficiency. ZNS SSDs have become a popular choice due to their high throughput and low latency. However, they still face challenges: the zone structure is not exposed to tenants, making performance control difficult, and the multi-namespace design can lead to wasted performance when tenant workloads are highly imbalanced. This paper proposes a tenant pressure-aware performance isolation scheme, called IP-Zone, that partitions users into independent regions and maximizes zone parallelism through cross-resource allocation and flexible address mapping. For severely unbalanced loads, a complementary load-aware strategy dynamically reallocates bandwidth among tenants to improve SSD utilization. Experiments show that this scheme improves IOPS and throughput by 34.6% and 25.0% over traditional channel isolation, while average and tail latencies are reduced by 76.3% and 36.0% compared to black-box sharing.
Remote object stores are widely used in public and private clouds for their simplicity and reliability, but their high latency and transfer costs make local caching essential. While RAM caches are common, they become prohibitively expensive at scale, leading to the adoption of flash-based (SSD) caches. However, convent...
J. Ramsden, Sam Cheng, Hans Holmberg et al.· Proceedings of the 19th ACM...· 0 citations
Modern SSDs face a fundamental trade-off between reducing write amplification and maximizing flash-level parallelism. Conventional FTL schemes improve resource utilization through aggressive data distribution, but incur higher garbage collection overhead by intermixing data with different update behaviors. In contrast,...
Dongjun Lee, Han Jang, Youngbin Jin et al.· Proceedings of the 19th ACM...· 0 citations
Within the shared industry vision of AI-RAN, AI-and-RAN seeks to co-locate virtualized radio access network (vRAN) workloads and AI services on shared GPUs. This sharing is inherently asymmetric: vRAN workload is latency-critical, whereas the machine learning (ML) workload is a throughput-oriented, best-effort co-tenan...
Yun-Cheng Yao, Zhen-Zhou Qi, Jun-Yao Zheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.