Delta Fair Sharing: Performance Isolation for Multi-Tenant Storage Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910003055558656 |
|---|---|
| author | Griggs, Tyler Ponnapalli, Soujanya Bali, Dev Ma, Wenjie DeLoye, James Cheng, Audrey Hong, Jaewan Crooks, Natacha Shenker, Scott Stoica, Ion Zaharia, Matei |
| author_facet | Griggs, Tyler Ponnapalli, Soujanya Bali, Dev Ma, Wenjie DeLoye, James Cheng, Audrey Hong, Jaewan Crooks, Natacha Shenker, Scott Stoica, Ion Zaharia, Matei |
| contents | Modern storage systems, often deployed to support multiple tenants in the cloud, must provide performance isolation. Unfortunately, traditional approaches such as fair sharing do not provide performance isolation for storage systems, because their resources (e.g., write buffers and read caches) exhibit high preemption delays. These delays lead to unacceptable spikes in client tail latencies, as clients may be forced to wait arbitrarily long to receive their fair share of resources.
We introduce Delta Fair Sharing, a family of algorithms for sharing resources with high preemption delays. These algorithms satisfy two key properties: $δ$-fairness, which bounds a client's delay in receiving its fair share of resources to $δ$ time units, and $δ$-Pareto-efficiency, which allocates unused resources to clients with unmet demand. Together, these properties capture resource-acquisition delays end-to-end, bound well-behaved clients' tail-latency spikes to $δ$ time units, and ensure high utilization. We implement such algorithms in FAIRDB, an extension of RocksDB. Our evaluation shows that FAIRDB isolates well-behaved clients from high-demand workloads better than state-of-the-art alternatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20030 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Delta Fair Sharing: Performance Isolation for Multi-Tenant Storage Systems Griggs, Tyler Ponnapalli, Soujanya Bali, Dev Ma, Wenjie DeLoye, James Cheng, Audrey Hong, Jaewan Crooks, Natacha Shenker, Scott Stoica, Ion Zaharia, Matei Databases Distributed, Parallel, and Cluster Computing Modern storage systems, often deployed to support multiple tenants in the cloud, must provide performance isolation. Unfortunately, traditional approaches such as fair sharing do not provide performance isolation for storage systems, because their resources (e.g., write buffers and read caches) exhibit high preemption delays. These delays lead to unacceptable spikes in client tail latencies, as clients may be forced to wait arbitrarily long to receive their fair share of resources. We introduce Delta Fair Sharing, a family of algorithms for sharing resources with high preemption delays. These algorithms satisfy two key properties: $δ$-fairness, which bounds a client's delay in receiving its fair share of resources to $δ$ time units, and $δ$-Pareto-efficiency, which allocates unused resources to clients with unmet demand. Together, these properties capture resource-acquisition delays end-to-end, bound well-behaved clients' tail-latency spikes to $δ$ time units, and ensure high utilization. We implement such algorithms in FAIRDB, an extension of RocksDB. Our evaluation shows that FAIRDB isolates well-behaved clients from high-demand workloads better than state-of-the-art alternatives. |
| title | Delta Fair Sharing: Performance Isolation for Multi-Tenant Storage Systems |
| topic | Databases Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.20030 |