Fifo queues are all you need for cache eviction

J Yang, Y Zhang, Z Qiu, Y Yue, R Vinayak - Proceedings of the 29th …, 2023‏ - dl.acm.org
As a cache eviction algorithm, FIFO has a lot of attractive properties, such as simplicity,
speed, scalability, and flash-friendliness. The most prominent criticism of FIFO is its low …

A large-scale analysis of hundreds of in-memory key-value cache clusters at twitter

J Yang, Y Yue, KV Rashmi - ACM Transactions on Storage (TOS), 2021‏ - dl.acm.org
Modern web services use in-memory caching extensively to increase throughput and reduce
latency. There have been several workload analyses of production systems that have fueled …

Faa $ t: A transparent auto-scaling cache for serverless applications

F Romero, GI Chaudhry, Í Goiri, P Gopa… - Proceedings of the …, 2021‏ - dl.acm.org
Function-as-a-Service (FaaS) has become an increasingly popular way for users to deploy
their applications without the burden of managing the underlying infrastructure. However …

The {CacheLib} caching engine: Design and experiences at scale

B Berg, DS Berger, S McAllister, I Grosof… - … USENIX Symposium on …, 2020‏ - usenix.org
Web services rely on caching at nearly every layer of the system architecture. Commonly,
each cache is implemented and maintained independently by a distinct team and is highly …

[HTML][HTML] Learning relaxed belady for content distribution network caching

Z Song, DS Berger, K Li, A Shaikh, W Lloyd… - … USENIX Symposium on …, 2020‏ - usenix.org
NSDI '20 List of Accepted Papers | USENIX Sign In Conferences Attend Registration
Information Registration Discounts Student Grant Application Diversity Grant Application …

{SIEVE} is simpler than {LRU}: an efficient {Turn-Key} eviction algorithm for web caches

Y Zhang, J Yang, Y Yue, Y Vigfusson… - 21st USENIX Symposium …, 2024‏ - usenix.org
Caching is an indispensable technique for low-cost and fast data serving. The eviction
algorithm, at the heart of a cache, has been primarily designed to maximize efficiency …

{GL-Cache}: Group-level learning for efficient and high-performance caching

J Yang, Z Mao, Y Yue, KV Rashmi - 21st USENIX Conference on File …, 2023‏ - usenix.org
Web applications rely heavily on software caches to achieve low-latency, high-throughput
services. To adapt to changing workloads, three types of learned caches (learned evictions) …

Approximate caching for efficiently serving {Text-to-Image} diffusion models

S Agarwal, S Mitra, S Chakraborty, S Karanam… - … USENIX Symposium on …, 2024‏ - usenix.org
Text-to-image generation using diffusion models has seen explosive popularity owing to
their ability in producing high quality images adhering to text prompts. However, diffusion …

Kangaroo: Caching billions of tiny objects on flash

S McAllister, B Berg, J Tutuncu-Macias, J Yang… - Proceedings of the …, 2021‏ - dl.acm.org
Many social-media and IoT services have very large working sets consisting of billions of
tiny (≈ 100 B) objects. Large, flash-based caches are important to serving these working …

Baleen:{ML} admission & prefetching for flash caches

DLK Wong, H Wu, C Molder, S Gunasekar… - … USENIX Conference on …, 2024‏ - usenix.org
Flash caches are used to reduce peak backend load for throughput-constrained data center
services, reducing the total number of backend servers required. Bulk storage systems are a …