• Liana Valdez
• Farzana Yusuf
• Steven Lyons
• Eysler Paz
• Raju Rangaswami
• Jason Liu
• Ming Zhao
• Giri Narasimhan

Recent advances in machine learning open up new and attractive approaches 
for solving classic problems in computing systems. For storage systems, 
cache replacement is one such problem because of its enormous impact on 
performance. CACHEUS represents a new class of fully adaptive, 
machine-learned caching algorithms that utilize a combination of experts 
designed to address a variety of workload primitive types. The experts 
used by CACHEUS include the state-of-the-art ARC, LIRS and LFU, and two 
new ones – SR-LRU, a scan-resistant version of LRU, and CR-LFU, a 
churn-resistant version of LFU. CACHEUS using the newly proposed 
lightweight experts, SR-LRU and CR-LFU, is the most consistently performing 
caching algorithm across a range of workloads and cache sizes. Furthermore, 
CACHEUS enables augmenting state-of-the-art algorithms (e.g., LIRS, ARC) 
by combining it with a complementary cache replacement algorithm (e.g., 
LFU) to to better handle a wider variety of workload primitive types.

• Learning Cache Replacement with CACHEUS pdf
  Liana V. Rodriguez, Farzana Yusuf, Steven Lyons, Eysler Paz, Raju Rangaswami, Jason Liu, Ming Zhao, and Giri Narsimhan
  Proceedings of the USENIX Conference on File and Storage Technologies (FAST), 2021.

• Cacheus sources can be accessed at here. This repo includes the parsing code to run cache simulation with several workloads available on the SNIA Website such as FIU, MSR, Nexus 5 Smartphone, CloudCache and CloudVPS.

This work was supported in part by a NetApp Faculty Fellowship, and NSF grants CCF-1718335, CNS-1563883, and CNS-1956229.