REVIEW 2 cited by
A Learned Cache Eviction Framework with Minimal Overhead
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent work shows the effectiveness of Machine Learning (ML) to reduce cache miss ratios by making better eviction decisions than heuristics. However, state-of-the-art ML caches require many predictions to make an eviction decision, making them impractical for high-throughput caching systems. This paper introduces Machine learning At the Tail (MAT), a framework to build efficient ML-based caching systems by integrating an ML module with a traditional cache system based on a heuristic algorithm. MAT treats the heuristic algorithm as a filter to receive high-quality samples to train an ML model and likely candidate objects for evictions. We evaluate MAT on 8 production workloads, spanning storage, in-memory caching, and CDNs. The simulation experiments show MAT reduces the number of costly ML predictions-per-eviction from 63 to 2, while achieving comparable miss ratios to the state-of-the-art ML cache system. We compare a MAT prototype system with an LRU-based caching system in the same setting and show that they achieve similar request rates.
Forward citations
Cited by 2 Pith papers
-
LearnedCache: eBPF-Integrated Perceptron-Based Eviction Policies for the Linux Page Cache
LearnedCache shows a quantized one-layer perceptron, trained on eBPF kernel traces and deployed through cache_ext, can beat FIFO page-cache eviction on some Filebench workloads.
-
Brame: Hierarchical Data Management Framework for Cloud-Edge-Device Collaboration
Brame groups relational tuples into workload-aware blocks and schedules block placement across cloud, edge, and terminal tiers, reporting improved query hit rates over data-aware baselines on two datasets.
Discussion (0). Continue with ORCID to comment.