The email sent will contain a link to this article, the article title, and an article excerpt (if available). For security reasons, your IP address will also be included in the sent email.
This is a guest post by Benjamin Manes, who did engineery things for Google and is now doing engineery things as CTO of Vector.
The previous article described the caching algorithms used by Caffeine, in particular the eviction and concurrency models. Since then we’ve made improvements to the eviction algorithm and explored a new approach towards expiration.
Eviction Policy
Window TinyLFU (W-TinyLFU) splits the policy into three parts: an admission window, a frequency filter, and the main region. By using a compact popularity sketch, the historic frequencies are cheap to retain and lookup. This allows for quickly discarding new arrivals that are unlikely to be used again, guarding the main region from cache pollution. The admission window provides a small region for recency bursts to avoid consecutive misses when an item is building up its popularity.
This structure works surprisingly well for many important workloads like database, search, and analytics. These cases are frequency-biased where a small admission window is desirable to filter aggressively...
Return to Article
