Facebook Opens Up CacheLib As Their New Caching Engine
Facebook last week formally announced CacheLib as their new open-source caching engine designed for web scale services and to make for effective non-volatile memory caching to offset the increasing costs of DRAM.
CacheLib's development was motivated in part by increasing prices around system memory. The Facebook announcement noted, "As traditional dynamic random-access memory (DRAM) caches become more expensive and require more power to scale, companies like Facebook are exploring hardware choices such as non-volatile memory (NVM) drives to augment their caching systems. This DRAM and NVM hybrid model is a step forward, but innovative caching designs are needed to harness the full potential of the hybrid cache."
CacheLib is C++ based and is a pluggable, in-process caching engine. CacheLib is being used now by more than 70 large-scale systems at Facebook from their social graph to CDN.
Those wanting to learn more about this open-source caching engine can read Facebook Engineering's announcement. There is also a project site at Cachelib.org and the Apache 2.0 licensed code is hosted on GitHub.
CacheLib's development was motivated in part by increasing prices around system memory. The Facebook announcement noted, "As traditional dynamic random-access memory (DRAM) caches become more expensive and require more power to scale, companies like Facebook are exploring hardware choices such as non-volatile memory (NVM) drives to augment their caching systems. This DRAM and NVM hybrid model is a step forward, but innovative caching designs are needed to harness the full potential of the hybrid cache."
CacheLib is C++ based and is a pluggable, in-process caching engine. CacheLib is being used now by more than 70 large-scale systems at Facebook from their social graph to CDN.
Those wanting to learn more about this open-source caching engine can read Facebook Engineering's announcement. There is also a project site at Cachelib.org and the Apache 2.0 licensed code is hosted on GitHub.
4 Comments