Study On Optimization Of Distributed Storage System For Social Network Service

The increasing popularity of photo sharing in social networking service(SNS) complicates the challenge of storing and transmitting large photo data for SNS providers. Distributed web caches are generally used by SNS providers to improve data transmission performance effectively. Two critical factors affect the efficiency of web caches: storage media and replacement algorithms. Solid-state drive(SSD) is often used in web caches given its good performance. Random write performance and SSD endurance are directly affected by the characteristic of write amplification; this characteristic is also related to replacement algorithms.The least recently used(LRU) algorithm effectively computes cache hit rate but induces severe write amplification. First in, first out(FIFO) method minimizes write amplification, whereas a weak hit rate increases bandwidth consumption. In this paper, we present a hybrid replacement strategy, namely, F-SkLRU. This strategy facilitates a good trade-off between performance and the cost of web cache. By expanding the eviction unit of FIFO to facilitate coarse-grained eviction operations. F-Sk LRU takes advantage of sequential writing to reduce SSD wear. Each eviction unit can store many items, items are separated into hot items and cold items according to time temporal and frequency. Hot items are saved when the erasure unit is erasing to improve hit rate. The parameter k in F-Sk LRU can be changed according to saved data to achieve highest performance.Simulation results show that F-SLRU can reduce bandwidth consumption by 14.11% to 23.4% in comparison with that of FIFO and LRU. The proposed strategy can also reduce the cost of SSD by 200% to 300% more than LRU can in general situations.