FAST: near real-time searchable data analytics for the cloud

摘要: With the explosive growth in data volume and complexity increasing need for highly efficient searchable analytics, existing cloud storage systems have largely failed to offer an adequate capability real-time analytics. Since true value or worth of heavily depends on how efficiently analytics can be carried out (near-) real-time, large fractions end up with their values being lost significantly reduced due staleness. To address this problem, we propose a near-real-time cost-effective methodology, called FAST. The idea behind FAST is explore exploit semantic correlation within among datasets via correlation-aware hashing manageable flat-structured addressing reduce processing latency, while incurring acceptably small loss data-search accuracy. property enables rapid identification correlated files significant narrowing scope processed. supports several types which implemented systems. We conduct real-world use case children reported missing extremely crowded environment (e.g., popular scenic spot peak tourist day) are identified timely fashion by analyzing 60 million images using Extensive experimental results demonstrate efficiency efficacy performance improvements energy savings.