Resource-Aware Availability Enhancement Mechanism of Riak TS

The dependability of various NoSQL stores in critical application is still worth studying. Currently, cluster and backup technologies are common ways to improve the availability of NoSQL, but with little consideration for availability reduction in case of performance bottlenecks. To improve the availability of Riak TS effectively, a resource-aware availability enhancement mechanism is proposed. At first, the data is sampled according to time to obtain the correspondence between time and data. Meanwhile, the real-time resource consumption is recorded by Prometheus. Based on the sampling results, the prediction model is established. Then the resources required for the upcoming operation are predicted according to the time interval in the SQL statement, and the operation is evaluated by comparing with the remaining resources. Using the real hydrological sensor dataset as experimental data, the effectiveness of the mechanism is evaluated in terms of sensitivity, specificity and average availability, respectively. The results show that, through the availability enhancement mechanism, the specificity reaches 98.04%, and the sensitivity reaches 95.67%. The average availability has been raised from 40.33% to 95.67%. This resource-aware mechanism can effectively prevent potential availability problems through status of the resource, improving the availability of Riak TS. Moreover, with the rapid growth of users and data size, this resource-aware availability enhancement mechanism will become more accurate and useful.