[Retracted] Load Balancing Optimization of In-Memory Database for Massive Information Processing of Internet of Things (IoTs)
Table 3
Load balancing optimization algorithm for in-memory database.
Step1: Set a threshold value T to compare the size of Q partition results generated from the first partition
Step2: In the second division process, the thread first compares the size and threshold T of the task before processing it. If the task is less than T, then the thread processes the task. If the task is greater than T, it is queued for D and not processed. So far, tasks less than T have been processed, while tasks greater than T have not been processed and are stored in D
Step3: Divide each task in queue D into T parts on average (T is the number of Reduce threads), and assign R parts of tasks to R threads for parallel processing
Step4: Get the final partition result after processing each task in queue D
