A new memory allocator selection method for reducing memory fragmentation

Memory fragmentation is one of the most important problems preventing efficient memory usage. Many solutions have been proposed for external and internal memory fragmentation. The up-to-date solution to internal memory fragmentation is garbage collectors. However, garbage collectors cause serious performance impact, memory and energy consumption. Therefore, various memory allocators have been developed, and they have shown different behaviour according to memory layout of the software. Software developers need to test these allocators, and find an efficient one for their programs. Selection of memory allocator at software development stage does not guarantees an efficient solution, since different memory usage patterns, operating system conditions, and hardware specifications may need to another memory allocator. Therefore, a novel approach for dynamically deciding the best memory allocator for every application is proposed. The proposed solution tests each process with various memory allocators. After the testing, it selects an efficient memory allocator according to condition of operating system (OS). If OS runs out of memory, then it will select the most memory efficient allocator for new processes. If most of the CPU power is occupied, then it will select the fastest allocator. Otherwise, the balanced allocator is selected. According to test results, the proposed solution offers up to 58% less fragmented memory, and 90% faster memory operations. In average of 107 processes, it offers 7.16% less fragmented memory, and 1.79% faster memory operations. The test results also prove, the proposed solution presents optimum solution for different memory usage patterns, operating system conditions, and hardware specifications.