In-Memory Performance for Big Data

When a working set fits into memory, the overhead im-posed by the buffer pool renders traditional databases non-competitive with in-memory designs that sacrifice the ben-efits of a buffer pool. However, despite the large memory available with modern hardware, data skew, shifting work-loads, and complex mixed workloads make it difficult to guarantee that a working set will fit in memory. Hence, some recent work has focused on enabling in-memory databases to protect performance when the working data set almost fits in memory. Contrary to those prior efforts, we en-able buffer pool designs to match in-memory performance while supporting the “big data ” workloads that continue to require secondary storage, thus providing the best of both worlds. We introduce here a novel buffer pool de-sign that adapts pointer swizzling for references between system objects (as opposed to application objects), and uses it to practically eliminate buffer pool overheads for memory-resident data. Our implementation and experimental eval-uation demonstrate that we achieve graceful performance degradation when the working set grows to exceed the buffer pool size, and graceful improvement when the working set shrinks towards and below the memory and buffer pool sizes. 1