Executing long-running transactions in synchronization-free main memory database systems

Powerful servers and growing DRAM capacities have initiated the development of main-memory DBMS, which avoid lock-based concurrency control by executing transactions serially on partitions. While allowing for unprecedentedly high throughput for homogeneous workloads consisting of short pre-canned transactions, heterogeneous workloads also containing long-running transactions cannot be executed efficiently. In this paper, we present our approach, called ‘tentative execution’, which retains the high throughput of serial execution for good-natured transactions while, at the same time, allowing for long-running and otherwise ill-natured transactions to be executed. To achieve this, we execute long-running transactions on a consistent snapshot and integrate their effects into the main database using a deterministic and short apply transaction. We discuss various implementation choices and offer an in-depth evaluation based on our main-memory database system prototype HyPer.