Taurus

Abstract

Existing single-stream logging schemes are unsuitable for in-memory database management systems (DBMSs) as the single log is often a performance bottleneck. To overcome this problem, we present Taurus, an efficient parallel logging scheme that uses multiple log streams, and is compatible with both data and command logging. Taurus tracks and encodes transaction dependencies using a vector of log sequence numbers (LSNs). These vectors ensure that the dependencies are fully captured in logging and correctly enforced in recovery. Our experimental evaluation with an in-memory DBMS shows that Taurus's parallel logging achieves up to 9.9X and 2.9X speedups over single-streamed data logging and command logging, respectively. It also enables the DBMS to recover up to 22.9X and 75.6X faster than these baselines for data and command logging, respectively. We also compare Taurus with two state-of-the-art parallel logging schemes and show that the DBMS achieves up to 2.8X better performance on NVMe drives and 9.2X on HDDs.

DecLog: Decentralized Logging in Non-Volatile Memory for Time Series Database Systems

“…Haubenschild et al [26] extend GSN based logging and propose a Remote Flush Avoidance (RFA) protocol to reduce the dependency between logs. Taurus [72] features parallel logging and employs an LSN vector to track transaction dependencies. Although these studies realize synchronization effectively, additional protocol and instruction overheads are introduced.…”

“…Parallel logging has been proposed in recent studies [26,36,38,67,72,79]. However, only few commercial database systems distribute log entries in parallel threads within a single node, and even distributed commercial database systems still opt for a shared log [31].…”

“…Its write latency is comparable to that of DRAM, and the read latency is about 2-3 times that of DRAM. Therefore, recent studies [1,15,16,19,23,28,38,40,55,57,59,65,67,68,72] propose to store logs in NVM to improve throughput for OLTP systems. However, since TSDBMS transactions differ considerably from OLTP transactions, the use of NVM for TSDBMS logging still faces the unaddressed challenges:…”