PostDoc, National University of Singapore
Optimize database system performance on modern hardware
My research focuses on designing and implementing high performance database management systems (DBMSs) with modern hardware support. The ultimate goal is to enable DBMSs to achieve scalable on-line transaction processing in the main-memory and multi-core settings.
Abstract: Multi-versioned database systems have the potential to significantly increase the amount of concurrency in transaction processing because they can avoid read-write conflicts. Unfortunately, the increase in concurrency usually comes at the cost of transaction serializability. If a database user requests full serializability, modern multi-versioned systems significantly constrain read-write concurrency among conflicting transactions and employ expensive synchronization patterns in their design. In main-memory multi-core settings, these additional constraints are so burdensome that multi-versioned systems are often significantly outperformed by single-version systems. We propose Bohm, a new concurrency control protocol for main-memory multi-versioned database systems. Bohm guarantees serializable execution while ensuring that reads never block writes. In addition, Bohm does not require reads to perform any book-keeping whatsoever, thereby avoiding the overhead of tracking reads via contended writes to shared memory. This leads to excellent scalability and performance in multi-core settings. Bohm has all the above characteristics without performing validation based concurrency control. Instead, it is pessimistic, and is therefore not prone to excessive aborts in the presence of contention. An experimental evaluation shows that Bohm performs well in both high contention and low contention settings, and is able to dramatically outperform state-of-the-art multi-versioned systems despite maintaining the full set of serializability guarantees.
Pub.: 02 Dec '15, Pinned: 27 Jul '17
Abstract: Multicore hardware demands software parallelism. Transaction processing workloads typically exhibit high concurrency, and, thus, provide ample opportunities for parallel execution. Unfortunately, because of the characteristics of the application, transaction processing systems must moderate and coordinate communication between independent agents; since it is notoriously difficult to implement high performing transaction processing systems that incur no communication whatsoever. As a result, transaction processing systems cannot always convert abundant, even embarrassing, request-level parallelism into execution parallelism due to communication bottlenecks. Transaction processing system designers must therefore find ways to achieve scalability while still allowing communication to occur. To this end, we identify three forms of communication in the system—unbounded, fixed, and cooperative—and argue that only the first type poses a fundamental threat to scalability. The other two types tend not impose obstacles to scalability, though they may reduce single-thread performance. We argue that proper analysis of communication patterns in any software system is a powerful tool for improving the system’s scalability. Then, we present and evaluate under a common framework techniques that attack significant sources of unbounded communication during transaction processing and sketch a solution for those that remain. The solutions we present affect fundamental services of any transaction processing engine, such as locking, logging, physical page accesses, and buffer pool frame accesses. They either reduce such communication through caching, downgrade it to a less-threatening type, or eliminate it completely through system design. We find that the later technique, revisiting the transaction processing architecture, is the most effective. The final design cuts unbounded communication by roughly an order of magnitude compared with the baseline, while exhibiting better scalability on multicore machines.
Pub.: 21 Apr '13, Pinned: 27 Jul '17
Abstract: Growing main memory sizes have facilitated database management systems that keep the entire database in main memory. The drastic performance improvements that came along with these in-memory systems have made it possible to reunite the two areas of online transaction processing (OLTP) and online analytical processing (OLAP): An emerging class of hybrid OLTP and OLAP database systems allows to process analytical queries directly on the transactional data. By offering arbitrarily current snapshots of the transactional data for OLAP, these systems enable real-time business intelligence. Despite memory sizes of several Terabytes in a single commodity server, RAM is still a precious resource: Since free memory can be used for intermediate results in query processing, the amount of memory determines query performance to a large extent. Consequently, we propose the compaction of memory-resident databases. Compaction consists of two tasks: First, separating the mutable working set from the immutable "frozen" data. Second, compressing the immutable data and optimizing it for efficient, memory-consumption-friendly snapshotting. Our approach reorganizes and compresses transactional data online and yet hardly affects the mission-critical OLTP throughput. This is achieved by unburdening the OLTP threads from all additional processing and performing these tasks asynchronously.
Pub.: 01 Aug '12, Pinned: 27 Jul '17
Abstract: Main-memory database systems for multicore servers can achieve excellent performance when processing massive volume of OLTP workloads. But crash-resilience mechanism, or namely logging-and-replay, can either degrade the performance of transaction processing or slow down the process of failure recovery. In this paper, we show that, by exploiting application semantics, it is possible to achieve speedy failure recovery without introducing any costly logging overhead to the execution of online transactions. We propose TARS, a parallel log-recovery mechanism that is specifically designed for lightweight, coarse-grained command-logging approach. TARS leverages a combination of static and dynamic analyses to parallelize the log replay: at compile time, TARS decomposes stored procedures by carefully analyzing dependencies within and across programs; at recovery time, a re-execution schedule with a high degree of parallelism is attained through lightweight one-pass scans over transaction parameter values. As such, recovery latency is remarkably minimized. We evaluated TARS in a main-memory database prototype running on a 40-core server. Compared to the state-of-the-art mechanisms, TARS yields significantly higher recovery rate without compromising the efficiency of transaction processing.
Pub.: 11 Apr '16, Pinned: 27 Jul '17
Abstract: The optimistic variants of MVCC (Multi-Version Concurrency Control) avoid blocking concurrent transactions at the cost of having a validation phase. Upon failure in the validation phase, the transaction is usually aborted and restarted from scratch. The "abort and restart" approach becomes a performance bottleneck for the use cases with high contention objects or long running transactions. In addition, restarting from scratch creates a negative feedback loop in the system, because the system incurs additional overhead that may create even further conflicts. In this paper, we propose a novel approach for conflict resolution in MVCC for in-memory databases. This low overhead approach summarizes the transaction programs in the form of a dependency graph. The dependency graph also contains the constructs used in the validation phase of the MVCC algorithm. Then, in the case of encountering conflicts among transactions, the conflict locations in the program are quickly detected, and the conflicting transactions are partially re-executed. This approach maximizes the reuse of the computations done in the initial execution round, and increases the transaction processing throughput.
Pub.: 01 Mar '16, Pinned: 27 Jul '17