Biblio

Due to the "curse of dimensionality" problem, it is very expensive to process the nearest neighbor (NN) query in high-dimensional spaces; and hence, approximate approaches, such as Locality-Sensitive Hashing (LSH), are widely used for their theoretical guarantees and empirical performance. Current LSH-based approaches target at the L1 and L2 spaces, while as shown in previous work, the fractional distance metrics (Lp metrics with 0 textless p textless 1) can provide more insightful results than the usual L1 and L2 metrics for data mining and multimedia applications. However, none of the existing work can support multiple fractional distance metrics using one index. In this paper, we propose LazyLSH that answers approximate nearest neighbor queries for multiple Lp metrics with theoretical guarantees. Different from previous LSH approaches which need to build one dedicated index for every query space, LazyLSH uses a single base index to support the computations in multiple Lp spaces, significantly reducing the maintenance overhead. Extensive experiments show that LazyLSH provides more accurate results for approximate kNN search under fractional distance metrics.

By maintaining the data in main memory, in-memory databases dramatically reduce the I/O cost of transaction processing. However, for recovery purposes, in-memory systems still need to flush the log to disk, which incurs a substantial number of I/Os. Recently, command logging has been proposed to replace the traditional data log (e.g., ARIES logging) in in-memory databases. Instead of recording how the tuples are updated, command logging only tracks the transactions that are being executed, thereby effectively reducing the size of the log and improving the performance. However, when a failure occurs, all the transactions in the log after the last checkpoint must be redone sequentially and this significantly increases the cost of recovery. In this paper, we first extend the command logging technique to a distributed system, where all the nodes can perform their recovery in parallel. We show that in a distributed system, the only bottleneck of recovery caused by command logging is the synchronization process that attempts to resolve the data dependency among the transactions. We then propose an adaptive logging approach by combining data logging and command logging. The percentage of data logging versus command logging becomes a tuning knob between the performance of transaction processing and recovery to meet different OLTP requirements, and a model is proposed to guide such tuning. Our experimental study compares the performance of our proposed adaptive logging, ARIES-style data logging and command logging on top of H-Store. The results show that adaptive logging can achieve a 10x boost for recovery and a transaction throughput that is comparable to that of command logging.