MESHJOIN*:实时数据仓库环境下的数据流更新算法

提出了一种新的实时数据仓库环境下的数据流更新算法——MESHJOIN*算法。算法的特性有:(1)关系R采用了分块和散列的组织形式,尽可能避免对当前连接无效元组的读取,减少连接操作所涉及元组的数量,从而提高连接算法的效率;(2)采用了多线程并发连接技术,并根据工程学原理,实现了连接操作和关系R读取操作的最佳调度,保证了连接算法效率的最大化;(3)根据当前系统的服务率和数据流元组的到达率之间的关系,合理调度实时元组和准实时元组的执行,保证了系统对实时元组的处理要求。实验结果表明,MESHJOIN*算法可以取得比MESHJOIN算法更好的性能。     

Efficient processing of streaming updates with archived master data in near-real-time data warehousing

In order to make timely and effective decisions, businesses need the latest information from data warehouse repositories. To keep these repositories up-to-date with respect to end user updates, near-real-time data integration is required. An important phase in near-real-time data integration is data transformation where the stream of updates is joined with disk-based master data. The stream-based algorithm MESHJOIN (Mesh Join) has been proposed to amortize disk access over fast streams. MESHJOIN makes no assumptions about the data distribution. In real-world applications, however, skewed distributions can be found, such as a stream of products sold, where certain products are sold more frequently than the remainder of the products. The question arises is how much does MESHJOIN lose in terms of performance by not adapting to data skew. In this paper we perform a rigorous experimental study analyzing the possible performance improvements while considering typical data distributions. For this purpose we design an algorithm Extended Hybrid Join (X-HYBRIDJOIN) that is complementary to MESHJOIN in that it can adapt to data skew and stores parts of the master data in memory permanently, reducing the disk access overhead significantly. We compare the performance of X-HYBRIDJOIN against the performance of MESHJOIN. We take several precautions to make sure the comparison is adequate and focuses on the utilization of data skew. The experiments show that considering data skew offers substantial room for performance gains that cannot be found in non-adaptive approaches such as MESHJOIN. We also present a cost model for X-HYBRIDJOIN, and based on that cost model, the algorithm is tuned.     

内存存储模型上的多表连接优化技术研究

分析了面向先进硬件平台上的数据库优化技术,提出了基于内存存储模型的多表连接查询处理优化技术,采用内存存储模型存储维表并对维表主键进行顺序化,从而使维表的主键与内存维表记录的内存偏移地址相一致,实现对维表记录的内存直接访问。通过列存储技术减少维表记录的访问宽度,进一步优化维表访问的cache性能。与基于SQL Server 2005的查询执行计划的连接算法、join index连接算法以及基于列存储模型的优化连接算法进行了实验比较和性能分析,结果表明:基于内存存储模型的多表连接算法在处理星型结构数据仓库多谓词、多连接的复杂查询时具有很好的性能,与join index相比不需要额外的空间开销,与列存储数据模型相比具有更好的兼容性和性能。     

Skewed distributions in semi-stream joins: How much can caching help?

Semi-stream join algorithms join a fast data stream with a disk-based relation. This is important, for example, in real-time data warehousing where a stream of transactions is joined with master data before loading it into a data warehouse. In many important scenarios, the stream input has a skewed distribution, which makes certain performance optimizations possible.We propose two such optimization techniques: (1) a caching technique for frequently used master data and (2) a technique for selective load shedding of stream tuples. The caching technique is fine-grained, operating on a tuple-level. Furthermore, it is generic in the sense that it can be applied to different semi-stream join algorithms to deal with data skew. We analyze it by combining it with various well-known semi-stream joins, and show that it improves the service rate by more than 40% for typical data with skewed distributions. The load shedding technique sheds the fraction of the stream that is most expensive to join. In contrast to existing approaches, the service rate improves under load shedding. We present experimental data showing significant improvements as compared to related approaches and perform a sensitivity analysis for various internal parameters.     

数据仓库中基于实体化辅助视图的视图增量维护

为了加快对大量数据的查询处理速度，通常在数据仓库以实视图方式存储数据，当基础数据发生变化时，这些实视图也必须随着更新，因而视图自维护和一致性维护成为数据仓库的重要问题。本文提出利用视图计算的中间结果创建辅助视图，在数据仓库中进行实体化，采用有效的增量维护算法计算实视图的精确变化，实现数据仓库视图自维护。     

基于统计的无阻塞连接算法

数据流上的关系查询处理技术是数据库研究领域的一大热点。优化无阻塞连接算法的关键在于提高内存连接阶段的效率。当内存空间满时,需要将内存数据刷新到外存相应分区,良好的刷新策略对于改进算法的性能至关重要。利用数据分布的特征,对关系连接的输出流,使用基于统计的方法,查找使用频率最低的元组,将使用频率较低的元组刷新到外存,以提高内存数据的效率。基于统计分析策略提高了刷新策略的准确性和效率及算法的适用范围。     

数据仓库中雪花模式的Skyline-Join查询

Skyline查询能够有效地实现多目标最优化,而数据仓库中的OLAP也是针对多维数据进行分析,因此,针对Skyline查询在数据仓库中的应用,提出了数据仓库中雪花模式的Skyline-Join查询算法.该算法首先将子维表M-Join父维表,然后渐进选择式地对事实表和父维表进行连接.每次连接之前都对事实表进行分组和组内Skyline计算,删除组内非Skyline元组,这样可以减少许多不必要的连接操作,使得查询效率大大提高.通过实验证明,在事实表元组数量逐渐变大和维表个数逐渐增多的情况下,提出的算法比先Join后Skyline计算的naive算法效率上有明显改善.     

一种基于路径连接的传感器网络内join算法

提出一种新的传感器网络内的路径连接实现算法,在连接路径中,通过将有效元组的选择与实际连接一定程度分离,在信息产生节点附近实现元组选择,在查询节点附近实现元组的真正连接,减少了元组的重复传输,有效降低了能量损耗,特别在针对事件监测系统中,针对突发性的连接选择系数变化或较大的情况,有效避免大量连接结果过早产生和传输的大量能量损耗.     

Consistency Algorithms for Multi-Source Warehouse View Maintenance

A warehouse is a data repository containing integrated information for efficient querying and analysis. Maintaining the consistency of warehouse data is challenging, especially if the data sources are autonomous and views of the data at the warehouse span multiple sources. Transactions containing multiple updates at one or more sources, e.g., batch updates, complicate the consistency problem. In this paper we identify and discuss three fundamental transaction processing scenarios for data warehousing. We define four levels of consistency for warehouse data and present a new family of algorithms, the Strobe family, that maintain consistency as the warehouse is updated, under the various warehousing scenarios. All of the algorithms are incremental and can handle a continuous and overlapping stream of updates from the sources. Our implementation shows that the algorithms are practical and realistic choices for a wide variety of update scenarios.     

数据仓库查询处理中的一种多表连接算法

在进行数据仓库的OLAP(onlineanalyticalprocessing,联机分析处理)查询处理时,经常会涉及到多表连接操作,因此,提高多表连接的性能就成了数据仓库领域的关键性问题.基于数据仓库的星型模式,给出了一种新的多表连接算法(M-Join).与传统关系数据库管理系统的多表连接查询处理相比,该算法充分考虑了数据仓库中的数据本身和多表连接的特点,采用对多个表进行一次性连接的方法,使得查询的性能有明显的改善.同时,还给出了算法的实验结果和分析.     

Faster joins, self-joins and multi-way joins using join indices

We propose a new algorithm, called Stripe-join, for performing a join given a join index. Stripe-join is inspired by an algorithm called ‘Jive-join’ developed by Li and Ross. Stripe-join makes a single sequential pass through each input relation, in addition to one pass through the join index and two passes through a set of temporary files that contain tuple identifiers but no input tuples. Stripe-join performs this efficiently even when the input relations are much larger than main memory, as long as the number of blocks in main memory is of the order of the square root of the number of blocks in the participating relations. Stripe-join is particularly efficient for self-joins. To our knowledge, Stripe-join is the first algorithm that, given a join index and a relation significantly larger than main memory, can perform a self-join with just a single pass over the input relation and without storing input tuples in intermediate files. Almost all the I/O is sequential, thus minimizing the impact of seek and rotational latency. The algorithm is resistant to data skew. It can also join multiple relations while still making only a single pass over each input relation. Using a detailed cost model, Stripe-join is analyzed and compared with competing algorithms. For large input relations, Stripe-join performs significantly better than Valduriez's algorithm and hash join algorithms. We demonstrate circumstances under which Stripe-join performs significantly better than Jive-join. Unlike Jive-join, Stripe-join makes no assumptions about the order of the join index.     

分布式数据仓库的一种聚集运算算法

考虑了分布式数据仓库的星型模式及数据分段的特点,在各站点对分组关键字进行编码压缩,并采用分布式聚集运算的方法,最后在请求站点生成完整的分组聚集结果,以降低站点内的排序费用,减少站点间传输的元组大小和数目,从而降低了站点内的处理代价和站点间的数据传输费用,提高了分布式数据仓库分组聚集运算的效率。     

三级存储系统中一种高效的连接算法

第3级存储器的联机使用为海量数据管理提供了一种廉价可行的方案.为了使数据库管理系统能够联机使用第3级存储设备,第3级存储设备上的关系操作算法,特别是连接操作算法是必须解决的关键问题之一.提出一种高效的连接算法.实验结果表明,该算法无论在性能方面还是在扩展性方面都优于以往算法,极大地减少了I/O代价.当数据量较大时,算法的性能不低于基于磁盘的连接算法.结果表明,第3级存储器可以像磁盘一样在海量数据库系统中联机使用,解决海量数据库存储和联机查询等关键问题.     

Distributed stream join query processing with semijoins

This paper addresses the distributed stream processing of window-based multi-way join queries considering the semijoin as a key join operator. In distributed stream processing, data streams arriving at remote sites need to be shipped to the processing site for query execution. This typically introduces high communication overhead. Our observation is that semijoin, effective in reducing communication overhead in distributed database query processing, can be also effective in distributed stream query processing. The challenge, however, lies in the streaming nature of the tuples, as it requires continuous and incremental processing of an unbounded sequence of tuples instead of one-time processing of a set of stored tuples. This paper describes our comprehensive work done to address the challenge. Specifically, we first propose a distributed stream join processing model that handles the issue of network delays introduced from the shipment of data streams, and allows for efficient batch processing. Then, based on the model, we propose join algorithms in a multi-way join case: first, one-way join algorithms for different combinations of join placement and join method and, then, multi-way join algorithms assuming linear join ordering. Regarding the join method, two distributed join methods are introduced: (1) simple join, in which full tuples are forwarded to the query processing site and (2) semijoin-based join, in which partial tuples are forwarded. A semijoin-based join can be executed with different possible semijoin strategies which incur different communication overheads. We present a complete set of join algorithms considering all possible semijoin strategies, and propose an optimization algorithm. The join algorithms are executed continuously in an incremental manner as tuples arrive, and never ship tuples redundantly. The optimization algorithm constructs an efficient multi-way join plan by using a greedy heuristic which adds to the plan one stream with the minimum join execution cost in each step. Through extensive experiments, we conduct comparative studies of the performance among the proposed one-way join algorithms and the efficiency of the generated plan between the optimization algorithm based on the greedy heuristic and the exhaustive search, respectively.     

大型压缩数据仓库上的Iceberg Cube算法

Iceberg Cube操作是OLAP(on-line analysis processing)分析中的一种重要操作.数据压缩技术在有效减小数据仓库所需的数据空间和提高数据处理性能方面的作用越来越明显.在压缩的数据仓库上,如何快速、有效地计算Iceberg Cube是目前亟待解决的问题.简要介绍了数据仓库的压缩,然后给出了在压缩数据仓库中计算Iceberg Cube的算法.实验结果表明,该算法的性能优于先在压缩数据上计算Cube再检查having条件这种方法.     

Load shedding for multi-way stream joins based on arrival order patterns

We address the problem of load shedding for continuous multi-way join queries over multiple data streams. When the arrival rates of tuples from data streams exceed the system capacity, a load shedding algorithm drops some subset of input tuples to avoid system overloads. To decide which tuples to drop among the input tuples, most existing load shedding algorithms determine the priority of each input tuple based on the frequency or some historical statistics of its join attribute value, and then drop tuples with the lowest priority. However, those value-based algorithms cannot determine the priorities of tuples properly in environments where join attribute values are unique and each join attribute value occurs at most once in each data stream. In this paper, we propose a load shedding algorithm specifically designed for such environments. The proposed load shedding algorithm determines the priority of each tuple based on the order of streams in which its join attribute value appears, rather than its join attribute value itself. Consequently, the priorities of tuples can be determined effectively in environments where join attribute values are unique and do not repeat. The experimental results show that the proposed algorithm outperforms the existing algorithms in such environments in terms of effectiveness and efficiency.     

Parallel multisource view maintenance

In a distributed environment, materialized views are used to integrate data from different information sources and then store them in some centralized location. In order to maintain such materialized views, maintenance queries need to be sent to information sources by the data warehouse management system. Due to the independence of the information sources and the data warehouse, concurrency issues are raised between the maintenance queries and the local update transactions at each information source. Recent solutions such as ECA and Strobe tackle such concurrent maintenance, however with the requirement of quiescence of the information sources. SWEEP and POSSE overcome this limitation by decomposing the global maintenance query into smaller subqueries to be sent to every information source and then performing conflict correction locally at the data warehouse. Note that all these previous approaches handle the data updates one at a time. Hence either some of the information sources or the data warehouse is likely to be idle during most of the maintenance process. In this paper, we propose that a set of updates should be maintained in parallel by several concurrent maintenance processes so that both the information sources as well as the warehouse would be utilized more fully throughout the maintenance process. This parallelism should then improve the overall maintenance performance. For this we have developed a parallel view maintenance algorithm, called PVM, that substantially improves upon the performance of previous maintenance approaches by handling a set of data updates at the same time. The parallel handling of a set of updates is orthogonal to the particular maintenance algorithm applied to the handling of each individual update. In order to perform parallel view maintenance, we have identified two critical issues that must be overcome: (1) detecting maintenance-concurrent data updates in a parallel mode and (2) correcting the problem that the data warehouse commit order may not correspond to the data warehouse update processing order due to parallel maintenance handling. In this work, we provide solutions to both issues. For the former, we insert a middle-layer timestamp assignment module for detecting maintenance-concurrent data updates without requiring any global clock synchronization. For the latter, we introduce the negative counter concept to solve the problem of variant orders of committing effects of data updates to the data warehouse. We provide a proof of the correctness of PVM that guarantees that our strategy indeed generates the correct final data warehouse state. We have implemented both SWEEP and PVM in our EVE data warehousing system. Our performance study demonstrates that a manyfold performance improvement is achieved by PVM over SWEEP.Received: 12 November 2001, Accepted: 18 December 2002, Published online: 31 July 2003This work was supported in part by the NSF NYI grant IIS-979624 and NSF CISE Instrumentation grant IRIS 97-29878 and NSF grant IIS-9988776.     

基于数据立方体的联机分析挖掘模型研究

本文提出一种联机分析挖掘模型,该模型基于数据仓库和其他各种类型文件生成的工作仓库,同时综合了联机分析处理多维分析的在线性、灵活性和数据挖掘处理的智能化特点,提高了传统模型的灵活性和智能化程度。     

数据仓库中基于密度的批量增量聚类算法

数据仓库为数据挖掘提供了很好的平台,当数据仓库中的数据发生变化时,原来挖掘出来的模式也要相应地进行更新。MartinEster等最先提出了增量聚类算法,但算法在增量聚类过程中,更新对象依次一个个地单独处理,而没有考虑更新对象之间的关系,效率较低。该文提出了基于DBSCAN算法的批量增量聚类算法,减少了对象的检索,提高了增量聚类的效率。     

基于Fermi架构的Join算法

在列数据库中,连接操作依然是最核心和最耗时的操作,GPU强大的计算能力可为此提供新的优化手段。基于Fermi架构,提出了新的Hash Join算法和Sort merge Join算法,其基本思想是充分利用该架构新增的缓存结构来减少连接操作的cache缺失率。与CUDA stream技术相结合,新算法在输出结果较多时可以有效地隐藏主存与显存间数据传输带来的延迟,进一步提升其执行效率。实验结果证实了基于Fcrmi架构的Hash Join算法处理偏抖数据的高效性及Sort merge Join算法的稳定性,并且通过比较表明,这两种算法的性能全面优于基于多核CPU充分优化的Join算法,最大加速2.4倍,在外键分布高偏抖时新的Hash Join算法的执行速度甚至达到每秒217M元组。